diff --git a/services/intern-decision-serve/acceptance/systemone-2026-09-30/README.md b/services/intern-decision-serve/acceptance/systemone-2026-09-30/README.md new file mode 100644 index 0000000..cb2fed6 --- /dev/null +++ b/services/intern-decision-serve/acceptance/systemone-2026-09-30/README.md @@ -0,0 +1,31 @@ +# /v1/systemone acceptance — 0.1.1 on fv-ml1, 2026-09-30 + +Live service: `http://intern-decision.fv.internal:8033`, image `intern-decision-serve:0.1.1` +(built in `/opt/docker/src/intern-decision-serve-0.1.1`; 0.1.0 kept for rollback). + +## JevBench (the pass/fail line) + +JevBench v1.2.16 (5e95f23), its own `typesafe` adapter, over the 231 public items: + + TYPESAFE_ENDPOINT=http://intern-decision.fv.internal:8033 TYPESAFE_API_KEY=$(secret get intern-decision/api-token) \ + PYTHONPATH=/tmp/jevbench python3 -m jevbench.cli run --tasks datasets/public/{easy,original,hard}.jsonl \ + --adapter typesafe --results ... --ledger ... --raw-dir ... --price-in-per-m 0 --price-out-per-m 0 + +- **all 202/231, hard 83/111** — matches the expected numbers exactly. +- Row-by-row vs the bench's own runs r1..r4 (`bench-jev-2026-09-30/raw/out/intern-decision-4b-native/`): + **0 changed answers/probabilities across 924 rows.** +- Artifacts here: jb-results.jsonl, jb-summary.json, jb-ledger.jsonl, jb-manifest.json. +- The first-run finding: the response `model` must be a string — the runner hashes it into + its manifest and a dict crashed the manifest step. Fixed before the run above. + +## Controls (live) + +- wrong token → 401; 17 questions → 422 ("never chunked"); `images` → 422 "images not supported". +- token limit at the boundary: 7,167 → 200, **7,169 → 422** (binary search; "one token over"). +- `/decide/shared` positive control: 2 decisions, 1 call, fields q1/q2 — unchanged. + +## Memory (GPU 1 is packed beside scriberr) + +`gpu1-peak.csv`: per-process GPU 1 footprint, nvidia-smi at 0.2 s, container PID resolved via +docker inspect. Largest accepted request (16 noul questions, 7,167-token prompt) found by binary +search. **Peak 9,866 MiB ≤ 9,876 budget** (10 MiB inside). diff --git a/services/intern-decision-serve/acceptance/systemone-2026-09-30/gpu1-peak.csv b/services/intern-decision-serve/acceptance/systemone-2026-09-30/gpu1-peak.csv new file mode 100644 index 0000000..8129e5d --- /dev/null +++ b/services/intern-decision-serve/acceptance/systemone-2026-09-30/gpu1-peak.csv @@ -0,0 +1,200 @@ +1790797992.275219389,8814 +1790797992.528134517,8814 +1790797992.782442163,8814 +1790797993.036905110,8814 +1790797993.286749941,8814 +1790797993.537033867,8814 +1790797993.786867048,8814 +1790797994.036752380,8814 +1790797994.286926255,8814 +1790797994.537741487,8814 +1790797994.789283619,8814 +1790797995.042452140,8814 +1790797995.293783329,8814 +1790797995.542482796,8814 +1790797995.793476031,8814 +1790797996.045355027,8814 +1790797996.296609315,8814 +1790797996.547937744,8814 +1790797996.798163870,8814 +1790797997.049695221,8814 +1790797997.298911135,8814 +1790797997.550710369,8814 +1790797997.800802394,8814 +1790797998.049903715,8814 +1790797998.300049490,8814 +1790797998.549759419,8814 +1790797998.801462043,8814 +1790797999.056878512,8814 +1790797999.307552963,8814 +1790797999.557768548,8814 +1790797999.809323980,8814 +1790798000.059983611,8814 +1790798000.309552168,8814 +1790798000.560665795,8814 +1790798000.812160136,8814 +1790798001.063213401,8814 +1790798001.384773395,8814 +1790798001.635289845,8814 +1790798001.885701852,8814 +1790798002.137152933,8814 +1790798002.388003236,8814 +1790798002.648094442,8814 +1790798002.906676989,8814 +1790798003.165978375,8814 +1790798003.429988489,8814 +1790798003.692488103,8814 +1790798003.958026246,8814 +1790798004.217595275,8814 +1790798004.477616569,8814 +1790798004.735814792,8814 +1790798004.996301314,8814 +1790798005.257145290,8814 +1790798005.509242798,8814 +1790798005.761915074,8814 +1790798006.013522466,8814 +1790798006.261383403,8814 +1790798006.509839947,8814 +1790798006.759945281,8814 +1790798007.009325717,8814 +1790798007.259248908,8814 +1790798007.509074620,8814 +1790798007.757134139,8814 +1790798008.008389567,8814 +1790798008.258308358,8814 +1790798008.509782620,8814 +1790798008.762703667,8814 +1790798009.013959326,8814 +1790798009.265419116,8814 +1790798009.517643807,8814 +1790798009.768969296,8814 +1790798010.020060822,8814 +1790798010.272152710,8814 +1790798010.523524400,8814 +1790798010.775224453,8814 +1790798011.024711090,9100 +1790798011.274599741,9744 +1790798011.525630117,9784 +1790798011.773812528,8814 +1790798012.025444091,9858 +1790798012.273861224,8814 +1790798012.525675459,9858 +1790798012.779701041,9866 +1790798013.028327277,8814 +1790798013.278584943,8814 +1790798013.527081368,8814 +1790798013.782313714,9866 +1790798014.035618717,9726 +1790798014.285904413,9866 +1790798014.536302521,8814 +1790798014.783907885,8814 +1790798015.031635740,8814 +1790798015.287270531,8814 +1790798015.541581207,8814 +1790798015.793417652,8814 +1790798016.045879645,8814 +1790798016.298108495,8814 +1790798016.552988218,8814 +1790798016.806985959,8814 +1790798017.060516335,8814 +1790798017.310125383,8814 +1790798017.559041433,8814 +1790798017.810315731,8814 +1790798018.060587688,8814 +1790798018.307504823,8814 +1790798018.555932506,8814 +1790798018.803918245,8814 +1790798019.051076723,8814 +1790798019.297895457,8814 +1790798019.549199626,8814 +1790798019.797913533,8814 +1790798020.047429250,8814 +1790798020.295132915,8814 +1790798020.544559950,8814 +1790798020.791692269,8814 +1790798021.037941146,8814 +1790798021.282822426,8814 +1790798021.530796784,8814 +1790798021.777932732,8814 +1790798022.025570107,8814 +1790798022.273930959,8814 +1790798022.523677689,8814 +1790798022.772933543,8814 +1790798023.021416457,8814 +1790798023.269167743,8814 +1790798023.520772785,8814 +1790798023.769215739,8814 +1790798024.015848411,8814 +1790798024.261590892,8814 +1790798024.505993137,8814 +1790798024.754091567,8814 +1790798024.998300749,8814 +1790798025.244962791,8814 +1790798025.489797311,8814 +1790798025.741631437,8814 +1790798025.993321750,8814 +1790798026.241268468,8814 +1790798026.489480899,8814 +1790798026.736946791,8814 +1790798026.982128625,8814 +1790798027.231035775,8814 +1790798027.477779468,8814 +1790798027.723650310,8814 +1790798027.968758813,8814 +1790798028.215362575,8814 +1790798028.459432046,8814 +1790798028.707014809,8814 +1790798028.953977985,8814 +1790798029.207485681,8814 +1790798029.453894320,8814 +1790798029.699582020,8814 +1790798029.947610629,8814 +1790798030.194115159,8814 +1790798030.443251171,8814 +1790798030.691241730,8814 +1790798030.937547808,8814 +1790798031.186285985,8814 +1790798031.438036740,8814 +1790798031.689127666,8814 +1790798031.936299374,8814 +1790798032.185773701,8814 +1790798032.435570711,8814 +1790798032.685758836,8814 +1790798032.937936956,8814 +1790798033.190218976,8814 +1790798033.442438916,8814 +1790798033.692587671,8814 +1790798033.945721401,8814 +1790798034.196543834,8814 +1790798034.446658779,8814 +1790798034.699299884,8814 +1790798034.948464907,8814 +1790798035.200068089,8814 +1790798035.449859579,8814 +1790798035.701269039,8814 +1790798035.948841423,8814 +1790798036.199208040,8814 +1790798036.448192100,8814 +1790798036.699020923,8814 +1790798036.950084909,8814 +1790798037.202002205,8814 +1790798037.454016452,8814 +1790798037.704971137,8814 +1790798037.953616153,8814 +1790798038.203430874,8814 +1790798038.453393196,8814 +1790798038.702761391,8814 +1790798038.952274678,8814 +1790798039.201829446,8814 +1790798039.453035373,8814 +1790798039.704085409,8814 +1790798039.953368553,8814 +1790798040.202695878,8814 +1790798040.455344553,8814 +1790798040.707320040,8814 +1790798040.967230153,8814 +1790798041.216682550,8834 +1790798041.466944055,8834 +1790798041.717427714,8836 +1790798041.965756467,8836 +1790798042.217163337,8836 diff --git a/services/intern-decision-serve/acceptance/systemone-2026-09-30/health-end.json b/services/intern-decision-serve/acceptance/systemone-2026-09-30/health-end.json new file mode 100644 index 0000000..e32fe86 --- /dev/null +++ b/services/intern-decision-serve/acceptance/systemone-2026-09-30/health-end.json @@ -0,0 +1 @@ +{"status":"ok","model":{"name":"Intern-Decision-4B","source":"internlm/Intern-Decision-4B","revision":"0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd","checkpoint":"/hf/hub/models--internlm--Intern-Decision-4B/snapshots/0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd","inference_py_sha256":"c904e2c67ca0775621a22375ee373d2ba30b52117cda870c6c9ef74143b29863","temperature":1.99241824,"dtype":"bfloat16","attn_implementation":"sdpa","device":"cuda","max_length":7168,"torch_version":"2.10.0+cu128","transformers_version":"5.17.0","vision_tower":"removed","device_name":"NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition","allocated_gib":7.937,"reserved_gib":7.969,"max_reserved_gib":8.861},"vram_cap_gib":9.0,"max_tokens":7168,"max_decisions":64,"max_questions_per_call":16,"chunking":"/decide/shared questions are packed greedily, in request order, into calls of at most 16 (1-16, 17-32, ...); each call is one prompt, so the questions in a call are asked together. With orderings, ordering k of every decision forms wave k, packed the same way.","workloads":[],"endpoints":["/decide","/decide/shared","/v1/systemone"],"systemone":{"max_questions":16,"chunking":"none","images":"not supported","max_tokens":7168}} \ No newline at end of file diff --git a/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-ledger.jsonl b/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-ledger.jsonl new file mode 100644 index 0000000..267c071 --- /dev/null +++ b/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-ledger.jsonl @@ -0,0 +1,463 @@ +{"event": "cap", "cap_usd": 15.0, "ts": 1790798238.6542706} +{"event": "reserve", "reservation_id": "627a98c1f49d4a2ab2202e33bd5e938a", "reserved_usd": 0.02, "ts": 1790798238.659769, "meta": {"task_id": "easy-intent-00", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "627a98c1f49d4a2ab2202e33bd5e938a", "charged_usd": 0.0, "ts": 1790798238.7287285, "meta": {"task_id": "easy-intent-00", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "02401994701543589d4291234d69ef3f", "reserved_usd": 0.02, "ts": 1790798238.7351491, "meta": {"task_id": "easy-intent-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "02401994701543589d4291234d69ef3f", "charged_usd": 0.0, "ts": 1790798238.7907438, "meta": {"task_id": "easy-intent-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8496997e2ff548b1b05335330fcd9ea9", "reserved_usd": 0.02, "ts": 1790798238.7973802, "meta": {"task_id": "easy-intent-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8496997e2ff548b1b05335330fcd9ea9", "charged_usd": 0.0, "ts": 1790798238.853179, "meta": {"task_id": "easy-intent-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ded7b1fe89c34f31bbbf02e2534c991e", "reserved_usd": 0.02, "ts": 1790798238.8586168, "meta": {"task_id": "easy-intent-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ded7b1fe89c34f31bbbf02e2534c991e", "charged_usd": 0.0, "ts": 1790798238.913867, "meta": {"task_id": "easy-intent-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "f46525e0b46c4b8eab7dd897de347312", "reserved_usd": 0.02, "ts": 1790798238.9194748, "meta": {"task_id": "easy-intent-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "f46525e0b46c4b8eab7dd897de347312", "charged_usd": 0.0, "ts": 1790798238.9748917, "meta": {"task_id": "easy-intent-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "cd4a90873da0447986eb9fc1fa8a7edc", "reserved_usd": 0.02, "ts": 1790798238.9817402, "meta": {"task_id": "easy-intent-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "cd4a90873da0447986eb9fc1fa8a7edc", "charged_usd": 0.0, "ts": 1790798239.037384, "meta": {"task_id": "easy-intent-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "90dfdeaf6dcc430ebf3fbb545d71af66", "reserved_usd": 0.02, "ts": 1790798239.0425768, "meta": {"task_id": "easy-intent-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "90dfdeaf6dcc430ebf3fbb545d71af66", "charged_usd": 0.0, "ts": 1790798239.0989919, "meta": {"task_id": "easy-intent-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "91c9fb3e9abe40e1bef4bbe69627a5cf", "reserved_usd": 0.02, "ts": 1790798239.1056275, "meta": {"task_id": "easy-intent-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "91c9fb3e9abe40e1bef4bbe69627a5cf", "charged_usd": 0.0, "ts": 1790798239.1618407, "meta": {"task_id": "easy-intent-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "b488340196e04156a49d04ddb287aefc", "reserved_usd": 0.02, "ts": 1790798239.1678061, "meta": {"task_id": "easy-intent-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "b488340196e04156a49d04ddb287aefc", "charged_usd": 0.0, "ts": 1790798239.2294233, "meta": {"task_id": "easy-intent-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "3d27fd1582864b4b8b96ff92fef84ca4", "reserved_usd": 0.02, "ts": 1790798239.23515, "meta": {"task_id": "easy-intent-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "3d27fd1582864b4b8b96ff92fef84ca4", "charged_usd": 0.0, "ts": 1790798239.2915626, "meta": {"task_id": "easy-intent-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "b825d9d8688d47ecb8366eb2990822dd", "reserved_usd": 0.02, "ts": 1790798239.29729, "meta": {"task_id": "easy-intent-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "b825d9d8688d47ecb8366eb2990822dd", "charged_usd": 0.0, "ts": 1790798239.354575, "meta": {"task_id": "easy-intent-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "0b0f5fecf87c481491a16a700fb9ca0c", "reserved_usd": 0.02, "ts": 1790798239.3625104, "meta": {"task_id": "easy-intent-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "0b0f5fecf87c481491a16a700fb9ca0c", "charged_usd": 0.0, "ts": 1790798239.4200366, "meta": {"task_id": "easy-intent-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "6df98a853d244072863b8b2861574ccb", "reserved_usd": 0.02, "ts": 1790798239.4266734, "meta": {"task_id": "easy-fact-00", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "6df98a853d244072863b8b2861574ccb", "charged_usd": 0.0, "ts": 1790798239.482841, "meta": {"task_id": "easy-fact-00", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "cd1d6857390043ecab985ad377067398", "reserved_usd": 0.02, "ts": 1790798239.4909654, "meta": {"task_id": "easy-fact-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "cd1d6857390043ecab985ad377067398", "charged_usd": 0.0, "ts": 1790798239.5481172, "meta": {"task_id": "easy-fact-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "82b538a3f5814f6b945aa2e2bd71e3ba", "reserved_usd": 0.02, "ts": 1790798239.5535345, "meta": {"task_id": "easy-fact-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "82b538a3f5814f6b945aa2e2bd71e3ba", "charged_usd": 0.0, "ts": 1790798239.60872, "meta": {"task_id": "easy-fact-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "998b3c8268464b97ad7f07ae6cd37245", "reserved_usd": 0.02, "ts": 1790798239.6136498, "meta": {"task_id": "easy-fact-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "998b3c8268464b97ad7f07ae6cd37245", "charged_usd": 0.0, "ts": 1790798239.6688125, "meta": {"task_id": "easy-fact-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "9ba5ae8d25864c09b80506a6734f2c09", "reserved_usd": 0.02, "ts": 1790798239.6746755, "meta": {"task_id": "easy-fact-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "9ba5ae8d25864c09b80506a6734f2c09", "charged_usd": 0.0, "ts": 1790798239.7303052, "meta": {"task_id": "easy-fact-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8a1888e270d84346b1c79aded73ab240", "reserved_usd": 0.02, "ts": 1790798239.735886, "meta": {"task_id": "easy-fact-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8a1888e270d84346b1c79aded73ab240", "charged_usd": 0.0, "ts": 1790798239.792064, "meta": {"task_id": "easy-fact-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "3c2db9c937674ac988bfea4cce66b998", "reserved_usd": 0.02, "ts": 1790798239.7976592, "meta": {"task_id": "easy-fact-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "3c2db9c937674ac988bfea4cce66b998", "charged_usd": 0.0, "ts": 1790798239.8525443, "meta": {"task_id": "easy-fact-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "907e9b4ff28f417885fb4dbf213f3374", "reserved_usd": 0.02, "ts": 1790798239.8572328, "meta": {"task_id": "easy-fact-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "907e9b4ff28f417885fb4dbf213f3374", "charged_usd": 0.0, "ts": 1790798239.9116766, "meta": {"task_id": "easy-fact-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "5edcebf25ad149b3a23990fbfce64062", "reserved_usd": 0.02, "ts": 1790798239.9171984, "meta": {"task_id": "easy-fact-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "5edcebf25ad149b3a23990fbfce64062", "charged_usd": 0.0, "ts": 1790798239.9719565, "meta": {"task_id": "easy-fact-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "5447c35bfcad4656bed468ab65dbd914", "reserved_usd": 0.02, "ts": 1790798239.9771302, "meta": {"task_id": "easy-fact-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "5447c35bfcad4656bed468ab65dbd914", "charged_usd": 0.0, "ts": 1790798240.0333383, "meta": {"task_id": "easy-fact-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "72df9adec7e4429c83835c59521907c4", "reserved_usd": 0.02, "ts": 1790798240.038263, "meta": {"task_id": "easy-fact-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "72df9adec7e4429c83835c59521907c4", "charged_usd": 0.0, "ts": 1790798240.093354, "meta": {"task_id": "easy-fact-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ff694a086a184380aea7be8c5955475c", "reserved_usd": 0.02, "ts": 1790798240.0989747, "meta": {"task_id": "easy-fact-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ff694a086a184380aea7be8c5955475c", "charged_usd": 0.0, "ts": 1790798240.1555765, "meta": {"task_id": "easy-fact-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "1f6cc94c89f241d09adc1ce8f2d9905e", "reserved_usd": 0.02, "ts": 1790798240.1624048, "meta": {"task_id": "easy-extraction-00", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "1f6cc94c89f241d09adc1ce8f2d9905e", "charged_usd": 0.0, "ts": 1790798240.2209032, "meta": {"task_id": "easy-extraction-00", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "3d21186f31bc460aaefd2fa3abcbfc90", "reserved_usd": 0.02, "ts": 1790798240.2279031, "meta": {"task_id": "easy-extraction-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "3d21186f31bc460aaefd2fa3abcbfc90", "charged_usd": 0.0, "ts": 1790798240.2884357, "meta": {"task_id": "easy-extraction-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c717ece9d21b4b50a00fd9ef73ca5b7d", "reserved_usd": 0.02, "ts": 1790798240.295053, "meta": {"task_id": "easy-extraction-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c717ece9d21b4b50a00fd9ef73ca5b7d", "charged_usd": 0.0, "ts": 1790798240.3511472, "meta": {"task_id": "easy-extraction-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "5926fbb268ef4a2485b27687a278be21", "reserved_usd": 0.02, "ts": 1790798240.3575783, "meta": {"task_id": "easy-extraction-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "5926fbb268ef4a2485b27687a278be21", "charged_usd": 0.0, "ts": 1790798240.4122655, "meta": {"task_id": "easy-extraction-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "6df3928395874746810431451410aeb0", "reserved_usd": 0.02, "ts": 1790798240.4185011, "meta": {"task_id": "easy-extraction-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "6df3928395874746810431451410aeb0", "charged_usd": 0.0, "ts": 1790798240.4728284, "meta": {"task_id": "easy-extraction-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8df865828c454e20afe04e1f256924b2", "reserved_usd": 0.02, "ts": 1790798240.47774, "meta": {"task_id": "easy-extraction-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8df865828c454e20afe04e1f256924b2", "charged_usd": 0.0, "ts": 1790798240.5319407, "meta": {"task_id": "easy-extraction-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "bff6a58af90a44d8b3cb192862f61850", "reserved_usd": 0.02, "ts": 1790798240.5364041, "meta": {"task_id": "easy-extraction-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "bff6a58af90a44d8b3cb192862f61850", "charged_usd": 0.0, "ts": 1790798240.5919433, "meta": {"task_id": "easy-extraction-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "b62d354adbb446e5bf77867119297410", "reserved_usd": 0.02, "ts": 1790798240.598612, "meta": {"task_id": "easy-extraction-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "b62d354adbb446e5bf77867119297410", "charged_usd": 0.0, "ts": 1790798240.6554232, "meta": {"task_id": "easy-extraction-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "fdbddecb888448d0a266fcabe5fc788d", "reserved_usd": 0.02, "ts": 1790798240.660763, "meta": {"task_id": "easy-extraction-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "fdbddecb888448d0a266fcabe5fc788d", "charged_usd": 0.0, "ts": 1790798240.7164695, "meta": {"task_id": "easy-extraction-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "e5b4d6d8ed184280999b0f3a18eee3dd", "reserved_usd": 0.02, "ts": 1790798240.7218425, "meta": {"task_id": "easy-extraction-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "e5b4d6d8ed184280999b0f3a18eee3dd", "charged_usd": 0.0, "ts": 1790798240.7768583, "meta": {"task_id": "easy-extraction-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ba1245c612df4eab8dc217a2f1eff716", "reserved_usd": 0.02, "ts": 1790798240.7822607, "meta": {"task_id": "easy-extraction-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ba1245c612df4eab8dc217a2f1eff716", "charged_usd": 0.0, "ts": 1790798240.837374, "meta": {"task_id": "easy-extraction-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "9250c3d4fb064cffafc80792394bd1e0", "reserved_usd": 0.02, "ts": 1790798240.8424635, "meta": {"task_id": "easy-extraction-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "9250c3d4fb064cffafc80792394bd1e0", "charged_usd": 0.0, "ts": 1790798240.896149, "meta": {"task_id": "easy-extraction-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c41ddf75211545c98fa162919f55e0ce", "reserved_usd": 0.02, "ts": 1790798240.9015346, "meta": {"task_id": "easy-tool_selection-00", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c41ddf75211545c98fa162919f55e0ce", "charged_usd": 0.0, "ts": 1790798240.9560153, "meta": {"task_id": "easy-tool_selection-00", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "df2403f1185c4f1dbb519b99c8047e3a", "reserved_usd": 0.02, "ts": 1790798240.9615202, "meta": {"task_id": "easy-tool_selection-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "df2403f1185c4f1dbb519b99c8047e3a", "charged_usd": 0.0, "ts": 1790798241.0160067, "meta": {"task_id": "easy-tool_selection-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "e6e3d42f53ff4872b2c1e4d44cef9de9", "reserved_usd": 0.02, "ts": 1790798241.0210505, "meta": {"task_id": "easy-tool_selection-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "e6e3d42f53ff4872b2c1e4d44cef9de9", "charged_usd": 0.0, "ts": 1790798241.0752804, "meta": {"task_id": "easy-tool_selection-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "4bfe63af4b8245faad9472958e737e06", "reserved_usd": 0.02, "ts": 1790798241.080178, "meta": {"task_id": "easy-tool_selection-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "4bfe63af4b8245faad9472958e737e06", "charged_usd": 0.0, "ts": 1790798241.1351855, "meta": {"task_id": "easy-tool_selection-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d6fc829ca377459da460baf775b130aa", "reserved_usd": 0.02, "ts": 1790798241.140824, "meta": {"task_id": "easy-tool_selection-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d6fc829ca377459da460baf775b130aa", "charged_usd": 0.0, "ts": 1790798241.1957126, "meta": {"task_id": "easy-tool_selection-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "2a3aac628b6a4b42a104807395d50f3a", "reserved_usd": 0.02, "ts": 1790798241.2012322, "meta": {"task_id": "easy-tool_selection-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "2a3aac628b6a4b42a104807395d50f3a", "charged_usd": 0.0, "ts": 1790798241.2563422, "meta": {"task_id": "easy-tool_selection-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "cd295b53a77e4d0e9cfd15a9cb4a1225", "reserved_usd": 0.02, "ts": 1790798241.2648437, "meta": {"task_id": "easy-tool_selection-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "cd295b53a77e4d0e9cfd15a9cb4a1225", "charged_usd": 0.0, "ts": 1790798241.3203056, "meta": {"task_id": "easy-tool_selection-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "5e45b6179caf4f4ca5e9f7b6844debe9", "reserved_usd": 0.02, "ts": 1790798241.3272476, "meta": {"task_id": "easy-tool_selection-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "5e45b6179caf4f4ca5e9f7b6844debe9", "charged_usd": 0.0, "ts": 1790798241.3872619, "meta": {"task_id": "easy-tool_selection-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "0ada330940944cb49887ac830788fb28", "reserved_usd": 0.02, "ts": 1790798241.393653, "meta": {"task_id": "easy-tool_selection-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "0ada330940944cb49887ac830788fb28", "charged_usd": 0.0, "ts": 1790798241.4557726, "meta": {"task_id": "easy-tool_selection-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "0dd626e5501c468aa379bdb7cac77078", "reserved_usd": 0.02, "ts": 1790798241.4615843, "meta": {"task_id": "easy-tool_selection-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "0dd626e5501c468aa379bdb7cac77078", "charged_usd": 0.0, "ts": 1790798241.5213861, "meta": {"task_id": "easy-tool_selection-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "f6277bda16a949bca0ddaf6cc1bfd462", "reserved_usd": 0.02, "ts": 1790798241.5266328, "meta": {"task_id": "easy-tool_selection-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "f6277bda16a949bca0ddaf6cc1bfd462", "charged_usd": 0.0, "ts": 1790798241.5828376, "meta": {"task_id": "easy-tool_selection-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "2339557e289e4923bdb4cfa54c4f1933", "reserved_usd": 0.02, "ts": 1790798241.5880659, "meta": {"task_id": "easy-tool_selection-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "2339557e289e4923bdb4cfa54c4f1933", "charged_usd": 0.0, "ts": 1790798241.644939, "meta": {"task_id": "easy-tool_selection-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "5cd797b8a4d44d0cb18a597cbe2aa6a7", "reserved_usd": 0.02, "ts": 1790798241.6497111, "meta": {"task_id": "original-policy-01-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "5cd797b8a4d44d0cb18a597cbe2aa6a7", "charged_usd": 0.0, "ts": 1790798241.7063174, "meta": {"task_id": "original-policy-01-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "4fd8c4ef3c52480ebfa5cda9fb27dfe1", "reserved_usd": 0.02, "ts": 1790798241.7118456, "meta": {"task_id": "original-policy-01-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "4fd8c4ef3c52480ebfa5cda9fb27dfe1", "charged_usd": 0.0, "ts": 1790798241.7674985, "meta": {"task_id": "original-policy-01-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "1ff223f09d1b445da04b2c57ffa4e7f1", "reserved_usd": 0.02, "ts": 1790798241.7726874, "meta": {"task_id": "original-policy-02-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "1ff223f09d1b445da04b2c57ffa4e7f1", "charged_usd": 0.0, "ts": 1790798241.8298485, "meta": {"task_id": "original-policy-02-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "bb2eda3f508e4b0abf95a13e38e50ae1", "reserved_usd": 0.02, "ts": 1790798241.835516, "meta": {"task_id": "original-policy-02-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "bb2eda3f508e4b0abf95a13e38e50ae1", "charged_usd": 0.0, "ts": 1790798241.8921857, "meta": {"task_id": "original-policy-02-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "0e821f6aae0d41299c2d0e847b2e9033", "reserved_usd": 0.02, "ts": 1790798241.8980367, "meta": {"task_id": "original-policy-03-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "0e821f6aae0d41299c2d0e847b2e9033", "charged_usd": 0.0, "ts": 1790798241.9547124, "meta": {"task_id": "original-policy-03-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "1a14b85f47c04dfab3cff731fbe837a3", "reserved_usd": 0.02, "ts": 1790798241.9605222, "meta": {"task_id": "original-policy-03-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "1a14b85f47c04dfab3cff731fbe837a3", "charged_usd": 0.0, "ts": 1790798242.0166733, "meta": {"task_id": "original-policy-03-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "f38b86f2cf4b4b39bd9fc1940eca27cc", "reserved_usd": 0.02, "ts": 1790798242.0216513, "meta": {"task_id": "original-policy-04-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "f38b86f2cf4b4b39bd9fc1940eca27cc", "charged_usd": 0.0, "ts": 1790798242.080262, "meta": {"task_id": "original-policy-04-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "1fb82d5e796c49749a3de3fa04ac2535", "reserved_usd": 0.02, "ts": 1790798242.0854135, "meta": {"task_id": "original-policy-04-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "1fb82d5e796c49749a3de3fa04ac2535", "charged_usd": 0.0, "ts": 1790798242.1419184, "meta": {"task_id": "original-policy-04-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "540e6dceee3d4c9586738b27256ea407", "reserved_usd": 0.02, "ts": 1790798242.148545, "meta": {"task_id": "original-policy-05-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "540e6dceee3d4c9586738b27256ea407", "charged_usd": 0.0, "ts": 1790798242.2055926, "meta": {"task_id": "original-policy-05-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "96dc57ac32e0447db10fd223b0618d76", "reserved_usd": 0.02, "ts": 1790798242.2112067, "meta": {"task_id": "original-policy-05-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "96dc57ac32e0447db10fd223b0618d76", "charged_usd": 0.0, "ts": 1790798242.2713304, "meta": {"task_id": "original-policy-05-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ecd1feeef8204d47888c06f44c722c71", "reserved_usd": 0.02, "ts": 1790798242.2769933, "meta": {"task_id": "original-policy-06-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ecd1feeef8204d47888c06f44c722c71", "charged_usd": 0.0, "ts": 1790798242.335612, "meta": {"task_id": "original-policy-06-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "46e285e06272424b94790f548e4932cc", "reserved_usd": 0.02, "ts": 1790798242.3420017, "meta": {"task_id": "original-policy-06-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "46e285e06272424b94790f548e4932cc", "charged_usd": 0.0, "ts": 1790798242.3988416, "meta": {"task_id": "original-policy-06-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "34f3ba13739042c1874dfa79488b1c7a", "reserved_usd": 0.02, "ts": 1790798242.4048462, "meta": {"task_id": "original-intent-01-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "34f3ba13739042c1874dfa79488b1c7a", "charged_usd": 0.0, "ts": 1790798242.461449, "meta": {"task_id": "original-intent-01-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "18abef7528cc432c827b208e64c99274", "reserved_usd": 0.02, "ts": 1790798242.4665883, "meta": {"task_id": "original-intent-01-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "18abef7528cc432c827b208e64c99274", "charged_usd": 0.0, "ts": 1790798242.5283933, "meta": {"task_id": "original-intent-01-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "4b8576830c2347ba90d62c7ca9c2dbe9", "reserved_usd": 0.02, "ts": 1790798242.5338404, "meta": {"task_id": "original-intent-02-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "4b8576830c2347ba90d62c7ca9c2dbe9", "charged_usd": 0.0, "ts": 1790798242.5910866, "meta": {"task_id": "original-intent-02-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "834ced07f510403f9328178b9fbbcfbd", "reserved_usd": 0.02, "ts": 1790798242.595736, "meta": {"task_id": "original-intent-02-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "834ced07f510403f9328178b9fbbcfbd", "charged_usd": 0.0, "ts": 1790798242.6522183, "meta": {"task_id": "original-intent-02-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "bbf883719d9848759ba8109118f00754", "reserved_usd": 0.02, "ts": 1790798242.6572573, "meta": {"task_id": "original-intent-03-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "bbf883719d9848759ba8109118f00754", "charged_usd": 0.0, "ts": 1790798242.7132146, "meta": {"task_id": "original-intent-03-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "18ebc30458234411914fbbe439526c19", "reserved_usd": 0.02, "ts": 1790798242.7182438, "meta": {"task_id": "original-intent-03-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "18ebc30458234411914fbbe439526c19", "charged_usd": 0.0, "ts": 1790798242.7739732, "meta": {"task_id": "original-intent-03-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "106a7e836b8c4c5d9170bd7a4e3086a2", "reserved_usd": 0.02, "ts": 1790798242.7795796, "meta": {"task_id": "original-intent-04-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "106a7e836b8c4c5d9170bd7a4e3086a2", "charged_usd": 0.0, "ts": 1790798242.8360767, "meta": {"task_id": "original-intent-04-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ee6707878b3d48c3b4e5821117964101", "reserved_usd": 0.02, "ts": 1790798242.8406117, "meta": {"task_id": "original-intent-04-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ee6707878b3d48c3b4e5821117964101", "charged_usd": 0.0, "ts": 1790798242.8976364, "meta": {"task_id": "original-intent-04-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "9cc0d7925d404f188490abd3352850aa", "reserved_usd": 0.02, "ts": 1790798242.9027164, "meta": {"task_id": "original-intent-05-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "9cc0d7925d404f188490abd3352850aa", "charged_usd": 0.0, "ts": 1790798242.9647396, "meta": {"task_id": "original-intent-05-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "12e52d510aeb4f09b86135270ac18e17", "reserved_usd": 0.02, "ts": 1790798242.9718177, "meta": {"task_id": "original-intent-05-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "12e52d510aeb4f09b86135270ac18e17", "charged_usd": 0.0, "ts": 1790798243.0316572, "meta": {"task_id": "original-intent-05-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8d9b9f1c12aa4c9abde5d4ef31f3bb54", "reserved_usd": 0.02, "ts": 1790798243.039179, "meta": {"task_id": "original-intent-06-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8d9b9f1c12aa4c9abde5d4ef31f3bb54", "charged_usd": 0.0, "ts": 1790798243.0977566, "meta": {"task_id": "original-intent-06-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "329b5295f07e472aae91bbd401fdfe96", "reserved_usd": 0.02, "ts": 1790798243.105193, "meta": {"task_id": "original-intent-06-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "329b5295f07e472aae91bbd401fdfe96", "charged_usd": 0.0, "ts": 1790798243.1646116, "meta": {"task_id": "original-intent-06-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "e20420aefc4a438facaeb54392857192", "reserved_usd": 0.02, "ts": 1790798243.1702683, "meta": {"task_id": "original-ordinal-01-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "e20420aefc4a438facaeb54392857192", "charged_usd": 0.0, "ts": 1790798243.2283697, "meta": {"task_id": "original-ordinal-01-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "08e230ff8b884f5d8b3de2ae0d39b9c5", "reserved_usd": 0.02, "ts": 1790798243.2347386, "meta": {"task_id": "original-ordinal-01-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "08e230ff8b884f5d8b3de2ae0d39b9c5", "charged_usd": 0.0, "ts": 1790798243.2923536, "meta": {"task_id": "original-ordinal-01-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "bed9d3e7be274dea9e829079d6343762", "reserved_usd": 0.02, "ts": 1790798243.2975664, "meta": {"task_id": "original-ordinal-02-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "bed9d3e7be274dea9e829079d6343762", "charged_usd": 0.0, "ts": 1790798243.3579712, "meta": {"task_id": "original-ordinal-02-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8e35d2e70440427dbdd8d7342c5be7a7", "reserved_usd": 0.02, "ts": 1790798243.3637314, "meta": {"task_id": "original-ordinal-02-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8e35d2e70440427dbdd8d7342c5be7a7", "charged_usd": 0.0, "ts": 1790798243.420809, "meta": {"task_id": "original-ordinal-02-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c23ffe98794b4914bd866441d34144ab", "reserved_usd": 0.02, "ts": 1790798243.426488, "meta": {"task_id": "original-ordinal-03-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c23ffe98794b4914bd866441d34144ab", "charged_usd": 0.0, "ts": 1790798243.483883, "meta": {"task_id": "original-ordinal-03-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d1600857cb8341d79e70b9f6bea0093d", "reserved_usd": 0.02, "ts": 1790798243.4884024, "meta": {"task_id": "original-ordinal-03-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d1600857cb8341d79e70b9f6bea0093d", "charged_usd": 0.0, "ts": 1790798243.5448146, "meta": {"task_id": "original-ordinal-03-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "60d75366f8ad4f5f8e8452306ecbd29d", "reserved_usd": 0.02, "ts": 1790798243.5497878, "meta": {"task_id": "original-ordinal-04-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "60d75366f8ad4f5f8e8452306ecbd29d", "charged_usd": 0.0, "ts": 1790798243.606168, "meta": {"task_id": "original-ordinal-04-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "cda4c9954d54422d859d9eb0c4f0c66e", "reserved_usd": 0.02, "ts": 1790798243.6122215, "meta": {"task_id": "original-ordinal-04-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "cda4c9954d54422d859d9eb0c4f0c66e", "charged_usd": 0.0, "ts": 1790798243.6770263, "meta": {"task_id": "original-ordinal-04-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "4b8afb66fa0f418c92e06d6baa4151ab", "reserved_usd": 0.02, "ts": 1790798243.6857228, "meta": {"task_id": "original-ordinal-05-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "4b8afb66fa0f418c92e06d6baa4151ab", "charged_usd": 0.0, "ts": 1790798243.7484293, "meta": {"task_id": "original-ordinal-05-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "61887b9cdc954dd2aa081506f778fb57", "reserved_usd": 0.02, "ts": 1790798243.7555583, "meta": {"task_id": "original-ordinal-05-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "61887b9cdc954dd2aa081506f778fb57", "charged_usd": 0.0, "ts": 1790798243.8167248, "meta": {"task_id": "original-ordinal-05-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "63c3c4e6794d47809c9b9bd44d9d121c", "reserved_usd": 0.02, "ts": 1790798243.8237505, "meta": {"task_id": "original-ordinal-06-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "63c3c4e6794d47809c9b9bd44d9d121c", "charged_usd": 0.0, "ts": 1790798243.8800912, "meta": {"task_id": "original-ordinal-06-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "5f543331f10245e8b10dc337054b3ba1", "reserved_usd": 0.02, "ts": 1790798243.885256, "meta": {"task_id": "original-ordinal-06-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "5f543331f10245e8b10dc337054b3ba1", "charged_usd": 0.0, "ts": 1790798243.9417272, "meta": {"task_id": "original-ordinal-06-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8ee02e5fc115491e9fcfb25acc788ea4", "reserved_usd": 0.02, "ts": 1790798243.946886, "meta": {"task_id": "original-extraction-01-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8ee02e5fc115491e9fcfb25acc788ea4", "charged_usd": 0.0, "ts": 1790798244.0046992, "meta": {"task_id": "original-extraction-01-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ff8e335ab22d4e45b1ba94a74e9ffb21", "reserved_usd": 0.02, "ts": 1790798244.0102077, "meta": {"task_id": "original-extraction-01-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ff8e335ab22d4e45b1ba94a74e9ffb21", "charged_usd": 0.0, "ts": 1790798244.0693493, "meta": {"task_id": "original-extraction-01-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d9bd266c76dd4f75ae2c2a9d26cb19ee", "reserved_usd": 0.02, "ts": 1790798244.0745256, "meta": {"task_id": "original-extraction-02-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d9bd266c76dd4f75ae2c2a9d26cb19ee", "charged_usd": 0.0, "ts": 1790798244.131556, "meta": {"task_id": "original-extraction-02-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "3806595691154051ae740fbb0435f436", "reserved_usd": 0.02, "ts": 1790798244.13677, "meta": {"task_id": "original-extraction-02-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "3806595691154051ae740fbb0435f436", "charged_usd": 0.0, "ts": 1790798244.1929743, "meta": {"task_id": "original-extraction-02-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ae29f7fcdde94321b9c384d0c30be24e", "reserved_usd": 0.02, "ts": 1790798244.19779, "meta": {"task_id": "original-extraction-03-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ae29f7fcdde94321b9c384d0c30be24e", "charged_usd": 0.0, "ts": 1790798244.255574, "meta": {"task_id": "original-extraction-03-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "53281104e37348c9818de29bd8dfd22a", "reserved_usd": 0.02, "ts": 1790798244.2633102, "meta": {"task_id": "original-extraction-03-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "53281104e37348c9818de29bd8dfd22a", "charged_usd": 0.0, "ts": 1790798244.3223941, "meta": {"task_id": "original-extraction-03-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "a6d0ee33023745838428551a2cb13c3c", "reserved_usd": 0.02, "ts": 1790798244.3307836, "meta": {"task_id": "original-extraction-04-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "a6d0ee33023745838428551a2cb13c3c", "charged_usd": 0.0, "ts": 1790798244.3896575, "meta": {"task_id": "original-extraction-04-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8c7053cdfe964c87aba628a20624ca7e", "reserved_usd": 0.02, "ts": 1790798244.3956788, "meta": {"task_id": "original-extraction-04-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8c7053cdfe964c87aba628a20624ca7e", "charged_usd": 0.0, "ts": 1790798244.4531143, "meta": {"task_id": "original-extraction-04-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ecdd42b2bdab4e9c84065d7a112f41da", "reserved_usd": 0.02, "ts": 1790798244.4589825, "meta": {"task_id": "original-extraction-05-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ecdd42b2bdab4e9c84065d7a112f41da", "charged_usd": 0.0, "ts": 1790798244.515253, "meta": {"task_id": "original-extraction-05-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "83262bb709dd48c89dc26ed8e3df6b8b", "reserved_usd": 0.02, "ts": 1790798244.5217957, "meta": {"task_id": "original-extraction-05-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "83262bb709dd48c89dc26ed8e3df6b8b", "charged_usd": 0.0, "ts": 1790798244.5779953, "meta": {"task_id": "original-extraction-05-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "53065b8ee9c9441f9030f563039adb7f", "reserved_usd": 0.02, "ts": 1790798244.5837898, "meta": {"task_id": "original-extraction-06-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "53065b8ee9c9441f9030f563039adb7f", "charged_usd": 0.0, "ts": 1790798244.6414514, "meta": {"task_id": "original-extraction-06-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7eebac393acf4ca1b6aa1d41fc6edbea", "reserved_usd": 0.02, "ts": 1790798244.646621, "meta": {"task_id": "original-extraction-06-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7eebac393acf4ca1b6aa1d41fc6edbea", "charged_usd": 0.0, "ts": 1790798244.7026088, "meta": {"task_id": "original-extraction-06-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "f1d25880a7f8440897e2d439540f8d72", "reserved_usd": 0.02, "ts": 1790798244.707957, "meta": {"task_id": "original-adequacy-01-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "f1d25880a7f8440897e2d439540f8d72", "charged_usd": 0.0, "ts": 1790798244.7653806, "meta": {"task_id": "original-adequacy-01-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "5da2c12c6dda4e6fb47c314be397b38d", "reserved_usd": 0.02, "ts": 1790798244.7707682, "meta": {"task_id": "original-adequacy-01-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "5da2c12c6dda4e6fb47c314be397b38d", "charged_usd": 0.0, "ts": 1790798244.8271205, "meta": {"task_id": "original-adequacy-01-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "308e31544d2b4c7ea4aa25e19af61bd3", "reserved_usd": 0.02, "ts": 1790798244.8320675, "meta": {"task_id": "original-adequacy-02-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "308e31544d2b4c7ea4aa25e19af61bd3", "charged_usd": 0.0, "ts": 1790798244.8881907, "meta": {"task_id": "original-adequacy-02-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "91439c2c7d974528828aa4a3f412a544", "reserved_usd": 0.02, "ts": 1790798244.8942413, "meta": {"task_id": "original-adequacy-02-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "91439c2c7d974528828aa4a3f412a544", "charged_usd": 0.0, "ts": 1790798244.9500167, "meta": {"task_id": "original-adequacy-02-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "06d899cbc6514dedb841c5528c8fe140", "reserved_usd": 0.02, "ts": 1790798244.955721, "meta": {"task_id": "original-adequacy-03-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "06d899cbc6514dedb841c5528c8fe140", "charged_usd": 0.0, "ts": 1790798245.0119946, "meta": {"task_id": "original-adequacy-03-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ee5a8b9656484c04811f21e1e8fce755", "reserved_usd": 0.02, "ts": 1790798245.0164943, "meta": {"task_id": "original-adequacy-03-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ee5a8b9656484c04811f21e1e8fce755", "charged_usd": 0.0, "ts": 1790798245.0725887, "meta": {"task_id": "original-adequacy-03-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "14ecf40f596c41baa6e58cfd7095f284", "reserved_usd": 0.02, "ts": 1790798245.0781164, "meta": {"task_id": "original-adequacy-04-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "14ecf40f596c41baa6e58cfd7095f284", "charged_usd": 0.0, "ts": 1790798245.135964, "meta": {"task_id": "original-adequacy-04-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "9df0e0fb8b1a45d3a9811af5dace2e75", "reserved_usd": 0.02, "ts": 1790798245.1416018, "meta": {"task_id": "original-adequacy-04-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "9df0e0fb8b1a45d3a9811af5dace2e75", "charged_usd": 0.0, "ts": 1790798245.2001624, "meta": {"task_id": "original-adequacy-04-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "09c4134fc411492abc0a36b0185f01ee", "reserved_usd": 0.02, "ts": 1790798245.2045841, "meta": {"task_id": "original-adequacy-05-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "09c4134fc411492abc0a36b0185f01ee", "charged_usd": 0.0, "ts": 1790798245.2621648, "meta": {"task_id": "original-adequacy-05-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "2b17a421d5a54b09aabe9d0d1a5e78e3", "reserved_usd": 0.02, "ts": 1790798245.268463, "meta": {"task_id": "original-adequacy-05-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "2b17a421d5a54b09aabe9d0d1a5e78e3", "charged_usd": 0.0, "ts": 1790798245.3248196, "meta": {"task_id": "original-adequacy-05-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "88737f5cf1a446899936e7ba686b8ce1", "reserved_usd": 0.02, "ts": 1790798245.329421, "meta": {"task_id": "original-adequacy-06-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "88737f5cf1a446899936e7ba686b8ce1", "charged_usd": 0.0, "ts": 1790798245.3853688, "meta": {"task_id": "original-adequacy-06-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "b6bcbeac2d814568911bd689cbdc0570", "reserved_usd": 0.02, "ts": 1790798245.3910508, "meta": {"task_id": "original-adequacy-06-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "b6bcbeac2d814568911bd689cbdc0570", "charged_usd": 0.0, "ts": 1790798245.4473743, "meta": {"task_id": "original-adequacy-06-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "16bc8509859b4617b5ef4ee6cc830344", "reserved_usd": 0.02, "ts": 1790798245.4526055, "meta": {"task_id": "original-routing-01-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "16bc8509859b4617b5ef4ee6cc830344", "charged_usd": 0.0, "ts": 1790798245.5095422, "meta": {"task_id": "original-routing-01-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "779c6c65df04470b8f4ae54cb5de7206", "reserved_usd": 0.02, "ts": 1790798245.5157156, "meta": {"task_id": "original-routing-01-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "779c6c65df04470b8f4ae54cb5de7206", "charged_usd": 0.0, "ts": 1790798245.5724366, "meta": {"task_id": "original-routing-01-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d6a255fc2cbd4475b40d1075aceff4d2", "reserved_usd": 0.02, "ts": 1790798245.5783703, "meta": {"task_id": "original-routing-02-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d6a255fc2cbd4475b40d1075aceff4d2", "charged_usd": 0.0, "ts": 1790798245.6371734, "meta": {"task_id": "original-routing-02-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d8d5ec120d2249a0858a37c9198446d0", "reserved_usd": 0.02, "ts": 1790798245.642535, "meta": {"task_id": "original-routing-02-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d8d5ec120d2249a0858a37c9198446d0", "charged_usd": 0.0, "ts": 1790798245.6995397, "meta": {"task_id": "original-routing-02-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "49ed4f1a2a76463a91f3580a2d17d19b", "reserved_usd": 0.02, "ts": 1790798245.7050977, "meta": {"task_id": "original-routing-03-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "49ed4f1a2a76463a91f3580a2d17d19b", "charged_usd": 0.0, "ts": 1790798245.7631872, "meta": {"task_id": "original-routing-03-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "2d0fb58246b04893943fa6db000ded18", "reserved_usd": 0.02, "ts": 1790798245.767911, "meta": {"task_id": "original-routing-03-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "2d0fb58246b04893943fa6db000ded18", "charged_usd": 0.0, "ts": 1790798245.8248425, "meta": {"task_id": "original-routing-03-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "3f9ad20fab3a4055beb6fad093e2667e", "reserved_usd": 0.02, "ts": 1790798245.8298554, "meta": {"task_id": "original-routing-04-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "3f9ad20fab3a4055beb6fad093e2667e", "charged_usd": 0.0, "ts": 1790798245.8870645, "meta": {"task_id": "original-routing-04-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "63a25233ac984786816d3c0744593222", "reserved_usd": 0.02, "ts": 1790798245.8925214, "meta": {"task_id": "original-routing-04-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "63a25233ac984786816d3c0744593222", "charged_usd": 0.0, "ts": 1790798245.9507518, "meta": {"task_id": "original-routing-04-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "a8a01a0d187844cfb38a3829398beea4", "reserved_usd": 0.02, "ts": 1790798245.955756, "meta": {"task_id": "original-routing-05-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "a8a01a0d187844cfb38a3829398beea4", "charged_usd": 0.0, "ts": 1790798246.0123346, "meta": {"task_id": "original-routing-05-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8930b1ce42cb42bb9cf9654245778e69", "reserved_usd": 0.02, "ts": 1790798246.0168061, "meta": {"task_id": "original-routing-05-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8930b1ce42cb42bb9cf9654245778e69", "charged_usd": 0.0, "ts": 1790798246.0751207, "meta": {"task_id": "original-routing-05-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c85bc1b144d34b358304dad3af31ea09", "reserved_usd": 0.02, "ts": 1790798246.079968, "meta": {"task_id": "original-routing-06-0", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c85bc1b144d34b358304dad3af31ea09", "charged_usd": 0.0, "ts": 1790798246.1372635, "meta": {"task_id": "original-routing-06-0", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "1f24bfef2dd84b9895aa167514809e65", "reserved_usd": 0.02, "ts": 1790798246.1426885, "meta": {"task_id": "original-routing-06-1", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "1f24bfef2dd84b9895aa167514809e65", "charged_usd": 0.0, "ts": 1790798246.2007182, "meta": {"task_id": "original-routing-06-1", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "5c2fde071f2f4ad0b1f09c4aba0cf92e", "reserved_usd": 0.02, "ts": 1790798246.2061448, "meta": {"task_id": "hard-opus-a-long_policy-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "5c2fde071f2f4ad0b1f09c4aba0cf92e", "charged_usd": 0.0, "ts": 1790798252.96226, "meta": {"task_id": "hard-opus-a-long_policy-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "a0c2f8e9381a4cd0aa1a7e22e844f533", "reserved_usd": 0.02, "ts": 1790798252.9713013, "meta": {"task_id": "hard-opus-a-long_policy-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "a0c2f8e9381a4cd0aa1a7e22e844f533", "charged_usd": 0.0, "ts": 1790798253.1255891, "meta": {"task_id": "hard-opus-a-long_policy-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7640cc2cf5b746549625b4bf243f71f4", "reserved_usd": 0.02, "ts": 1790798253.135936, "meta": {"task_id": "hard-opus-a-long_policy-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7640cc2cf5b746549625b4bf243f71f4", "charged_usd": 0.0, "ts": 1790798253.2719178, "meta": {"task_id": "hard-opus-a-long_policy-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d3294755da6549daa2a30274b1a23205", "reserved_usd": 0.02, "ts": 1790798253.2817423, "meta": {"task_id": "hard-opus-a-long_policy-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d3294755da6549daa2a30274b1a23205", "charged_usd": 0.0, "ts": 1790798253.426073, "meta": {"task_id": "hard-opus-a-long_policy-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "adab5651a20d419f9ec9aa196b880242", "reserved_usd": 0.02, "ts": 1790798253.435719, "meta": {"task_id": "hard-opus-a-long_policy-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "adab5651a20d419f9ec9aa196b880242", "charged_usd": 0.0, "ts": 1790798253.5707788, "meta": {"task_id": "hard-opus-a-long_policy-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "55ab9ffab6544069984842161d58fc81", "reserved_usd": 0.02, "ts": 1790798253.58082, "meta": {"task_id": "hard-opus-a-long_policy-13", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "55ab9ffab6544069984842161d58fc81", "charged_usd": 0.0, "ts": 1790798253.7167149, "meta": {"task_id": "hard-opus-a-long_policy-13", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d2c698d518664ff5a0b85ab4ac2e41fd", "reserved_usd": 0.02, "ts": 1790798253.7255418, "meta": {"task_id": "hard-opus-a-long_policy-17", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d2c698d518664ff5a0b85ab4ac2e41fd", "charged_usd": 0.0, "ts": 1790798253.8569238, "meta": {"task_id": "hard-opus-a-long_policy-17", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "a743ea6305a54dc5b0a1f953e90e2857", "reserved_usd": 0.02, "ts": 1790798253.866284, "meta": {"task_id": "hard-opus-a-long_policy-19", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "a743ea6305a54dc5b0a1f953e90e2857", "charged_usd": 0.0, "ts": 1790798253.994871, "meta": {"task_id": "hard-opus-a-long_policy-19", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c1fd3185cc02496497a16f52d57765fa", "reserved_usd": 0.02, "ts": 1790798254.0041766, "meta": {"task_id": "hard-opus-a-probability-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c1fd3185cc02496497a16f52d57765fa", "charged_usd": 0.0, "ts": 1790798254.093114, "meta": {"task_id": "hard-opus-a-probability-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "67ac663b86ee4946aaea5c9eb4c3184a", "reserved_usd": 0.02, "ts": 1790798254.1021557, "meta": {"task_id": "hard-opus-a-probability-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "67ac663b86ee4946aaea5c9eb4c3184a", "charged_usd": 0.0, "ts": 1790798254.183268, "meta": {"task_id": "hard-opus-a-probability-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "6efa8963d85546748988c5167de7c09e", "reserved_usd": 0.02, "ts": 1790798254.1898663, "meta": {"task_id": "hard-opus-a-probability-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "6efa8963d85546748988c5167de7c09e", "charged_usd": 0.0, "ts": 1790798254.2757905, "meta": {"task_id": "hard-opus-a-probability-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c1fea13d36d1488ebf8fa270302e16a8", "reserved_usd": 0.02, "ts": 1790798254.2819996, "meta": {"task_id": "hard-opus-a-probability-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c1fea13d36d1488ebf8fa270302e16a8", "charged_usd": 0.0, "ts": 1790798254.344353, "meta": {"task_id": "hard-opus-a-probability-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c9ca35ffd89149fd90100d1ffceb902a", "reserved_usd": 0.02, "ts": 1790798254.353223, "meta": {"task_id": "hard-opus-a-temporal_numeric-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c9ca35ffd89149fd90100d1ffceb902a", "charged_usd": 0.0, "ts": 1790798254.4202268, "meta": {"task_id": "hard-opus-a-temporal_numeric-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "57ce336c4bfe4365ace1b4f1d5668eab", "reserved_usd": 0.02, "ts": 1790798254.4279056, "meta": {"task_id": "hard-opus-a-temporal_numeric-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "57ce336c4bfe4365ace1b4f1d5668eab", "charged_usd": 0.0, "ts": 1790798254.4946907, "meta": {"task_id": "hard-opus-a-temporal_numeric-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7f510b484a3f4265863b94864ce03f8a", "reserved_usd": 0.02, "ts": 1790798254.5010111, "meta": {"task_id": "hard-opus-a-temporal_numeric-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7f510b484a3f4265863b94864ce03f8a", "charged_usd": 0.0, "ts": 1790798254.5911267, "meta": {"task_id": "hard-opus-a-temporal_numeric-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "acc0dc8f8ea141f4b66627e946a1a457", "reserved_usd": 0.02, "ts": 1790798254.59758, "meta": {"task_id": "hard-opus-a-temporal_numeric-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "acc0dc8f8ea141f4b66627e946a1a457", "charged_usd": 0.0, "ts": 1790798254.6659126, "meta": {"task_id": "hard-opus-a-temporal_numeric-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d96b8fcd8fff48ba8b9f832bed9e01e7", "reserved_usd": 0.02, "ts": 1790798254.6721182, "meta": {"task_id": "hard-opus-a-temporal_numeric-12", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d96b8fcd8fff48ba8b9f832bed9e01e7", "charged_usd": 0.0, "ts": 1790798254.7365952, "meta": {"task_id": "hard-opus-a-temporal_numeric-12", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "69ccecba1d6c40f689c7d6aaff61e64b", "reserved_usd": 0.02, "ts": 1790798254.7440445, "meta": {"task_id": "hard-opus-b-ambiguous-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "69ccecba1d6c40f689c7d6aaff61e64b", "charged_usd": 0.0, "ts": 1790798254.8108788, "meta": {"task_id": "hard-opus-b-ambiguous-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "b0071c22a49448de8e599e88c0bda93e", "reserved_usd": 0.02, "ts": 1790798254.8175645, "meta": {"task_id": "hard-opus-b-ambiguous-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "b0071c22a49448de8e599e88c0bda93e", "charged_usd": 0.0, "ts": 1790798254.8833559, "meta": {"task_id": "hard-opus-b-ambiguous-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "50ae3a4f965c4b4d98bd1dea6cb2db80", "reserved_usd": 0.02, "ts": 1790798254.889488, "meta": {"task_id": "hard-opus-b-ambiguous-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "50ae3a4f965c4b4d98bd1dea6cb2db80", "charged_usd": 0.0, "ts": 1790798254.956946, "meta": {"task_id": "hard-opus-b-ambiguous-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "59da289675e3422e9796c7f1bfe370b8", "reserved_usd": 0.02, "ts": 1790798254.9647696, "meta": {"task_id": "hard-opus-b-ambiguous-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "59da289675e3422e9796c7f1bfe370b8", "charged_usd": 0.0, "ts": 1790798255.0299416, "meta": {"task_id": "hard-opus-b-ambiguous-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7e09e825280748639bbc8e76b95bea33", "reserved_usd": 0.02, "ts": 1790798255.0357406, "meta": {"task_id": "hard-opus-b-ambiguous-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7e09e825280748639bbc8e76b95bea33", "charged_usd": 0.0, "ts": 1790798255.1009424, "meta": {"task_id": "hard-opus-b-ambiguous-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "2b33738422964241bd9827bc268072ea", "reserved_usd": 0.02, "ts": 1790798255.1086643, "meta": {"task_id": "hard-opus-b-ambiguous-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "2b33738422964241bd9827bc268072ea", "charged_usd": 0.0, "ts": 1790798255.1742558, "meta": {"task_id": "hard-opus-b-ambiguous-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8206c1d006024660b7243ce289832e48", "reserved_usd": 0.02, "ts": 1790798255.1810453, "meta": {"task_id": "hard-opus-b-ambiguous-13", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8206c1d006024660b7243ce289832e48", "charged_usd": 0.0, "ts": 1790798255.2492106, "meta": {"task_id": "hard-opus-b-ambiguous-13", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "eec1317cfcc34e3185e48bdfca518e68", "reserved_usd": 0.02, "ts": 1790798255.256022, "meta": {"task_id": "hard-opus-b-multi_hop-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "eec1317cfcc34e3185e48bdfca518e68", "charged_usd": 0.0, "ts": 1790798255.4199476, "meta": {"task_id": "hard-opus-b-multi_hop-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "6c6e78693ee24c0e8cd3cc80b69ceba4", "reserved_usd": 0.02, "ts": 1790798255.4292357, "meta": {"task_id": "hard-opus-b-multi_hop-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "6c6e78693ee24c0e8cd3cc80b69ceba4", "charged_usd": 0.0, "ts": 1790798255.5604944, "meta": {"task_id": "hard-opus-b-multi_hop-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "a63aea3d4f4d4d639596d5964115994a", "reserved_usd": 0.02, "ts": 1790798255.569024, "meta": {"task_id": "hard-opus-b-multi_hop-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "a63aea3d4f4d4d639596d5964115994a", "charged_usd": 0.0, "ts": 1790798255.712253, "meta": {"task_id": "hard-opus-b-multi_hop-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "fb05895c32b54abba49ad802ad850496", "reserved_usd": 0.02, "ts": 1790798255.7226484, "meta": {"task_id": "hard-opus-b-multi_hop-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "fb05895c32b54abba49ad802ad850496", "charged_usd": 0.0, "ts": 1790798255.8676105, "meta": {"task_id": "hard-opus-b-multi_hop-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "dd6d5291b44f4fcc93e1d7ac86099826", "reserved_usd": 0.02, "ts": 1790798255.87706, "meta": {"task_id": "hard-opus-b-multi_hop-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "dd6d5291b44f4fcc93e1d7ac86099826", "charged_usd": 0.0, "ts": 1790798256.008892, "meta": {"task_id": "hard-opus-b-multi_hop-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "f6dad7eb54b947f59e8369f87b5d5382", "reserved_usd": 0.02, "ts": 1790798256.0181978, "meta": {"task_id": "hard-opus-b-probability-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "f6dad7eb54b947f59e8369f87b5d5382", "charged_usd": 0.0, "ts": 1790798256.1284068, "meta": {"task_id": "hard-opus-b-probability-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c648e02c039e4f93a6a190b27fdefec2", "reserved_usd": 0.02, "ts": 1790798256.1380637, "meta": {"task_id": "hard-opus-b-probability-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c648e02c039e4f93a6a190b27fdefec2", "charged_usd": 0.0, "ts": 1790798256.2061071, "meta": {"task_id": "hard-opus-b-probability-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7c398497b5ed41828435ddffe1233a2f", "reserved_usd": 0.02, "ts": 1790798256.2124856, "meta": {"task_id": "hard-opus-b-probability-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7c398497b5ed41828435ddffe1233a2f", "charged_usd": 0.0, "ts": 1790798256.2991846, "meta": {"task_id": "hard-opus-b-probability-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "b7be8606dce54c7eafa0f72264dfacb0", "reserved_usd": 0.02, "ts": 1790798256.3063643, "meta": {"task_id": "hard-opus-b-probability-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "b7be8606dce54c7eafa0f72264dfacb0", "charged_usd": 0.0, "ts": 1790798256.3709257, "meta": {"task_id": "hard-opus-b-probability-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "8a506753c80948e4bf881822270d1283", "reserved_usd": 0.02, "ts": 1790798256.3776274, "meta": {"task_id": "hard-opus-b-probability-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "8a506753c80948e4bf881822270d1283", "charged_usd": 0.0, "ts": 1790798256.4580915, "meta": {"task_id": "hard-opus-b-probability-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "f151688cb2514d0cbe511bde53a581f5", "reserved_usd": 0.02, "ts": 1790798256.4652445, "meta": {"task_id": "hard-opus-b-tradeoff-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "f151688cb2514d0cbe511bde53a581f5", "charged_usd": 0.0, "ts": 1790798256.5410855, "meta": {"task_id": "hard-opus-b-tradeoff-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "531d18683fc4418f80963859fc9fe7b4", "reserved_usd": 0.02, "ts": 1790798256.5482013, "meta": {"task_id": "hard-opus-b-tradeoff-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "531d18683fc4418f80963859fc9fe7b4", "charged_usd": 0.0, "ts": 1790798256.6184337, "meta": {"task_id": "hard-opus-b-tradeoff-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d0b4330f0f5748dcaa722cfa2ff6bfa2", "reserved_usd": 0.02, "ts": 1790798256.6255207, "meta": {"task_id": "hard-opus-b-tradeoff-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d0b4330f0f5748dcaa722cfa2ff6bfa2", "charged_usd": 0.0, "ts": 1790798256.6952293, "meta": {"task_id": "hard-opus-b-tradeoff-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "0a238e543d57421aa5705e4aa03978d2", "reserved_usd": 0.02, "ts": 1790798256.7020698, "meta": {"task_id": "hard-opus-b-tradeoff-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "0a238e543d57421aa5705e4aa03978d2", "charged_usd": 0.0, "ts": 1790798256.7713056, "meta": {"task_id": "hard-opus-b-tradeoff-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "97adc64691754b4d8b9291db5a93e359", "reserved_usd": 0.02, "ts": 1790798256.7790346, "meta": {"task_id": "hard-opus-b-tradeoff-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "97adc64691754b4d8b9291db5a93e359", "charged_usd": 0.0, "ts": 1790798256.8445463, "meta": {"task_id": "hard-opus-b-tradeoff-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "498ab0f1a2d8493b9bb9b8e0a4662059", "reserved_usd": 0.02, "ts": 1790798256.8514152, "meta": {"task_id": "hard-opus-b-tradeoff-12", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "498ab0f1a2d8493b9bb9b8e0a4662059", "charged_usd": 0.0, "ts": 1790798256.9154117, "meta": {"task_id": "hard-opus-b-tradeoff-12", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "bb32594b4b8d41f1a23fe3559e865263", "reserved_usd": 0.02, "ts": 1790798256.9211042, "meta": {"task_id": "hard-opus-c-long_policy-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "bb32594b4b8d41f1a23fe3559e865263", "charged_usd": 0.0, "ts": 1790798257.1142535, "meta": {"task_id": "hard-opus-c-long_policy-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d130ea92d18f4510ad1c2464448e7da4", "reserved_usd": 0.02, "ts": 1790798257.1227221, "meta": {"task_id": "hard-opus-c-long_policy-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d130ea92d18f4510ad1c2464448e7da4", "charged_usd": 0.0, "ts": 1790798257.3096788, "meta": {"task_id": "hard-opus-c-long_policy-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "2122e2c6ced4451990f73aeccd5be213", "reserved_usd": 0.02, "ts": 1790798257.316806, "meta": {"task_id": "hard-opus-c-long_policy-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "2122e2c6ced4451990f73aeccd5be213", "charged_usd": 0.0, "ts": 1790798257.4948235, "meta": {"task_id": "hard-opus-c-long_policy-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "bef0f4f7bffb476097d5d10d6eedc38e", "reserved_usd": 0.02, "ts": 1790798257.5031354, "meta": {"task_id": "hard-opus-c-long_policy-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "bef0f4f7bffb476097d5d10d6eedc38e", "charged_usd": 0.0, "ts": 1790798257.6851125, "meta": {"task_id": "hard-opus-c-long_policy-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "916e26c03e2c456785e9514e55c94149", "reserved_usd": 0.02, "ts": 1790798257.6931646, "meta": {"task_id": "hard-opus-c-long_policy-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "916e26c03e2c456785e9514e55c94149", "charged_usd": 0.0, "ts": 1790798257.8807297, "meta": {"task_id": "hard-opus-c-long_policy-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d43700af42e947a8b16e4d169aa5ccae", "reserved_usd": 0.02, "ts": 1790798257.8892286, "meta": {"task_id": "hard-opus-c-long_policy-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d43700af42e947a8b16e4d169aa5ccae", "charged_usd": 0.0, "ts": 1790798258.0811431, "meta": {"task_id": "hard-opus-c-long_policy-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "be3fd920473d4821a52366426af1782b", "reserved_usd": 0.02, "ts": 1790798258.091001, "meta": {"task_id": "hard-opus-c-long_policy-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "be3fd920473d4821a52366426af1782b", "charged_usd": 0.0, "ts": 1790798258.2745306, "meta": {"task_id": "hard-opus-c-long_policy-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "b057e923d36f4ebcb3026f9720dbef71", "reserved_usd": 0.02, "ts": 1790798258.2845466, "meta": {"task_id": "hard-opus-c-probability-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "b057e923d36f4ebcb3026f9720dbef71", "charged_usd": 0.0, "ts": 1790798258.3547487, "meta": {"task_id": "hard-opus-c-probability-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "65b4f44f33be41459c46ea1f160ac7df", "reserved_usd": 0.02, "ts": 1790798258.3625875, "meta": {"task_id": "hard-opus-c-temporal_numeric-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "65b4f44f33be41459c46ea1f160ac7df", "charged_usd": 0.0, "ts": 1790798258.4394522, "meta": {"task_id": "hard-opus-c-temporal_numeric-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "a38e57db9f4e4288baa58bbeb9be137d", "reserved_usd": 0.02, "ts": 1790798258.4467824, "meta": {"task_id": "hard-opus-c-temporal_numeric-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "a38e57db9f4e4288baa58bbeb9be137d", "charged_usd": 0.0, "ts": 1790798258.5187607, "meta": {"task_id": "hard-opus-c-temporal_numeric-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ba13106c137a4ca8806fdbe8b268a870", "reserved_usd": 0.02, "ts": 1790798258.5259216, "meta": {"task_id": "hard-opus-c-temporal_numeric-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ba13106c137a4ca8806fdbe8b268a870", "charged_usd": 0.0, "ts": 1790798258.5963724, "meta": {"task_id": "hard-opus-c-temporal_numeric-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "50a0b34112984e479ef8123003e84a4b", "reserved_usd": 0.02, "ts": 1790798258.6025739, "meta": {"task_id": "hard-opus-c-temporal_numeric-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "50a0b34112984e479ef8123003e84a4b", "charged_usd": 0.0, "ts": 1790798258.6808443, "meta": {"task_id": "hard-opus-c-temporal_numeric-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "b050a112c9b5477aac834b1481165f1c", "reserved_usd": 0.02, "ts": 1790798258.6874259, "meta": {"task_id": "hard-opus-c-temporal_numeric-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "b050a112c9b5477aac834b1481165f1c", "charged_usd": 0.0, "ts": 1790798258.7646506, "meta": {"task_id": "hard-opus-c-temporal_numeric-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7f437107ba374e1da6438013c6238e00", "reserved_usd": 0.02, "ts": 1790798258.7709737, "meta": {"task_id": "hard-opus-c-temporal_numeric-12", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7f437107ba374e1da6438013c6238e00", "charged_usd": 0.0, "ts": 1790798258.841395, "meta": {"task_id": "hard-opus-c-temporal_numeric-12", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "69ca90cc2cd148558171444e753da27f", "reserved_usd": 0.02, "ts": 1790798258.8470707, "meta": {"task_id": "hard-sol-a-adversarial-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "69ca90cc2cd148558171444e753da27f", "charged_usd": 0.0, "ts": 1790798258.9051485, "meta": {"task_id": "hard-sol-a-adversarial-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "e6b42f3dbf264c8fb5387847a24d1479", "reserved_usd": 0.02, "ts": 1790798258.911179, "meta": {"task_id": "hard-sol-a-adversarial-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "e6b42f3dbf264c8fb5387847a24d1479", "charged_usd": 0.0, "ts": 1790798258.9691355, "meta": {"task_id": "hard-sol-a-adversarial-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "1c099b460f3c45419be1883ac65bf241", "reserved_usd": 0.02, "ts": 1790798258.9753938, "meta": {"task_id": "hard-sol-a-adversarial-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "1c099b460f3c45419be1883ac65bf241", "charged_usd": 0.0, "ts": 1790798259.035524, "meta": {"task_id": "hard-sol-a-adversarial-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "0dd2333837b74857898da3f3d211dd53", "reserved_usd": 0.02, "ts": 1790798259.042257, "meta": {"task_id": "hard-sol-a-adversarial-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "0dd2333837b74857898da3f3d211dd53", "charged_usd": 0.0, "ts": 1790798259.1025176, "meta": {"task_id": "hard-sol-a-adversarial-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "731ceee3ca7d41ab90c920141f488065", "reserved_usd": 0.02, "ts": 1790798259.1098435, "meta": {"task_id": "hard-sol-a-adversarial-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "731ceee3ca7d41ab90c920141f488065", "charged_usd": 0.0, "ts": 1790798259.1680374, "meta": {"task_id": "hard-sol-a-adversarial-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "a0095f53806c4816b8532bf03e6995f6", "reserved_usd": 0.02, "ts": 1790798259.174709, "meta": {"task_id": "hard-sol-a-adversarial-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "a0095f53806c4816b8532bf03e6995f6", "charged_usd": 0.0, "ts": 1790798259.2366996, "meta": {"task_id": "hard-sol-a-adversarial-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "a1229d38a9414868bbe5687e42af7f20", "reserved_usd": 0.02, "ts": 1790798259.244666, "meta": {"task_id": "hard-sol-a-multi_hop-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "a1229d38a9414868bbe5687e42af7f20", "charged_usd": 0.0, "ts": 1790798259.3970447, "meta": {"task_id": "hard-sol-a-multi_hop-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "3eb2e78d372b4168baffc325e7161572", "reserved_usd": 0.02, "ts": 1790798259.407781, "meta": {"task_id": "hard-sol-a-multi_hop-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "3eb2e78d372b4168baffc325e7161572", "charged_usd": 0.0, "ts": 1790798259.5606925, "meta": {"task_id": "hard-sol-a-multi_hop-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "608b4e27c5f14cc5b56936f2af10dbdd", "reserved_usd": 0.02, "ts": 1790798259.5691597, "meta": {"task_id": "hard-sol-a-multi_hop-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "608b4e27c5f14cc5b56936f2af10dbdd", "charged_usd": 0.0, "ts": 1790798259.7138143, "meta": {"task_id": "hard-sol-a-multi_hop-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "626f72df1de149e99183ac3d2543c2aa", "reserved_usd": 0.02, "ts": 1790798259.72321, "meta": {"task_id": "hard-sol-a-multi_hop-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "626f72df1de149e99183ac3d2543c2aa", "charged_usd": 0.0, "ts": 1790798259.8685446, "meta": {"task_id": "hard-sol-a-multi_hop-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "1348b1ed926b4c16bb2de0af13f04b3f", "reserved_usd": 0.02, "ts": 1790798259.8779206, "meta": {"task_id": "hard-sol-a-multi_hop-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "1348b1ed926b4c16bb2de0af13f04b3f", "charged_usd": 0.0, "ts": 1790798260.022437, "meta": {"task_id": "hard-sol-a-multi_hop-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d9595234e6a04b8384c812efcb26f81f", "reserved_usd": 0.02, "ts": 1790798260.0310407, "meta": {"task_id": "hard-sol-a-multi_hop-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d9595234e6a04b8384c812efcb26f81f", "charged_usd": 0.0, "ts": 1790798260.1768746, "meta": {"task_id": "hard-sol-a-multi_hop-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "dfd08a2571b8453a8efa48125cd3dbb6", "reserved_usd": 0.02, "ts": 1790798260.1863694, "meta": {"task_id": "hard-sol-a-multi_hop-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "dfd08a2571b8453a8efa48125cd3dbb6", "charged_usd": 0.0, "ts": 1790798260.3306315, "meta": {"task_id": "hard-sol-a-multi_hop-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "18338c6bea9d4fbe9631dc5a049c8ad6", "reserved_usd": 0.02, "ts": 1790798260.3418725, "meta": {"task_id": "hard-sol-a-multi_hop-12", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "18338c6bea9d4fbe9631dc5a049c8ad6", "charged_usd": 0.0, "ts": 1790798260.4860864, "meta": {"task_id": "hard-sol-a-multi_hop-12", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "f50a8138393d4f369be6addbd75a713f", "reserved_usd": 0.02, "ts": 1790798260.496313, "meta": {"task_id": "hard-sol-a-trap-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "f50a8138393d4f369be6addbd75a713f", "charged_usd": 0.0, "ts": 1790798260.5567062, "meta": {"task_id": "hard-sol-a-trap-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "4dbccfb2cf4a45209dc400ef920cc6c4", "reserved_usd": 0.02, "ts": 1790798260.5653596, "meta": {"task_id": "hard-sol-a-trap-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "4dbccfb2cf4a45209dc400ef920cc6c4", "charged_usd": 0.0, "ts": 1790798260.6234674, "meta": {"task_id": "hard-sol-a-trap-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7f12bdbf1dd2487cbb4d07134cc867ce", "reserved_usd": 0.02, "ts": 1790798260.6312716, "meta": {"task_id": "hard-sol-a-trap-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7f12bdbf1dd2487cbb4d07134cc867ce", "charged_usd": 0.0, "ts": 1790798260.6902902, "meta": {"task_id": "hard-sol-a-trap-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "523c26b405e942d2a630447b81643550", "reserved_usd": 0.02, "ts": 1790798260.697037, "meta": {"task_id": "hard-sol-a-trap-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "523c26b405e942d2a630447b81643550", "charged_usd": 0.0, "ts": 1790798260.7557194, "meta": {"task_id": "hard-sol-a-trap-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ec521cc577d34560b93b02c414b918af", "reserved_usd": 0.02, "ts": 1790798260.762544, "meta": {"task_id": "hard-sol-a-trap-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ec521cc577d34560b93b02c414b918af", "charged_usd": 0.0, "ts": 1790798260.8205235, "meta": {"task_id": "hard-sol-a-trap-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "4ce24977b9854e71a0392d74dbd65794", "reserved_usd": 0.02, "ts": 1790798260.8283963, "meta": {"task_id": "hard-sol-a-trap-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "4ce24977b9854e71a0392d74dbd65794", "charged_usd": 0.0, "ts": 1790798260.8871224, "meta": {"task_id": "hard-sol-a-trap-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "163763190c41489abeb9fb904b912eee", "reserved_usd": 0.02, "ts": 1790798260.8956575, "meta": {"task_id": "hard-sol-a-trap-13", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "163763190c41489abeb9fb904b912eee", "charged_usd": 0.0, "ts": 1790798260.954686, "meta": {"task_id": "hard-sol-a-trap-13", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "20cd55d26d544f26978dd54f8178a0de", "reserved_usd": 0.02, "ts": 1790798260.9619107, "meta": {"task_id": "hard-sol-a-trap-15", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "20cd55d26d544f26978dd54f8178a0de", "charged_usd": 0.0, "ts": 1790798261.0201137, "meta": {"task_id": "hard-sol-a-trap-15", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "ed776e40d7e94fb2a3bee6d24575d3f1", "reserved_usd": 0.02, "ts": 1790798261.027706, "meta": {"task_id": "hard-sol-b-judge_hard-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "ed776e40d7e94fb2a3bee6d24575d3f1", "charged_usd": 0.0, "ts": 1790798261.0867062, "meta": {"task_id": "hard-sol-b-judge_hard-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "79f9b51c3cc64484bde6658f3b1fdf88", "reserved_usd": 0.02, "ts": 1790798261.0932438, "meta": {"task_id": "hard-sol-b-judge_hard-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "79f9b51c3cc64484bde6658f3b1fdf88", "charged_usd": 0.0, "ts": 1790798261.151012, "meta": {"task_id": "hard-sol-b-judge_hard-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "613c53f5b32547f2afbaaa1a567e190f", "reserved_usd": 0.02, "ts": 1790798261.158094, "meta": {"task_id": "hard-sol-b-judge_hard-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "613c53f5b32547f2afbaaa1a567e190f", "charged_usd": 0.0, "ts": 1790798261.217493, "meta": {"task_id": "hard-sol-b-judge_hard-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "823c2bca18c441bda0be68dc71d9fc61", "reserved_usd": 0.02, "ts": 1790798261.2240095, "meta": {"task_id": "hard-sol-b-judge_hard-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "823c2bca18c441bda0be68dc71d9fc61", "charged_usd": 0.0, "ts": 1790798261.281873, "meta": {"task_id": "hard-sol-b-judge_hard-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "dcc3b5841ef14afc9a948dba6b9d4490", "reserved_usd": 0.02, "ts": 1790798261.2879906, "meta": {"task_id": "hard-sol-b-judge_hard-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "dcc3b5841ef14afc9a948dba6b9d4490", "charged_usd": 0.0, "ts": 1790798261.3452897, "meta": {"task_id": "hard-sol-b-judge_hard-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7b22518e00d04804acb530b537a32732", "reserved_usd": 0.02, "ts": 1790798261.3522062, "meta": {"task_id": "hard-sol-b-judge_hard-14", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7b22518e00d04804acb530b537a32732", "charged_usd": 0.0, "ts": 1790798261.410699, "meta": {"task_id": "hard-sol-b-judge_hard-14", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "17625ee45e524714be5c42228881256a", "reserved_usd": 0.02, "ts": 1790798261.4174612, "meta": {"task_id": "hard-sol-b-judge_hard-15", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "17625ee45e524714be5c42228881256a", "charged_usd": 0.0, "ts": 1790798261.475063, "meta": {"task_id": "hard-sol-b-judge_hard-15", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "6f32a68fceae42cebd13c614b4f58b8f", "reserved_usd": 0.02, "ts": 1790798261.4811974, "meta": {"task_id": "hard-sol-b-judge_hard-18", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "6f32a68fceae42cebd13c614b4f58b8f", "charged_usd": 0.0, "ts": 1790798261.538304, "meta": {"task_id": "hard-sol-b-judge_hard-18", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "e0e22132dca6485fb6719f242be02e0c", "reserved_usd": 0.02, "ts": 1790798261.5459082, "meta": {"task_id": "hard-sol-b-long_policy-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "e0e22132dca6485fb6719f242be02e0c", "charged_usd": 0.0, "ts": 1790798261.7010531, "meta": {"task_id": "hard-sol-b-long_policy-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "cc4f729cebe54335955e580139eabb0b", "reserved_usd": 0.02, "ts": 1790798261.7117176, "meta": {"task_id": "hard-sol-b-long_policy-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "cc4f729cebe54335955e580139eabb0b", "charged_usd": 0.0, "ts": 1790798261.8613029, "meta": {"task_id": "hard-sol-b-long_policy-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "84043adce4514252b4429a80bcb26b26", "reserved_usd": 0.02, "ts": 1790798261.8721275, "meta": {"task_id": "hard-sol-b-long_policy-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "84043adce4514252b4429a80bcb26b26", "charged_usd": 0.0, "ts": 1790798262.0187125, "meta": {"task_id": "hard-sol-b-long_policy-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "dc110617e56e4151a5855079a20bb787", "reserved_usd": 0.02, "ts": 1790798262.0284925, "meta": {"task_id": "hard-sol-b-long_policy-06", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "dc110617e56e4151a5855079a20bb787", "charged_usd": 0.0, "ts": 1790798262.1761098, "meta": {"task_id": "hard-sol-b-long_policy-06", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "6841e2506d6748698c2cc9caafcc2852", "reserved_usd": 0.02, "ts": 1790798262.1829057, "meta": {"task_id": "hard-sol-b-routing_hard-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "6841e2506d6748698c2cc9caafcc2852", "charged_usd": 0.0, "ts": 1790798262.2429755, "meta": {"task_id": "hard-sol-b-routing_hard-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "aec04439d11d460eb58711a1641de81c", "reserved_usd": 0.02, "ts": 1790798262.251921, "meta": {"task_id": "hard-sol-b-routing_hard-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "aec04439d11d460eb58711a1641de81c", "charged_usd": 0.0, "ts": 1790798262.3111022, "meta": {"task_id": "hard-sol-b-routing_hard-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "bbea997600fd4cc6b634b9c43ccf014f", "reserved_usd": 0.02, "ts": 1790798262.3172553, "meta": {"task_id": "hard-sol-b-routing_hard-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "bbea997600fd4cc6b634b9c43ccf014f", "charged_usd": 0.0, "ts": 1790798262.37679, "meta": {"task_id": "hard-sol-b-routing_hard-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "fb9ac128b2aa4a23b165290ac49038e4", "reserved_usd": 0.02, "ts": 1790798262.3838544, "meta": {"task_id": "hard-sol-b-routing_hard-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "fb9ac128b2aa4a23b165290ac49038e4", "charged_usd": 0.0, "ts": 1790798262.4437556, "meta": {"task_id": "hard-sol-b-routing_hard-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "c20b02e640b443a5a3d92b248f0775d5", "reserved_usd": 0.02, "ts": 1790798262.4516823, "meta": {"task_id": "hard-sol-b-routing_hard-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "c20b02e640b443a5a3d92b248f0775d5", "charged_usd": 0.0, "ts": 1790798262.5097988, "meta": {"task_id": "hard-sol-b-routing_hard-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "0dcd09f3e1e24d4093008189bd507029", "reserved_usd": 0.02, "ts": 1790798262.518912, "meta": {"task_id": "hard-sol-b-temporal_numeric-01", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "0dcd09f3e1e24d4093008189bd507029", "charged_usd": 0.0, "ts": 1790798262.5772636, "meta": {"task_id": "hard-sol-b-temporal_numeric-01", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "25cc722aba964ca085971d8c60ff17f2", "reserved_usd": 0.02, "ts": 1790798262.5845861, "meta": {"task_id": "hard-sol-b-temporal_numeric-02", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "25cc722aba964ca085971d8c60ff17f2", "charged_usd": 0.0, "ts": 1790798262.642112, "meta": {"task_id": "hard-sol-b-temporal_numeric-02", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "62099025dd354a5791fe4000f5868b2b", "reserved_usd": 0.02, "ts": 1790798262.6485755, "meta": {"task_id": "hard-sol-b-temporal_numeric-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "62099025dd354a5791fe4000f5868b2b", "charged_usd": 0.0, "ts": 1790798262.7064745, "meta": {"task_id": "hard-sol-b-temporal_numeric-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "3c9edf384c0d453f93006710845f0280", "reserved_usd": 0.02, "ts": 1790798262.7132225, "meta": {"task_id": "hard-sol-b-temporal_numeric-04", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "3c9edf384c0d453f93006710845f0280", "charged_usd": 0.0, "ts": 1790798262.7717485, "meta": {"task_id": "hard-sol-b-temporal_numeric-04", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "06af4c8cf9b64d928a12ec4dfcd87780", "reserved_usd": 0.02, "ts": 1790798262.779106, "meta": {"task_id": "hard-sol-c-judge_hard-03", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "06af4c8cf9b64d928a12ec4dfcd87780", "charged_usd": 0.0, "ts": 1790798262.8379526, "meta": {"task_id": "hard-sol-c-judge_hard-03", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "1d923e54510a4b72af42188570bcad21", "reserved_usd": 0.02, "ts": 1790798262.8449638, "meta": {"task_id": "hard-sol-c-judge_hard-05", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "1d923e54510a4b72af42188570bcad21", "charged_usd": 0.0, "ts": 1790798262.9035194, "meta": {"task_id": "hard-sol-c-judge_hard-05", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "27d22e6cdf50468092baddb3fc3bd01c", "reserved_usd": 0.02, "ts": 1790798262.9107742, "meta": {"task_id": "hard-sol-c-judge_hard-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "27d22e6cdf50468092baddb3fc3bd01c", "charged_usd": 0.0, "ts": 1790798262.9693456, "meta": {"task_id": "hard-sol-c-judge_hard-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "e6f654e14fd5493181d0e2a3d1e324bd", "reserved_usd": 0.02, "ts": 1790798262.9779055, "meta": {"task_id": "hard-sol-c-judge_hard-08", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "e6f654e14fd5493181d0e2a3d1e324bd", "charged_usd": 0.0, "ts": 1790798263.0354629, "meta": {"task_id": "hard-sol-c-judge_hard-08", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7c487b6dd2e247e3a0a91dd3d413ebfe", "reserved_usd": 0.02, "ts": 1790798263.0420816, "meta": {"task_id": "hard-sol-c-judge_hard-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7c487b6dd2e247e3a0a91dd3d413ebfe", "charged_usd": 0.0, "ts": 1790798263.0995173, "meta": {"task_id": "hard-sol-c-judge_hard-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "855a946379dc4ac1965d490401bf1974", "reserved_usd": 0.02, "ts": 1790798263.1066015, "meta": {"task_id": "hard-sol-c-judge_hard-10", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "855a946379dc4ac1965d490401bf1974", "charged_usd": 0.0, "ts": 1790798263.1646004, "meta": {"task_id": "hard-sol-c-judge_hard-10", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "dbadb2c6fcaa429cabeba573ee6cf833", "reserved_usd": 0.02, "ts": 1790798263.1711452, "meta": {"task_id": "hard-sol-c-judge_hard-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "dbadb2c6fcaa429cabeba573ee6cf833", "charged_usd": 0.0, "ts": 1790798263.2306335, "meta": {"task_id": "hard-sol-c-judge_hard-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "7c778df49c2c43f8864d2c70311ddbbd", "reserved_usd": 0.02, "ts": 1790798263.2371361, "meta": {"task_id": "hard-sol-c-judge_hard-13", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "7c778df49c2c43f8864d2c70311ddbbd", "charged_usd": 0.0, "ts": 1790798263.2955127, "meta": {"task_id": "hard-sol-c-judge_hard-13", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "d083c52044934671994fe549dc21765b", "reserved_usd": 0.02, "ts": 1790798263.3015401, "meta": {"task_id": "hard-sol-c-judge_hard-15", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "d083c52044934671994fe549dc21765b", "charged_usd": 0.0, "ts": 1790798263.3590791, "meta": {"task_id": "hard-sol-c-judge_hard-15", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "2a6b029c8d6544a5937d67be767ea0a3", "reserved_usd": 0.02, "ts": 1790798263.3658307, "meta": {"task_id": "hard-sol-c-multi_hop-07", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "2a6b029c8d6544a5937d67be767ea0a3", "charged_usd": 0.0, "ts": 1790798263.5023403, "meta": {"task_id": "hard-sol-c-multi_hop-07", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "da457d5abb034c78b0d973c605b3f859", "reserved_usd": 0.02, "ts": 1790798263.5110981, "meta": {"task_id": "hard-sol-c-multi_hop-09", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "da457d5abb034c78b0d973c605b3f859", "charged_usd": 0.0, "ts": 1790798263.6487644, "meta": {"task_id": "hard-sol-c-multi_hop-09", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "f2408dbce68a49d4bcc2d25aa616c8cc", "reserved_usd": 0.02, "ts": 1790798263.6578279, "meta": {"task_id": "hard-sol-c-multi_hop-11", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "f2408dbce68a49d4bcc2d25aa616c8cc", "charged_usd": 0.0, "ts": 1790798263.8020973, "meta": {"task_id": "hard-sol-c-multi_hop-11", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "dc7d2a78d91a438b9b95594042762404", "reserved_usd": 0.02, "ts": 1790798263.8113334, "meta": {"task_id": "hard-sol-c-multi_hop-12", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "dc7d2a78d91a438b9b95594042762404", "charged_usd": 0.0, "ts": 1790798263.880316, "meta": {"task_id": "hard-sol-c-multi_hop-12", "basis": "zero_route_fee_compute_excluded"}} +{"event": "reserve", "reservation_id": "e916a8bbb71f420ba813f4eafb7bc8dc", "reserved_usd": 0.02, "ts": 1790798263.887308, "meta": {"task_id": "hard-sol-c-multi_hop-13", "adapter": "typesafe"}} +{"event": "settle", "reservation_id": "e916a8bbb71f420ba813f4eafb7bc8dc", "charged_usd": 0.0, "ts": 1790798264.026431, "meta": {"task_id": "hard-sol-c-multi_hop-13", "basis": "zero_route_fee_compute_excluded"}} diff --git a/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-manifest.json b/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-manifest.json new file mode 100644 index 0000000..77706c7 --- /dev/null +++ b/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-manifest.json @@ -0,0 +1,21 @@ +{ + "adapter": "typesafe", + "charged_usd": 0.0, + "cost_basis": null, + "dataset_hash": "dc3995d8ae1e2fc8e81ce38431add509eb8bb39b85aadfd0c7c32079382dde51", + "delay_s": 0.0, + "endpoint": "http://intern-decision.fv.internal:8033", + "finished_utc": "2026-09-30T19:57:44.055953+00:00", + "key_env_used": true, + "n_attempted": 231, + "n_planned": 231, + "price_input_per_m": 0.0, + "price_output_per_m": 0.0, + "request_options": {}, + "requested_model": null, + "resolved_models": [ + "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd" + ], + "run_label": "typesafe", + "started_utc": "2026-09-30T19:57:18.649032+00:00" +} \ No newline at end of file diff --git a/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-results.jsonl b/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-results.jsonl new file mode 100644 index 0000000..4dcfb45 --- /dev/null +++ b/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-results.jsonl @@ -0,0 +1,231 @@ +{"task_id": "easy-intent-00", "family": "intent", "split": "public", "group": null, "ts": 1790798238.7320504, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "track_order", "ordinal_ev": null, "probs": {"billing_question": 0.0037157811604703298, "cancel_order": 0.003078293568895903, "change_address": 0.001361767731259195, "report_damage": 0.0032776061174943907, "track_order": 0.9885665514218801}, "probs_as_returned": {"billing_question": 0.0037157811604703298, "cancel_order": 0.003078293568895903, "change_address": 0.001361767731259195, "report_damage": 0.0032776061174943907, "track_order": 0.9885665514218801}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06609244598075747, "usage": {"input_tokens": 237, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4514624eb9683768f321959e389dbe6ef0945b853a432db1e99ba7a7f26345e8", "runtime": null} +{"task_id": "easy-intent-01", "family": "intent", "split": "public", "group": null, "ts": 1790798238.7945983, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cancel_order", "ordinal_ev": null, "probs": {"billing_question": 0.008350062041863383, "cancel_order": 0.9827395556133772, "change_address": 0.002380980312875335, "report_damage": 0.003060149037375123, "track_order": 0.003469252994509084}, "probs_as_returned": {"billing_question": 0.008350062041863383, "cancel_order": 0.9827395556133772, "change_address": 0.002380980312875335, "report_damage": 0.003060149037375123, "track_order": 0.003469252994509084}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05283547198632732, "usage": {"input_tokens": 237, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8368b57c796ce5b5beb75d44b08b51f7834a71bf0b64819b6eee8ee1bccc8b96", "runtime": null} +{"task_id": "easy-intent-02", "family": "intent", "split": "public", "group": null, "ts": 1790798238.8561182, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "change_address", "ordinal_ev": null, "probs": {"billing_question": 0.006453941294493193, "cancel_order": 0.004160046017396561, "change_address": 0.976248827903928, "report_damage": 0.0053466891642593726, "track_order": 0.007790495619922923}, "probs_as_returned": {"billing_question": 0.006453941294493193, "cancel_order": 0.004160046017396561, "change_address": 0.976248827903928, "report_damage": 0.0053466891642593726, "track_order": 0.007790495619922923}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05276026198407635, "usage": {"input_tokens": 239, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "3d534ff746c9f7c5425bf9322592aaa9f7b4221f9e5792fc80b53d20bd542d22", "runtime": null} +{"task_id": "easy-intent-03", "family": "intent", "split": "public", "group": null, "ts": 1790798238.9169612, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "report_damage", "ordinal_ev": null, "probs": {"billing_question": 0.0032856469914429327, "cancel_order": 0.0024009737772375207, "change_address": 0.0014534960934417126, "report_damage": 0.9909917808872951, "track_order": 0.0018681022505827403}, "probs_as_returned": {"billing_question": 0.0032856469914429327, "cancel_order": 0.0024009737772375207, "change_address": 0.0014534960934417126, "report_damage": 0.9909917808872951, "track_order": 0.0018681022505827403}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.052977222949266434, "usage": {"input_tokens": 228, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "620d63f3a6437857ddcc391af828b7fd57d6980b8e670416c4c538c336394131", "runtime": null} +{"task_id": "easy-intent-04", "family": "intent", "split": "public", "group": null, "ts": 1790798238.9786363, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "billing_question", "ordinal_ev": null, "probs": {"billing_question": 0.9920142822722872, "cancel_order": 0.005433032876037771, "change_address": 0.0007769531103232375, "report_damage": 0.0011320744243103107, "track_order": 0.000643657317041507}, "probs_as_returned": {"billing_question": 0.9920142822722872, "cancel_order": 0.005433032876037771, "change_address": 0.0007769531103232375, "report_damage": 0.0011320744243103107, "track_order": 0.000643657317041507}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05310912802815437, "usage": {"input_tokens": 233, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1317d8636137ad327b49008a868e3397e33906ceef5724845150085078a4a829", "runtime": null} +{"task_id": "easy-intent-05", "family": "intent", "split": "public", "group": null, "ts": 1790798239.0404685, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "track_order", "ordinal_ev": null, "probs": {"billing_question": 0.005069572552208189, "cancel_order": 0.003479294303948175, "change_address": 0.0023878717693975727, "report_damage": 0.003479294303948175, "track_order": 0.9855839670704978}, "probs_as_returned": {"billing_question": 0.005069572552208189, "cancel_order": 0.003479294303948175, "change_address": 0.0023878717693975727, "report_damage": 0.003479294303948175, "track_order": 0.9855839670704978}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.052612571977078915, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1c982edbb0cb4173f26c1f5dfdec83481d7834bd148b0748868b2e7e29d31329", "runtime": null} +{"task_id": "easy-intent-06", "family": "intent", "split": "public", "group": null, "ts": 1790798239.1027277, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "set_alarm", "ordinal_ev": null, "probs": {"play_music": 0.006093371416719093, "send_message": 0.003927632182349683, "set_alarm": 0.9813860625238946, "turn_off_lights": 0.005722831872794024, "weather": 0.0028701020042427037}, "probs_as_returned": {"play_music": 0.006093371416719093, "send_message": 0.003927632182349683, "set_alarm": 0.9813860625238946, "turn_off_lights": 0.005722831872794024, "weather": 0.0028701020042427037}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053734806017018855, "usage": {"input_tokens": 225, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "049773108f5e7dd405ad36213739d4ffe2f4acc1e6c1f120a07f0dbc317575fa", "runtime": null} +{"task_id": "easy-intent-07", "family": "intent", "split": "public", "group": null, "ts": 1790798239.1645494, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "play_music", "ordinal_ev": null, "probs": {"play_music": 0.9889646607601771, "send_message": 0.00653800507921397, "set_alarm": 0.0017509134460344028, "turn_off_lights": 0.0017509134460344028, "weather": 0.000995507268540069}, "probs_as_returned": {"play_music": 0.9889646607601771, "send_message": 0.00653800507921397, "set_alarm": 0.0017509134460344028, "turn_off_lights": 0.0017509134460344028, "weather": 0.000995507268540069}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05340296804206446, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "fbfcb24ff81cc18a8c22195e4fcbb995f680ff748558c6be2f0a54a08490e8fa", "runtime": null} +{"task_id": "easy-intent-08", "family": "intent", "split": "public", "group": null, "ts": 1790798239.2326345, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "weather", "ordinal_ev": null, "probs": {"play_music": 0.0073499617445077865, "send_message": 0.00417892749053501, "set_alarm": 0.0030537350538425087, "turn_off_lights": 0.0047375981872448125, "weather": 0.9806797775238698}, "probs_as_returned": {"play_music": 0.0073499617445077865, "send_message": 0.00417892749053501, "set_alarm": 0.0030537350538425087, "turn_off_lights": 0.0047375981872448125, "weather": 0.9806797775238698}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.059098818979691714, "usage": {"input_tokens": 220, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "dc0d2aa413915453edafa844532510a937024c8331c87435d9fbdd680047beb0", "runtime": null} +{"task_id": "easy-intent-09", "family": "intent", "split": "public", "group": null, "ts": 1790798239.2946787, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "send_message", "ordinal_ev": null, "probs": {"play_music": 0.012056092798137684, "send_message": 0.9738121212463231, "set_alarm": 0.004418343519024835, "turn_off_lights": 0.004704420988497517, "weather": 0.005009021448016902}, "probs_as_returned": {"play_music": 0.012056092798137684, "send_message": 0.9738121212463231, "set_alarm": 0.004418343519024835, "turn_off_lights": 0.004704420988497517, "weather": 0.005009021448016902}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05384727305499837, "usage": {"input_tokens": 223, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a9ac702c1fd910e4c5038d6765dab4abe2d3b39efe71e1c432a04a73ee2ebf3e", "runtime": null} +{"task_id": "easy-intent-10", "family": "intent", "split": "public", "group": null, "ts": 1790798239.35951, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "turn_off_lights", "ordinal_ev": null, "probs": {"play_music": 0.0037055333570594024, "send_message": 0.0034801987605495434, "set_alarm": 0.0032685666377679874, "turn_off_lights": 0.9858401678875638, "weather": 0.0037055333570594024}, "probs_as_returned": {"play_music": 0.0037055333570594024, "send_message": 0.0034801987605495434, "set_alarm": 0.0032685666377679874, "turn_off_lights": 0.9858401678875638, "weather": 0.0037055333570594024}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054713898978661746, "usage": {"input_tokens": 221, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8ff1504e3b89b876c3ede7808292d348e8983047933782d993fe1f1db16a6407", "runtime": null} +{"task_id": "easy-intent-11", "family": "intent", "split": "public", "group": null, "ts": 1790798239.423728, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "set_alarm", "ordinal_ev": null, "probs": {"play_music": 0.00611383130526039, "send_message": 0.0027046210473488227, "set_alarm": 0.9846812885886964, "turn_off_lights": 0.004756929120067906, "weather": 0.0017433299386264444}, "probs_as_returned": {"play_music": 0.00611383130526039, "send_message": 0.0027046210473488227, "set_alarm": 0.9846812885886964, "turn_off_lights": 0.004756929120067906, "weather": 0.0017433299386264444}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054407514980994165, "usage": {"input_tokens": 221, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ea5e071c38d4d6066b61e675d245b65f27ac17e0abaeebba8b5d9386c971e986", "runtime": null} +{"task_id": "easy-fact-00", "family": "fact", "split": "public", "group": null, "ts": 1790798239.4866815, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9710643566281367, "no": 0.028935643371863273}, "probs_as_returned": {"yes": 0.9710643566281367, "no": 0.028935643371863273}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0532659359741956, "usage": {"input_tokens": 199, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d878da6e0b97d627124b0a4794d127c7349cee00087a1e887226ff0a7ee2a38c", "runtime": null} +{"task_id": "easy-fact-01", "family": "fact", "split": "public", "group": null, "ts": 1790798239.5510871, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.010802420461426548, "no": 0.9891975795385735}, "probs_as_returned": {"yes": 0.010802420461426548, "no": 0.9891975795385735}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05331841896986589, "usage": {"input_tokens": 197, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "205a2f09e6ba9fd71444f01aa5ce85f6aba2515683f8e0b92586866df3466693", "runtime": null} +{"task_id": "easy-fact-02", "family": "fact", "split": "public", "group": null, "ts": 1790798239.6114492, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9743891388556707, "no": 0.02561086114432931}, "probs_as_returned": {"yes": 0.9743891388556707, "no": 0.02561086114432931}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05238888500025496, "usage": {"input_tokens": 205, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f3c224df5b539d56f2caddc3c581fb6551c2e3f4af2c5365a17977b5ea03aae6", "runtime": null} +{"task_id": "easy-fact-03", "family": "fact", "split": "public", "group": null, "ts": 1790798239.6719594, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.011493812770397228, "no": 0.9885061872296028}, "probs_as_returned": {"yes": 0.011493812770397228, "no": 0.9885061872296028}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.052541400014888495, "usage": {"input_tokens": 208, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8e00b9c7ce0be60ec071c00901888fe7709560b3a03655f73b2cabadc332f98c", "runtime": null} +{"task_id": "easy-fact-04", "family": "fact", "split": "public", "group": null, "ts": 1790798239.73332, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9710643566281367, "no": 0.028935643371863273}, "probs_as_returned": {"yes": 0.9710643566281367, "no": 0.028935643371863273}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05279545299708843, "usage": {"input_tokens": 197, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2e47e3a49221389b307e4d3a77bc644d27491da3124d31f23d58e9070d4878e3", "runtime": null} +{"task_id": "easy-fact-05", "family": "fact", "split": "public", "group": null, "ts": 1790798239.7953045, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.07967467169628852, "no": 0.9203253283037115}, "probs_as_returned": {"yes": 0.07967467169628852, "no": 0.9203253283037115}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05346314300550148, "usage": {"input_tokens": 198, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2177f1de1e17e1d8789541f11f8d14a63b0fde0a44b43ae7f38db206ac729caa", "runtime": null} +{"task_id": "easy-fact-06", "family": "fact", "split": "public", "group": null, "ts": 1790798239.8552246, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9608203271108413, "no": 0.03917967288915869}, "probs_as_returned": {"yes": 0.9608203271108413, "no": 0.03917967288915869}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05262259900337085, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "27edc3741cf909f25a883ebdf4cb37cc571589704ba241e0e8475106bf7d5931", "runtime": null} +{"task_id": "easy-fact-07", "family": "fact", "split": "public", "group": null, "ts": 1790798239.9148104, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "probs_as_returned": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05239791702479124, "usage": {"input_tokens": 193, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1ffd9d74601a75827a072c7dd3652d025389c94b5ca9a3607a5ecc09f508d0aa", "runtime": null} +{"task_id": "easy-fact-08", "family": "fact", "split": "public", "group": null, "ts": 1790798239.9749506, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9759090252955993, "no": 0.02409097470440069}, "probs_as_returned": {"yes": 0.9759090252955993, "no": 0.02409097470440069}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.052400070999283344, "usage": {"input_tokens": 189, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "098fe53c245387d4a08a38a1cc2eefe4a22f76b2bf99fb1d923e42a1e2d98f62", "runtime": null} +{"task_id": "easy-fact-09", "family": "fact", "split": "public", "group": null, "ts": 1790798240.036027, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.013841134222312299, "no": 0.9861588657776877}, "probs_as_returned": {"yes": 0.013841134222312299, "no": 0.9861588657776877}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0536329869646579, "usage": {"input_tokens": 189, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ad93ce925fc515f54bdbefaa791d2cbc33a59a09a07a597dfa6fa244965520ff", "runtime": null} +{"task_id": "easy-fact-10", "family": "fact", "split": "public", "group": null, "ts": 1790798240.0965762, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9405016353866033, "no": 0.05949836461339675}, "probs_as_returned": {"yes": 0.9405016353866033, "no": 0.05949836461339675}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053037685982417315, "usage": {"input_tokens": 197, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b7fbb65257b5eed0021c8ecce9f30a321a638c3ee67f6ca3212333f9dc681ea0", "runtime": null} +{"task_id": "easy-fact-11", "family": "fact", "split": "public", "group": null, "ts": 1790798240.159645, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.012228909296002857, "no": 0.9877710907039972}, "probs_as_returned": {"yes": 0.012228909296002857, "no": 0.9877710907039972}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054156975995283574, "usage": {"input_tokens": 198, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "41189a5c1696eb51062289fe4d33c15742c600872d3a284a4d034398e8dfa5fb", "runtime": null} +{"task_id": "easy-extraction-00", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.2243328, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "paypal", "ordinal_ev": null, "probs": {"bank_transfer": 0.005387207125398065, "cash": 0.004462965891172113, "credit_card": 0.006502850175498755, "paypal": 0.9836469768079311}, "probs_as_returned": {"bank_transfer": 0.005387207125398065, "cash": 0.004462965891172113, "credit_card": 0.006502850175498755, "paypal": 0.9836469768079311}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05600597697775811, "usage": {"input_tokens": 191, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "69cc44e9263f230d21c2e173cdf873a029430e541ca5bcddec8a1837d4eaefed", "runtime": null} +{"task_id": "easy-extraction-01", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.2923846, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cash", "ordinal_ev": null, "probs": {"bank_transfer": 0.005362202749492144, "cash": 0.9790814538511988, "credit_card": 0.011384226924270966, "paypal": 0.004172116475037995}, "probs_as_returned": {"bank_transfer": 0.005362202749492144, "cash": 0.9790814538511988, "credit_card": 0.011384226924270966, "paypal": 0.004172116475037995}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.057605537003837526, "usage": {"input_tokens": 193, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "22a75904dfbd69debdcbf7c350b4d8bca9f439fd14c35450b2425864b6b35f69", "runtime": null} +{"task_id": "easy-extraction-02", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.355176, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "bank_transfer", "ordinal_ev": null, "probs": {"bank_transfer": 0.9886611045091759, "cash": 0.006959188878070115, "credit_card": 0.002395327053946649, "paypal": 0.001984379558807392}, "probs_as_returned": {"bank_transfer": 0.9886611045091759, "cash": 0.006959188878070115, "credit_card": 0.002395327053946649, "paypal": 0.001984379558807392}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05319781904108822, "usage": {"input_tokens": 194, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "13cb3660567a013fb5d12233347a3e8f3f331a272173d8aa7aaf54150c687903", "runtime": null} +{"task_id": "easy-extraction-03", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.4155009, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "high", "ordinal_ev": null, "probs": {"high": 0.9233443241587275, "low": 0.012959506894251118, "medium": 0.01217143488730339, "urgent": 0.051524734059717935}, "probs_as_returned": {"high": 0.9233443241587275, "low": 0.012959506894251118, "medium": 0.01217143488730339, "urgent": 0.051524734059717935}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0524761849665083, "usage": {"input_tokens": 196, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "bfae07e4c4a5b97430881b8e6a28b6a87717f8279393ba7cf0ce945b13e46654", "runtime": null} +{"task_id": "easy-extraction-04", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.475359, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "low", "ordinal_ev": null, "probs": {"high": 0.012079556291950424, "low": 0.9757073270220792, "medium": 0.007786174264223241, "urgent": 0.004426942421747175}, "probs_as_returned": {"high": 0.012079556291950424, "low": 0.9757073270220792, "medium": 0.007786174264223241, "urgent": 0.004426942421747175}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05214233201695606, "usage": {"input_tokens": 194, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b110ed1ade581ce788d53150b4ce197bb06dc4c8d59b7ce0233d443d6b9db537", "runtime": null} +{"task_id": "easy-extraction-05", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.534182, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "urgent", "ordinal_ev": null, "probs": {"high": 0.012123545380943897, "low": 0.004172879641756854, "medium": 0.004443063766191328, "urgent": 0.9792605112111079}, "probs_as_returned": {"high": 0.012123545380943897, "low": 0.004172879641756854, "medium": 0.004443063766191328, "urgent": 0.9792605112111079}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05179836798924953, "usage": {"input_tokens": 194, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "27e86aed0bf319fe47512dc8f0a3f8b4a3395714d2682817ce25817ed2ad62da", "runtime": null} +{"task_id": "easy-extraction-06", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.595573, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "M", "ordinal_ev": null, "probs": {"L": 0.011362559593985683, "M": 0.9772179520276576, "S": 0.006067491605402367, "XL": 0.005351996772954305}, "probs_as_returned": {"L": 0.011362559593985683, "M": 0.9772179520276576, "S": 0.006067491605402367, "XL": 0.005351996772954305}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0529552279622294, "usage": {"input_tokens": 187, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ff880e6635d0ee708102ab83fa72493bffcf29963fbf5baa3783ac836f672057", "runtime": null} +{"task_id": "easy-extraction-07", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.6580687, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "XL", "ordinal_ev": null, "probs": {"L": 0.0236463954766581, "M": 0.009227085930027284, "S": 0.009227085930027284, "XL": 0.9578994326632874}, "probs_as_returned": {"L": 0.0236463954766581, "M": 0.009227085930027284, "S": 0.009227085930027284, "XL": 0.9578994326632874}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0535175779950805, "usage": {"input_tokens": 184, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8a41b3cce3b45c12e414da50050cd64675fc62eaff022e135f81d53c136c0012", "runtime": null} +{"task_id": "easy-extraction-08", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.7189376, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "thursday", "ordinal_ev": null, "probs": {"friday": 0.005378595700972278, "monday": 0.0030580785963976943, "thursday": 0.9820746521827389, "tuesday": 0.0047443367599455805, "wednesday": 0.0047443367599455805}, "probs_as_returned": {"friday": 0.005378595700972278, "monday": 0.0030580785963976943, "thursday": 0.9820746521827389, "tuesday": 0.0047443367599455805, "wednesday": 0.0047443367599455805}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053064427978824824, "usage": {"input_tokens": 195, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "bf28661f658019452a6d22d2b43464c52364a253bb64c85208ec85f48f5dcc8b", "runtime": null} +{"task_id": "easy-extraction-09", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.779957, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "monday", "ordinal_ev": null, "probs": {"friday": 0.006487826443252909, "monday": 0.9813744363156989, "thursday": 0.00223308577898157, "tuesday": 0.004181887565710403, "wednesday": 0.005722763896356328}, "probs_as_returned": {"friday": 0.006487826443252909, "monday": 0.9813744363156989, "thursday": 0.00223308577898157, "tuesday": 0.004181887565710403, "wednesday": 0.005722763896356328}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05255089100683108, "usage": {"input_tokens": 197, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8c4ab09ce8ed4f6342266b69b969f6356f1a8692f0bcc91d3a87b2dbb6f04a12", "runtime": null} +{"task_id": "easy-extraction-10", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.840048, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "friday", "ordinal_ev": null, "probs": {"friday": 0.9843070496345583, "monday": 0.005390822043802262, "thursday": 0.005063004435363676, "tuesday": 0.0019756402868039927, "wednesday": 0.0032634835994717003}, "probs_as_returned": {"friday": 0.9843070496345583, "monday": 0.005390822043802262, "thursday": 0.005063004435363676, "tuesday": 0.0019756402868039927, "wednesday": 0.0032634835994717003}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05286766798235476, "usage": {"input_tokens": 192, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e3ff13d392ff6741a4a0e8e9490b2d634a6cab63c8cc06849a4976b72e372b4b", "runtime": null} +{"task_id": "easy-extraction-11", "family": "extraction", "split": "public", "group": null, "ts": 1790798240.899239, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "credit_card", "ordinal_ev": null, "probs": {"bank_transfer": 0.00782696473030407, "cash": 0.004450134632367189, "credit_card": 0.9808189129742555, "paypal": 0.006903987663073161}, "probs_as_returned": {"bank_transfer": 0.00782696473030407, "cash": 0.004450134632367189, "credit_card": 0.9808189129742555, "paypal": 0.006903987663073161}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05166366801131517, "usage": {"input_tokens": 198, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7796f21128b64953568485dab1b7f49a1a0e8e0550c50fccbc9fbc5622f9b924", "runtime": null} +{"task_id": "easy-tool_selection-00", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798240.9589982, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "get_weather", "ordinal_ev": null, "probs": {"convert_currency": 0.007829807987743406, "create_calendar_event": 0.0032530999253130594, "get_weather": 0.9811752060057245, "send_email": 0.0050468950765359955, "translate_text": 0.0026949910046831105}, "probs_as_returned": {"convert_currency": 0.007829807987743406, "create_calendar_event": 0.0032530999253130594, "get_weather": 0.9811752060057245, "send_email": 0.0050468950765359955, "translate_text": 0.0026949910046831105}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05227820394793525, "usage": {"input_tokens": 227, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f70323029ee7b97ce7307802dc552ce98ff3da56d4f2685c115785bdf72514cb", "runtime": null} +{"task_id": "easy-tool_selection-01", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.0186362, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "send_email", "ordinal_ev": null, "probs": {"convert_currency": 0.004770803588408859, "create_calendar_event": 0.0034862463985914503, "get_weather": 0.001642093020855755, "send_email": 0.9875532959266949, "translate_text": 0.0025475610654490583}, "probs_as_returned": {"convert_currency": 0.004770803588408859, "create_calendar_event": 0.0034862463985914503, "get_weather": 0.001642093020855755, "send_email": 0.9875532959266949, "translate_text": 0.0025475610654490583}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05205978098092601, "usage": {"input_tokens": 229, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7aa01ce0bcf36de2774af20f10c71d51c16b7b1d79fab4104311695dce9f730a", "runtime": null} +{"task_id": "easy-tool_selection-02", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.0778768, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "create_calendar_event", "ordinal_ev": null, "probs": {"convert_currency": 0.006516607444799637, "create_calendar_event": 0.9857279498146715, "get_weather": 0.001978492219286686, "send_email": 0.0030694545003598877, "translate_text": 0.002707496020882359}, "probs_as_returned": {"convert_currency": 0.006516607444799637, "create_calendar_event": 0.9857279498146715, "get_weather": 0.001978492219286686, "send_email": 0.0030694545003598877, "translate_text": 0.002707496020882359}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05167615500977263, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5755c0279a396757452bba6b75d6b4d31532529bb9c4281888d78f4ab7f19632", "runtime": null} +{"task_id": "easy-tool_selection-03", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.138424, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "convert_currency", "ordinal_ev": null, "probs": {"convert_currency": 0.9879132695583835, "create_calendar_event": 0.0050815538345912745, "get_weather": 0.0017490519673023376, "send_email": 0.0015427989590568122, "translate_text": 0.003713325680665897}, "probs_as_returned": {"convert_currency": 0.9879132695583835, "create_calendar_event": 0.0050815538345912745, "get_weather": 0.0017490519673023376, "send_email": 0.0015427989590568122, "translate_text": 0.003713325680665897}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0527269080048427, "usage": {"input_tokens": 229, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6a4175c4f14f74defc76778483062eb2203ffa7e507a51e2e096684b2ef845bb", "runtime": null} +{"task_id": "easy-tool_selection-04", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.1986237, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "translate_text", "ordinal_ev": null, "probs": {"convert_currency": 0.0065024668896828735, "create_calendar_event": 0.004462702891725051, "get_weather": 0.002383038386749453, "send_email": 0.0030627940173430794, "translate_text": 0.9835889978144995}, "probs_as_returned": {"convert_currency": 0.0065024668896828735, "create_calendar_event": 0.004462702891725051, "get_weather": 0.002383038386749453, "send_email": 0.0030627940173430794, "translate_text": 0.9835889978144995}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05239356803940609, "usage": {"input_tokens": 226, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "76ace10b57d5a79d04ffb03940dee3a847a6b3f0f64f68edcbf33ce6df945210", "runtime": null} +{"task_id": "easy-tool_selection-05", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.2610114, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "create_calendar_event", "ordinal_ev": null, "probs": {"convert_currency": 0.007354093936894176, "create_calendar_event": 0.9812311228123023, "get_weather": 0.0022327596869927153, "send_email": 0.006486878942590166, "translate_text": 0.002695144621220672}, "probs_as_returned": {"convert_currency": 0.007354093936894176, "create_calendar_event": 0.9812311228123023, "get_weather": 0.0022327596869927153, "send_email": 0.006486878942590166, "translate_text": 0.002695144621220672}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.052587932033929974, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5382e2a6b0288663083caa0ac1fd79be0b0abb558bc24344b795e19be1927354", "runtime": null} +{"task_id": "easy-tool_selection-06", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.3245406, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "search_flights", "ordinal_ev": null, "probs": {"book_restaurant": 0.002723028128906097, "call_taxi": 0.0022558595435807336, "get_stock_price": 0.0019898423713477923, "search_flights": 0.9913828092209783, "set_reminder": 0.0016484607351869884}, "probs_as_returned": {"book_restaurant": 0.002723028128906097, "call_taxi": 0.0022558595435807336, "get_stock_price": 0.0019898423713477923, "search_flights": 0.9913828092209783, "set_reminder": 0.0016484607351869884}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05283860396593809, "usage": {"input_tokens": 236, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "fbb02aa3b962f959f4d5c622a07966439b2bf897d1a7f8a6796d7d6ad7e5d9f8", "runtime": null} +{"task_id": "easy-tool_selection-07", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.3909948, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "book_restaurant", "ordinal_ev": null, "probs": {"book_restaurant": 0.9875027503742834, "call_taxi": 0.005758500527357331, "get_stock_price": 0.0010583971646233432, "search_flights": 0.0011998917646541929, "set_reminder": 0.004480460169081839}, "probs_as_returned": {"book_restaurant": 0.9875027503742834, "call_taxi": 0.005758500527357331, "get_stock_price": 0.0010583971646233432, "search_flights": 0.0011998917646541929, "set_reminder": 0.004480460169081839}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05746507301228121, "usage": {"input_tokens": 236, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a3819445d678f9d221bc2d9d81b3a3419e5a34e9d57ab093631d5f5c947349e3", "runtime": null} +{"task_id": "easy-tool_selection-08", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.4587662, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "set_reminder", "ordinal_ev": null, "probs": {"book_restaurant": 0.0027204340659280554, "call_taxi": 0.0022537104865137892, "get_stock_price": 0.0018670590411967879, "search_flights": 0.0027204340659280554, "set_reminder": 0.9904383623404333}, "probs_as_returned": {"book_restaurant": 0.0027204340659280554, "call_taxi": 0.0022537104865137892, "get_stock_price": 0.0018670590411967879, "search_flights": 0.0027204340659280554, "set_reminder": 0.9904383623404333}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05939583299914375, "usage": {"input_tokens": 235, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f4f6d95ae582aaa1e4353f41c12f7799d643f37000618d96ed97171ebb25d5f0", "runtime": null} +{"task_id": "easy-tool_selection-09", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.5242615, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "get_stock_price", "ordinal_ev": null, "probs": {"book_restaurant": 0.006098491673709373, "call_taxi": 0.0030585022990139332, "get_stock_price": 0.98221073526815, "search_flights": 0.006098491673709373, "set_reminder": 0.0025337790854174126}, "probs_as_returned": {"book_restaurant": 0.006098491673709373, "call_taxi": 0.0030585022990139332, "get_stock_price": 0.98221073526815, "search_flights": 0.006098491673709373, "set_reminder": 0.0025337790854174126}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.057231393991969526, "usage": {"input_tokens": 231, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "bf53efeb12adff8b02aa013811100e2403c11d485980caa05231bb62f0f4c6d0", "runtime": null} +{"task_id": "easy-tool_selection-10", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.58557, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "call_taxi", "ordinal_ev": null, "probs": {"book_restaurant": 0.008868475619137011, "call_taxi": 0.9802820079262876, "get_stock_price": 0.002230600011225041, "search_flights": 0.0053687778295083005, "set_reminder": 0.0032501386138420975}, "probs_as_returned": {"book_restaurant": 0.008868475619137011, "call_taxi": 0.9802820079262876, "get_stock_price": 0.002230600011225041, "search_flights": 0.0053687778295083005, "set_reminder": 0.0032501386138420975}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05387516203336418, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9e63f0f0b5768b9b733c46d7ff13e39d95575077c8b502f35a25596e1ea7eb29", "runtime": null} +{"task_id": "easy-tool_selection-11", "family": "tool_selection", "split": "public", "group": null, "ts": 1790798241.64732, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "set_reminder", "ordinal_ev": null, "probs": {"book_restaurant": 0.0024029836241437775, "call_taxi": 0.0018696659764764975, "get_stock_price": 0.0016491898330211032, "search_flights": 0.002256857361858334, "set_reminder": 0.9918213032045002}, "probs_as_returned": {"book_restaurant": 0.0024029836241437775, "call_taxi": 0.0018696659764764975, "get_stock_price": 0.0016491898330211032, "search_flights": 0.002256857361858334, "set_reminder": 0.9918213032045002}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053899799997452646, "usage": {"input_tokens": 235, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2a6d4b29ebe7a1259dcab75d70baef81981673a73b9b127d850cb2063f4d5a0e", "runtime": null} +{"task_id": "original-policy-01-0", "family": "policy", "split": "public", "group": "original-policy-01", "ts": 1790798241.7091625, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.022659190258890113, "no": 0.9773408097411099}, "probs_as_returned": {"yes": 0.022659190258890113, "no": 0.9773408097411099}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0542533440166153, "usage": {"input_tokens": 219, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6753c27bb08bb22825cad028aff5761377c7f572d31edde8ffc6a244c5559b4d", "runtime": null} +{"task_id": "original-policy-01-1", "family": "policy", "split": "public", "group": "original-policy-01", "ts": 1790798241.7704496, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.005797568831524007, "no": 0.994202431168476}, "probs_as_returned": {"yes": 0.005797568831524007, "no": 0.994202431168476}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05332394799916074, "usage": {"input_tokens": 221, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "3f3d0f4e1729e55f24b4c71817fee746593b6b48f9cb3da557e9afe4514f42c7", "runtime": null} +{"task_id": "original-policy-02-0", "family": "policy", "split": "public", "group": "original-policy-02", "ts": 1790798241.8328776, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9652800911770798, "no": 0.0347199088229202}, "probs_as_returned": {"yes": 0.9652800911770798, "no": 0.0347199088229202}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05433333700057119, "usage": {"input_tokens": 208, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "288b0ff9906a5f0c73fe6e21e820f2ba15c98e44c1e68fa80e03e2444bff7f37", "runtime": null} +{"task_id": "original-policy-02-1", "family": "policy", "split": "public", "group": "original-policy-02", "ts": 1790798241.8954616, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "probs_as_returned": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05430796497967094, "usage": {"input_tokens": 206, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b18f4bf3e1fdff892ebe9c8bf744b7ec7849692eb71c41254cab618179cf5127", "runtime": null} +{"task_id": "original-policy-03-0", "family": "policy", "split": "public", "group": "original-policy-03", "ts": 1790798241.9582064, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8879876242264044, "no": 0.11201237577359557}, "probs_as_returned": {"yes": 0.8879876242264044, "no": 0.11201237577359557}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05400517501402646, "usage": {"input_tokens": 210, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f890739036b55c48068e7e6286f9b55c0cf2a84fafb5b35ecc8b75db8a3f0d7c", "runtime": null} +{"task_id": "original-policy-03-1", "family": "policy", "split": "public", "group": "original-policy-03", "ts": 1790798242.0193846, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "probs_as_returned": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05360740900505334, "usage": {"input_tokens": 209, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a6a4cdbfb0c97b778d8bc8f93707efd843b2471609ce958bf999f2d80fb0c61c", "runtime": null} +{"task_id": "original-policy-04-0", "family": "policy", "split": "public", "group": "original-policy-04", "ts": 1790798242.0832067, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.09461348765523125, "no": 0.9053865123447687}, "probs_as_returned": {"yes": 0.09461348765523125, "no": 0.9053865123447687}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05632407602388412, "usage": {"input_tokens": 216, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6524d404ffa0e9fb8de935a5616a090d1bc9fa272242e0fd8b9239c98f723ad1", "runtime": null} +{"task_id": "original-policy-04-1", "family": "policy", "split": "public", "group": "original-policy-04", "ts": 1790798242.145682, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.012228909296002857, "no": 0.9877710907039972}, "probs_as_returned": {"yes": 0.012228909296002857, "no": 0.9877710907039972}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05408247496234253, "usage": {"input_tokens": 212, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e69df9298875262f77f1bb127b4d9ebfb87eaec6225ff02cd28f52cff2e6c84f", "runtime": null} +{"task_id": "original-policy-05-0", "family": "policy", "split": "public", "group": "original-policy-05", "ts": 1790798242.2085059, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.03917967288915878, "no": 0.9608203271108412}, "probs_as_returned": {"yes": 0.03917967288915878, "no": 0.9608203271108412}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05441639298805967, "usage": {"input_tokens": 220, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f91a7ce0467dff32d18ba4caf6fdc1211257e4e6b200f51f43f08a5d310a0299", "runtime": null} +{"task_id": "original-policy-05-1", "family": "policy", "split": "public", "group": "original-policy-05", "ts": 1790798242.2742817, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.04979902705524531, "no": 0.9502009729447547}, "probs_as_returned": {"yes": 0.04979902705524531, "no": 0.9502009729447547}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05742331099463627, "usage": {"input_tokens": 212, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "723218e8b9cee81da0e09d6b0df69f2e96d3a8b0a4201238c67d892025dd7f35", "runtime": null} +{"task_id": "original-policy-06-0", "family": "policy", "split": "public", "group": "original-policy-06", "ts": 1790798242.3393924, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "probs_as_returned": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05605236999690533, "usage": {"input_tokens": 222, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d8ce1237060ac2867b2ab3b7b3f5f00add144b0c8a9694879b74efdccfa8344c", "runtime": null} +{"task_id": "original-policy-06-1", "family": "policy", "split": "public", "group": "original-policy-06", "ts": 1790798242.4021442, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8604937671763584, "no": 0.1395062328236416}, "probs_as_returned": {"yes": 0.8604937671763584, "no": 0.1395062328236416}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05391103500733152, "usage": {"input_tokens": 211, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f8a5538573ec25070d5f6bfb318ab5405888e51f2db0b4239f5c63f99ebe3020", "runtime": null} +{"task_id": "original-intent-01-0", "family": "intent", "split": "public", "group": "original-intent-01", "ts": 1790798242.464037, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "refund", "ordinal_ev": null, "probs": {"cancel": 0.019858206552561444, "change_address": 0.007277679357392087, "other": 0.11503962460331064, "refund": 0.8565281796860903, "status": 0.0012963098006456009}, "probs_as_returned": {"cancel": 0.019858206552561444, "change_address": 0.007277679357392087, "other": 0.11503962460331064, "refund": 0.8565281796860903, "status": 0.0012963098006456009}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054142698005307466, "usage": {"input_tokens": 216, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "0bd27efdfc2b80394c8f2c152761e9a2b949931a5f8e2f05cdc88d3e4f5ff2ac", "runtime": null} +{"task_id": "original-intent-01-1", "family": "intent", "split": "public", "group": "original-intent-01", "ts": 1790798242.531465, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "refund", "ordinal_ev": null, "probs": {"cancel": 0.013157397907281692, "change_address": 0.010900086144070705, "other": 0.19533400388242703, "refund": 0.7766138243051219, "status": 0.003994687761098555}, "probs_as_returned": {"cancel": 0.013157397907281692, "change_address": 0.010900086144070705, "other": 0.19533400388242703, "refund": 0.7766138243051219, "status": 0.003994687761098555}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.059145299019292, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4718c9685a09ed8584fe1e256a3e41b97f26459e514e3d4703b3bd9735f17264", "runtime": null} +{"task_id": "original-intent-02-0", "family": "intent", "split": "public", "group": "original-intent-02", "ts": 1790798242.59353, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "other", "ordinal_ev": null, "probs": {"cancel": 0.011108283739639322, "change_address": 0.017233512714200254, "other": 0.4791247461286767, "refund": 0.013408711288806937, "status": 0.4791247461286767}, "probs_as_returned": {"cancel": 0.011108283739639322, "change_address": 0.017233512714200254, "other": 0.4791247461286767, "refund": 0.013408711288806937, "status": 0.4791247461286767}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05460492899874225, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "12324517e48b78c65dedb6217f310b9eec4ed2da8088b8afa09ceb1bf48159df", "runtime": null} +{"task_id": "original-intent-02-1", "family": "intent", "split": "public", "group": "original-intent-02", "ts": 1790798242.6546605, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "status", "ordinal_ev": null, "probs": {"cancel": 0.002321175467540561, "change_address": 0.0031764458100722866, "other": 0.0323645156724377, "refund": 0.004082518984442435, "status": 0.958055344065507}, "probs_as_returned": {"cancel": 0.002321175467540561, "change_address": 0.0031764458100722866, "other": 0.0323645156724377, "refund": 0.004082518984442435, "status": 0.958055344065507}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0540599970263429, "usage": {"input_tokens": 217, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "90efa47440cd270d9e6bad6f841a3c44559e4d6d8c42977cf6dc682b17fd88f0", "runtime": null} +{"task_id": "original-intent-03-0", "family": "intent", "split": "public", "group": "original-intent-03", "ts": 1790798242.7160296, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "change_address", "ordinal_ev": null, "probs": {"cancel": 0.009915815183017014, "change_address": 0.9080094929418733, "other": 0.04469398562198547, "refund": 0.011969292639071262, "status": 0.02541141361405287}, "probs_as_returned": {"cancel": 0.009915815183017014, "change_address": 0.9080094929418733, "other": 0.04469398562198547, "refund": 0.011969292639071262, "status": 0.02541141361405287}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05364580295281485, "usage": {"input_tokens": 218, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8cd729a66d35ce27defc353c3c46321997f9bec95678ac185acb1a90d607732c", "runtime": null} +{"task_id": "original-intent-03-1", "family": "intent", "split": "public", "group": "original-intent-03", "ts": 1790798242.777007, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "change_address", "ordinal_ev": null, "probs": {"cancel": 0.006265845660924066, "change_address": 0.947796734818206, "other": 0.03409105347210196, "refund": 0.008053162589058565, "status": 0.0037932034597093207}, "probs_as_returned": {"cancel": 0.006265845660924066, "change_address": 0.947796734818206, "other": 0.03409105347210196, "refund": 0.008053162589058565, "status": 0.0037932034597093207}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053491192986257374, "usage": {"input_tokens": 217, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c29fbd643d32cd5c267a625ed63860a4da5cfb955ab790e1ae6af8a961c3aa32", "runtime": null} +{"task_id": "original-intent-04-0", "family": "intent", "split": "public", "group": "original-intent-04", "ts": 1790798242.83847, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cancel", "ordinal_ev": null, "probs": {"cancel": 0.9378732275183023, "change_address": 0.004530802608425531, "other": 0.05233548212728289, "refund": 0.0042552831109369605, "status": 0.0010052046350524108}, "probs_as_returned": {"cancel": 0.9378732275183023, "change_address": 0.004530802608425531, "other": 0.05233548212728289, "refund": 0.0042552831109369605, "status": 0.0010052046350524108}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05408834700938314, "usage": {"input_tokens": 222, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "504c0f938e50602cb97c32dfb9ba9c47fee3fa9e5577b93637a8f4f0ed3b1421", "runtime": null} +{"task_id": "original-intent-04-1", "family": "intent", "split": "public", "group": "original-intent-04", "ts": 1790798242.9000568, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cancel", "ordinal_ev": null, "probs": {"cancel": 0.947910801764849, "change_address": 0.004300825146805656, "other": 0.0438207144703226, "refund": 0.0029516958001635546, "status": 0.0010159628178592127}, "probs_as_returned": {"cancel": 0.947910801764849, "change_address": 0.004300825146805656, "other": 0.0438207144703226, "refund": 0.0029516958001635546, "status": 0.0010159628178592127}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05377873597899452, "usage": {"input_tokens": 217, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "3994e201cad970e6481c9f0bccbba05a52c9284736f51687faf7566292e4015e", "runtime": null} +{"task_id": "original-intent-05-0", "family": "intent", "split": "public", "group": "original-intent-05", "ts": 1790798242.9687436, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "other", "ordinal_ev": null, "probs": {"cancel": 0.007151922435870813, "change_address": 0.004066329316103547, "other": 0.697318944283325, "refund": 0.2897195038147706, "status": 0.0017433001499300139}, "probs_as_returned": {"cancel": 0.007151922435870813, "change_address": 0.004066329316103547, "other": 0.697318944283325, "refund": 0.2897195038147706, "status": 0.0017433001499300139}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05928322800900787, "usage": {"input_tokens": 217, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5fe1c571e85681b04a3867ef6b09b4e350bc8af0759804e460d98505700aa8cd", "runtime": null} +{"task_id": "original-intent-05-1", "family": "intent", "split": "public", "group": "original-intent-05", "ts": 1790798243.035629, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "other", "ordinal_ev": null, "probs": {"cancel": 0.008842063949217063, "change_address": 0.00367366817047693, "other": 0.8621092581823092, "refund": 0.1232862922745069, "status": 0.0020887174234899913}, "probs_as_returned": {"cancel": 0.008842063949217063, "change_address": 0.00367366817047693, "other": 0.8621092581823092, "refund": 0.1232862922745069, "status": 0.0020887174234899913}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05627896898658946, "usage": {"input_tokens": 216, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "881258bef887b55b760b76fd760c1951e6f6c73a355860c737bb199ae6d8a604", "runtime": null} +{"task_id": "original-intent-06-0", "family": "intent", "split": "public", "group": "original-intent-06", "ts": 1790798243.101396, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "status", "ordinal_ev": null, "probs": {"cancel": 0.04041415591597284, "change_address": 0.015770051641193803, "other": 0.2065130791599608, "refund": 0.013064506583094595, "status": 0.7242382066997779}, "probs_as_returned": {"cancel": 0.04041415591597284, "change_address": 0.015770051641193803, "other": 0.2065130791599608, "refund": 0.013064506583094595, "status": 0.7242382066997779}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05544981197454035, "usage": {"input_tokens": 214, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "0f016e131ccd4de0b9054b3bf18d7bc7eea0c2c7e4ac495323fe934e594ff58b", "runtime": null} +{"task_id": "original-intent-06-1", "family": "intent", "split": "public", "group": "original-intent-06", "ts": 1790798243.1675327, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "status", "ordinal_ev": null, "probs": {"cancel": 0.010751220386095738, "change_address": 0.0078564127691029, "other": 0.10288184565711354, "refund": 0.010097435369874964, "status": 0.868413085817813}, "probs_as_returned": {"cancel": 0.010751220386095738, "change_address": 0.0078564127691029, "other": 0.10288184565711354, "refund": 0.010097435369874964, "status": 0.868413085817813}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05651093798223883, "usage": {"input_tokens": 219, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4d95cc031f48100c5a8b31b485ee88bc803629df30d725aab6b4c07aae9ef97b", "runtime": null} +{"task_id": "original-ordinal-01-0", "family": "ordinal", "split": "public", "group": "original-ordinal-01", "ts": 1790798243.2318232, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "0", "ordinal_ev": 0.07628057138193826, "probs": {"0": 0.9336912617650633, "1": 0.05906752177300131, "2": 0.004510599776869139, "3": 0.0027306166850662277}, "probs_as_returned": {"0": 0.9336912617650633, "1": 0.05906752177300131, "2": 0.004510599776869139, "3": 0.0027306166850662277}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055644781969022006, "usage": {"input_tokens": 226, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "040dbc6214d5daba68dc3415cad757272e0dbcf376001a177aaf63b4050c8174", "runtime": null} +{"task_id": "original-ordinal-01-1", "family": "ordinal", "split": "public", "group": "original-ordinal-01", "ts": 1790798243.2952602, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "0", "ordinal_ev": 0.043562903333643106, "probs": {"0": 0.9617730521586384, "1": 0.03459376436924552, "2": 0.001930411451950494, "3": 0.0017027720201655324}, "probs_as_returned": {"0": 0.9617730521586384, "1": 0.03459376436924552, "2": 0.001930411451950494, "3": 0.0017027720201655324}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05494906799867749, "usage": {"input_tokens": 228, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "302cdce63a427bae240080c64ec292c67d29901553e2b8ce77a525ca4a54ced3", "runtime": null} +{"task_id": "original-ordinal-02-0", "family": "ordinal", "split": "public", "group": "original-ordinal-02", "ts": 1790798243.3608932, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "1", "ordinal_ev": 0.9606073357096381, "probs": {"0": 0.06552783210496539, "1": 0.9136649245071803, "2": 0.015479318961105435, "3": 0.005327924426748972}, "probs_as_returned": {"0": 0.06552783210496539, "1": 0.9136649245071803, "2": 0.015479318961105435, "3": 0.005327924426748972}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05803194805048406, "usage": {"input_tokens": 230, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "14181a35a2e33a360a7f52eb261930f0a0cc5b92fe684dbd17e619b35988986b", "runtime": null} +{"task_id": "original-ordinal-02-1", "family": "ordinal", "split": "public", "group": "original-ordinal-02", "ts": 1790798243.4236357, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "1", "ordinal_ev": 0.9734045635133284, "probs": {"0": 0.03881697376711625, "1": 0.9519256866551472, "2": 0.006293141875028083, "3": 0.0029641977027083286}, "probs_as_returned": {"0": 0.03881697376711625, "1": 0.9519256866551472, "2": 0.006293141875028083, "3": 0.0029641977027083286}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05480465601431206, "usage": {"input_tokens": 231, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d2316951e5ee527a274a135c62da65338daf08bc474540a6a2e3b5e9b846c428", "runtime": null} +{"task_id": "original-ordinal-03-0", "family": "ordinal", "split": "public", "group": "original-ordinal-03", "ts": 1790798243.4863393, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 1.9918667458343595, "probs": {"0": 0.0060159904313022965, "1": 0.01058101655212649, "2": 0.9689232497674803, "3": 0.014479743249090765}, "probs_as_returned": {"0": 0.0060159904313022965, "1": 0.01058101655212649, "2": 0.9689232497674803, "3": 0.014479743249090765}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054436111997347325, "usage": {"input_tokens": 227, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e7d176e82f77ebe060d9526681251a6e476239eba31821f6af1fb347cc24b84b", "runtime": null} +{"task_id": "original-ordinal-03-1", "family": "ordinal", "split": "public", "group": "original-ordinal-03", "ts": 1790798243.5474544, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 2.00299542852447, "probs": {"0": 0.006773356163561288, "1": 0.007211914883152434, "2": 0.9622606732185414, "3": 0.023754055734744896}, "probs_as_returned": {"0": 0.006773356163561288, "1": 0.007211914883152434, "2": 0.9622606732185414, "3": 0.023754055734744896}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053760517039336264, "usage": {"input_tokens": 230, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "90e2fc59f50cd54333f0e9d2642fa5abd3d4959eecb89fcfe577fc8408f0b22f", "runtime": null} +{"task_id": "original-ordinal-04-0", "family": "ordinal", "split": "public", "group": "original-ordinal-04", "ts": 1790798243.609132, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "3", "ordinal_ev": 2.9704331614645687, "probs": {"0": 0.004185713097107498, "1": 0.0034676031589811955, "2": 0.010074492926146724, "3": 0.9822721908177647}, "probs_as_returned": {"0": 0.004185713097107498, "1": 0.0034676031589811955, "2": 0.010074492926146724, "3": 0.9822721908177647}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05370333697646856, "usage": {"input_tokens": 230, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1ac60c30484bafe119d998375b1bd4252b2e4274eabd087743cbe6e8376b4d7b", "runtime": null} +{"task_id": "original-ordinal-04-1", "family": "ordinal", "split": "public", "group": "original-ordinal-04", "ts": 1790798243.681654, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "3", "ordinal_ev": 2.967596710904972, "probs": {"0": 0.003917633194691461, "1": 0.003455654971049581, "2": 0.013739079568854744, "3": 0.9788876322654043}, "probs_as_returned": {"0": 0.003917633194691461, "1": 0.003455654971049581, "2": 0.013739079568854744, "3": 0.9788876322654043}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06196466099936515, "usage": {"input_tokens": 229, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cdad39f4baa4944e26fcb860940a965eca4ee07581b9b67200967a13e93dda87", "runtime": null} +{"task_id": "original-ordinal-05-0", "family": "ordinal", "split": "public", "group": "original-ordinal-05", "ts": 1790798243.7517595, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "0", "ordinal_ev": 0.2291006823712572, "probs": {"0": 0.8500853530913438, "1": 0.08343242245188087, "2": 0.053778413450949664, "3": 0.012703811005825663}, "probs_as_returned": {"0": 0.8500853530913438, "1": 0.08343242245188087, "2": 0.053778413450949664, "3": 0.012703811005825663}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0590499920072034, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c339308ebfdfbbf51859de820fd16f09e3f6f70471b24652da64b3dc080f0a90", "runtime": null} +{"task_id": "original-ordinal-05-1", "family": "ordinal", "split": "public", "group": "original-ordinal-05", "ts": 1790798243.8207154, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "0", "ordinal_ev": 0.12180446059244274, "probs": {"0": 0.9151321240993054, "1": 0.054372909340145624, "2": 0.024053348429349676, "3": 0.006441618131199253}, "probs_as_returned": {"0": 0.9151321240993054, "1": 0.054372909340145624, "2": 0.024053348429349676, "3": 0.006441618131199253}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05781350104371086, "usage": {"input_tokens": 232, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "de37ffb32194fd56515412fb284110621575526d169189d665edb1422ef45860", "runtime": null} +{"task_id": "original-ordinal-06-0", "family": "ordinal", "split": "public", "group": "original-ordinal-06", "ts": 1790798243.8825629, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 1.9749699592964916, "probs": {"0": 0.006417617571413263, "1": 0.017511402806940014, "2": 0.9707543823753891, "3": 0.005316597246257736}, "probs_as_returned": {"0": 0.006417617571413263, "1": 0.017511402806940014, "2": 0.9707543823753891, "3": 0.005316597246257736}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053586800990160555, "usage": {"input_tokens": 233, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "17ed37c3ff5b482463ead960617c09872a9a6b134431c3d36f0c128908b25cb0", "runtime": null} +{"task_id": "original-ordinal-06-1", "family": "ordinal", "split": "public", "group": "original-ordinal-06", "ts": 1790798243.9445944, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 1.9972653111993102, "probs": {"0": 0.002390359574020004, "1": 0.004476413325753633, "2": 0.9866107834271227, "3": 0.006522443673103714}, "probs_as_returned": {"0": 0.002390359574020004, "1": 0.004476413325753633, "2": 0.9866107834271227, "3": 0.006522443673103714}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05345639999723062, "usage": {"input_tokens": 240, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "86f5d38ebe5ccf4d3f9881b2e1dacf191ff1050bbb756b76926b9c031e16d312", "runtime": null} +{"task_id": "original-extraction-01-0", "family": "extraction", "split": "public", "group": "original-extraction-01", "ts": 1790798244.0075548, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "pickup", "ordinal_ev": null, "probs": {"courier": 0.038581401175833197, "pickup": 0.9461486456144061, "post": 0.003556342540584308, "unknown": 0.011713610669176297}, "probs_as_returned": {"courier": 0.038581401175833197, "pickup": 0.9461486456144061, "post": 0.003556342540584308, "unknown": 0.011713610669176297}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055001398955937475, "usage": {"input_tokens": 204, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "df5a57c70fd1193e0972e303c2ac962c1e439e53d44f4ac772a0f83733d20c28", "runtime": null} +{"task_id": "original-extraction-01-1", "family": "extraction", "split": "public", "group": "original-extraction-01", "ts": 1790798244.0718908, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "pickup", "ordinal_ev": null, "probs": {"courier": 0.02334986205840487, "pickup": 0.9458870455791862, "post": 0.004291643013286111, "unknown": 0.026471449349122916}, "probs_as_returned": {"courier": 0.02334986205840487, "pickup": 0.9458870455791862, "post": 0.004291643013286111, "unknown": 0.026471449349122916}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05607908801175654, "usage": {"input_tokens": 206, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f3c5807fee410c7f6afb0f7fcec58a3513cc16e35ee43472e38e81fd5396db5b", "runtime": null} +{"task_id": "original-extraction-02-0", "family": "extraction", "split": "public", "group": "original-extraction-02", "ts": 1790798244.1343346, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "unknown", "ordinal_ev": null, "probs": {"courier": 0.01060657179917826, "pickup": 0.006836726175654022, "post": 0.011293323016761128, "unknown": 0.9712633790084065}, "probs_as_returned": {"courier": 0.01060657179917826, "pickup": 0.006836726175654022, "post": 0.011293323016761128, "unknown": 0.9712633790084065}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05446557799587026, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "89899f21e85f16a43995bf75af9bf812008d994d4b57e8d0b5d27be575a57c23", "runtime": null} +{"task_id": "original-extraction-02-1", "family": "extraction", "split": "public", "group": "original-extraction-02", "ts": 1790798244.195442, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "unknown", "ordinal_ev": null, "probs": {"courier": 0.006844176014044733, "pickup": 0.012037641429207909, "post": 0.008796460047921562, "unknown": 0.9723217225088259}, "probs_as_returned": {"courier": 0.006844176014044733, "pickup": 0.012037641429207909, "post": 0.008796460047921562, "unknown": 0.9723217225088259}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05353393900441006, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "be7fb48e04e66ad48861615f767b962c14b4fba513894efa65153cb766728df7", "runtime": null} +{"task_id": "original-extraction-03-0", "family": "extraction", "split": "public", "group": "original-extraction-03", "ts": 1790798244.2592912, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "courier", "ordinal_ev": null, "probs": {"courier": 0.9326330187285887, "pickup": 0.03354563366553508, "post": 0.00423150739028277, "unknown": 0.02958984021559345}, "probs_as_returned": {"courier": 0.9326330187285887, "pickup": 0.03354563366553508, "post": 0.00423150739028277, "unknown": 0.02958984021559345}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05463600001530722, "usage": {"input_tokens": 211, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "494f3ae8e7d4ca74f0ed3327a667eca1854b8d40364130ecad8c493656013437", "runtime": null} +{"task_id": "original-extraction-03-1", "family": "extraction", "split": "public", "group": "original-extraction-03", "ts": 1790798244.327005, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "courier", "ordinal_ev": null, "probs": {"courier": 0.9787207813254738, "pickup": 0.012116863344787614, "post": 0.0034550659828031225, "unknown": 0.005707289346935534}, "probs_as_returned": {"courier": 0.9787207813254738, "pickup": 0.012116863344787614, "post": 0.0034550659828031225, "unknown": 0.005707289346935534}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056155684986151755, "usage": {"input_tokens": 210, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1f6286e03c5e0d171c5ff8af2dcafe6faea1b5880aab8db4df6e9ed2dd6ed70d", "runtime": null} +{"task_id": "original-extraction-04-0", "family": "extraction", "split": "public", "group": "original-extraction-04", "ts": 1790798244.393063, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "post", "ordinal_ev": null, "probs": {"courier": 0.012648863682625869, "pickup": 0.010478797335157587, "post": 0.9595628201991785, "unknown": 0.017309518783038134}, "probs_as_returned": {"courier": 0.012648863682625869, "pickup": 0.010478797335157587, "post": 0.9595628201991785, "unknown": 0.017309518783038134}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05494381097378209, "usage": {"input_tokens": 208, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5f5058297b3c81d505816ea30dda40c3cddd5b58baf790ceb05cc4d35b15d170", "runtime": null} +{"task_id": "original-extraction-04-1", "family": "extraction", "split": "public", "group": "original-extraction-04", "ts": 1790798244.456323, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "post", "ordinal_ev": null, "probs": {"courier": 0.03782691951412233, "pickup": 0.013019885086963941, "post": 0.9276461528936708, "unknown": 0.021507042505243032}, "probs_as_returned": {"courier": 0.03782691951412233, "pickup": 0.013019885086963941, "post": 0.9276461528936708, "unknown": 0.021507042505243032}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05417081498308107, "usage": {"input_tokens": 204, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "223e28a44fe8c9688896307d3ea4b83907cac7e439c971fde6fb7bcbd4af339e", "runtime": null} +{"task_id": "original-extraction-05-0", "family": "extraction", "split": "public", "group": "original-extraction-05", "ts": 1790798244.519088, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "unknown", "ordinal_ev": null, "probs": {"courier": 0.013695135711406525, "pickup": 0.007313064273085332, "post": 0.003235134664139037, "unknown": 0.9757566653513692}, "probs_as_returned": {"courier": 0.013695135711406525, "pickup": 0.007313064273085332, "post": 0.003235134664139037, "unknown": 0.9757566653513692}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05345906299771741, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4d0599fba479521dba22463c3dcf44483b8d74512b269415e38b284606c286bb", "runtime": null} +{"task_id": "original-extraction-05-1", "family": "extraction", "split": "public", "group": "original-extraction-05", "ts": 1790798244.5812109, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "unknown", "ordinal_ev": null, "probs": {"courier": 0.01138842444688154, "pickup": 0.005711497827869614, "post": 0.003457613540319971, "unknown": 0.9794424641849289}, "probs_as_returned": {"courier": 0.01138842444688154, "pickup": 0.005711497827869614, "post": 0.003457613540319971, "unknown": 0.9794424641849289}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05353969300631434, "usage": {"input_tokens": 204, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "efb5351094c3274c0506524a9a198c1548806d8c95243b351f8d84a8deef4896", "runtime": null} +{"task_id": "original-extraction-06-0", "family": "extraction", "split": "public", "group": "original-extraction-06", "ts": 1790798244.6439168, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "courier", "ordinal_ev": null, "probs": {"courier": 0.9860425408815783, "pickup": 0.003946267989335649, "post": 0.006940756955696869, "unknown": 0.003070434173389162}, "probs_as_returned": {"courier": 0.9860425408815783, "pickup": 0.003946267989335649, "post": 0.006940756955696869, "unknown": 0.003070434173389162}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054092272999696434, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "46fd1ab251d64326fe1c8612b8ab5f7a8f62201042c8db21b13c66117db18962", "runtime": null} +{"task_id": "original-extraction-06-1", "family": "extraction", "split": "public", "group": "original-extraction-06", "ts": 1790798244.7050462, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "courier", "ordinal_ev": null, "probs": {"courier": 0.9707499602252476, "pickup": 0.012018182452518955, "post": 0.00995631722051821, "unknown": 0.007275540101715229}, "probs_as_returned": {"courier": 0.9707499602252476, "pickup": 0.012018182452518955, "post": 0.00995631722051821, "unknown": 0.007275540101715229}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05302195000695065, "usage": {"input_tokens": 207, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "27155e94826126917c5f063d4029a7c2e696bccaac3cfb433ae703ec60205ff9", "runtime": null} +{"task_id": "original-adequacy-01-0", "family": "adequacy", "split": "public", "group": "original-adequacy-01", "ts": 1790798244.768455, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "probs_as_returned": {"yes": 0.91062577829021, "no": 0.08937422170979004}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05454882298363373, "usage": {"input_tokens": 202, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d4ca3b04fbe82b221cfa74ac406ca4d6d89b6e6047b0cc67d500198b8433f6a1", "runtime": null} +{"task_id": "original-adequacy-01-1", "family": "adequacy", "split": "public", "group": "original-adequacy-01", "ts": 1790798244.8296702, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "probs_as_returned": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053918385005090386, "usage": {"input_tokens": 198, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "72454b7f44db9f32fd43c041e2f414b5dee8c8b829125d3a77a3ec7c137cd6d7", "runtime": null} +{"task_id": "original-adequacy-02-0", "family": "adequacy", "split": "public", "group": "original-adequacy-02", "ts": 1790798244.8915865, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.00791685353903075, "no": 0.9920831464609693}, "probs_as_returned": {"yes": 0.00791685353903075, "no": 0.9920831464609693}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05321957101114094, "usage": {"input_tokens": 199, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "51de29ffce8de120b78f05ddfd18a6bf3966011113ec18ec603245d23d39e807", "runtime": null} +{"task_id": "original-adequacy-02-1", "family": "adequacy", "split": "public", "group": "original-adequacy-02", "ts": 1790798244.9530516, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.006989802244620407, "no": 0.9930101977553796}, "probs_as_returned": {"yes": 0.006989802244620407, "no": 0.9930101977553796}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053112035035155714, "usage": {"input_tokens": 199, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "164a7f12248827bd9032e7ef8a64b0eda172d823508f0505c6547e19be9fe5a8", "runtime": null} +{"task_id": "original-adequacy-03-0", "family": "adequacy", "split": "public", "group": "original-adequacy-03", "ts": 1790798245.0143547, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.08937422170979005, "no": 0.91062577829021}, "probs_as_returned": {"yes": 0.08937422170979005, "no": 0.91062577829021}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053930120018776506, "usage": {"input_tokens": 201, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "25866924e254600b9cbf43b825c4704fbb956b9401721d569393ed31212ce0ca", "runtime": null} +{"task_id": "original-adequacy-03-1", "family": "adequacy", "split": "public", "group": "original-adequacy-03", "ts": 1790798245.075392, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.06310763191560703, "no": 0.936892368084393}, "probs_as_returned": {"yes": 0.06310763191560703, "no": 0.936892368084393}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053685966006014496, "usage": {"input_tokens": 205, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1cabed8e1d9e9183b86ffd77fbe5fe1c3579fe43a0cbf61eee1e646109cb49b0", "runtime": null} +{"task_id": "original-adequacy-04-0", "family": "adequacy", "split": "public", "group": "original-adequacy-04", "ts": 1790798245.1391277, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9471470189565372, "no": 0.05285298104346281}, "probs_as_returned": {"yes": 0.9471470189565372, "no": 0.05285298104346281}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055174158012960106, "usage": {"input_tokens": 205, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6c7740c109068456a2d2c8136db869f96f0d9fa2cf0db0a412d552ba7bdd15f1", "runtime": null} +{"task_id": "original-adequacy-04-1", "family": "adequacy", "split": "public", "group": "original-adequacy-04", "ts": 1790798245.2024841, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8940776460411956, "no": 0.10592235395880445}, "probs_as_returned": {"yes": 0.8940776460411956, "no": 0.10592235395880445}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05561440298333764, "usage": {"input_tokens": 202, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e62b1c8037bb0d03610997186bec485e7d82b1fdfe4285a6f0292cc4d8931aec", "runtime": null} +{"task_id": "original-adequacy-05-0", "family": "adequacy", "split": "public", "group": "original-adequacy-05", "ts": 1790798245.2655745, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.11840617139815589, "no": 0.8815938286018441}, "probs_as_returned": {"yes": 0.11840617139815589, "no": 0.8815938286018441}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05494537204504013, "usage": {"input_tokens": 195, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5b3debeea141615bd2fbd4626ab90e4fdedd815b17c3043a863ebf9185feec6d", "runtime": null} +{"task_id": "original-adequacy-05-1", "family": "adequacy", "split": "public", "group": "original-adequacy-05", "ts": 1790798245.3272114, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.03267757061976492, "no": 0.967322429380235}, "probs_as_returned": {"yes": 0.03267757061976492, "no": 0.967322429380235}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05378465395187959, "usage": {"input_tokens": 195, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5ee8087a3d48741faa6dc1c8838dd942d9a30279f5260240744dc048d742ac30", "runtime": null} +{"task_id": "original-adequacy-06-0", "family": "adequacy", "split": "public", "group": "original-adequacy-06", "ts": 1790798245.3881712, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9583890938912367, "no": 0.04161090610876328}, "probs_as_returned": {"yes": 0.9583890938912367, "no": 0.04161090610876328}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05354283703491092, "usage": {"input_tokens": 211, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "227b13c1515ae12df65b750c12c68e45b81f9953b67e7a011e482d1ef05fcb10", "runtime": null} +{"task_id": "original-adequacy-06-1", "family": "adequacy", "split": "public", "group": "original-adequacy-06", "ts": 1790798245.4503725, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.5930110454411601, "no": 0.4069889545588399}, "probs_as_returned": {"yes": 0.5930110454411601, "no": 0.4069889545588399}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05335792002733797, "usage": {"input_tokens": 212, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "96df9bf17e5fdc153c8de9380ef89b94e870509646cb472174bb8632db83907f", "runtime": null} +{"task_id": "original-routing-01-0", "family": "routing", "split": "public", "group": "original-routing-01", "ts": 1790798245.512647, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "math", "ordinal_ev": null, "probs": {"coding": 0.030403476101725994, "coding_agent": 0.005588078139470822, "document": 0.0029839776552908095, "general": 0.05693642518396949, "math": 0.9000045761395922, "tools": 0.004083466779950801}, "probs_as_returned": {"coding": 0.030403476101725994, "coding_agent": 0.005588078139470822, "document": 0.0029839776552908095, "general": 0.05693642518396949, "math": 0.9000045761395922, "tools": 0.004083466779950801}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054153611010406166, "usage": {"input_tokens": 248, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c0be47152a4764ebd83d54cdff87c81cd865a1445ae1c7163a1d7827b8a42b85", "runtime": null} +{"task_id": "original-routing-01-1", "family": "routing", "split": "public", "group": "original-routing-01", "ts": 1790798245.5754118, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "math", "ordinal_ev": null, "probs": {"coding": 0.027064128848065867, "coding_agent": 0.006004452348212528, "document": 0.004120910951392922, "general": 0.05068284732390288, "math": 0.9082573436250052, "tools": 0.003870316903420689}, "probs_as_returned": {"coding": 0.027064128848065867, "coding_agent": 0.006004452348212528, "document": 0.004120910951392922, "general": 0.05068284732390288, "math": 0.9082573436250052, "tools": 0.003870316903420689}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05374445696361363, "usage": {"input_tokens": 244, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "63adf138ab6adaa3cc24cdd2af7f38820566c0b3372eb1d75cdf6f28bf34bb7f", "runtime": null} +{"task_id": "original-routing-02-0", "family": "routing", "split": "public", "group": "original-routing-02", "ts": 1790798245.639648, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coding", "ordinal_ev": null, "probs": {"coding": 0.9415619813564295, "coding_agent": 0.018084528998433786, "document": 0.01595195139756404, "general": 0.02050220621528298, "math": 0.0024289187126925386, "tools": 0.0014704133195969841}, "probs_as_returned": {"coding": 0.9415619813564295, "coding_agent": 0.018084528998433786, "document": 0.01595195139756404, "general": 0.02050220621528298, "math": 0.0024289187126925386, "tools": 0.0014704133195969841}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05630508600734174, "usage": {"input_tokens": 249, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a1bb3d62799f815bc75ecd503c58245443ad70f153fb38768d85e9dbc3397c8f", "runtime": null} +{"task_id": "original-routing-02-1", "family": "routing", "split": "public", "group": "original-routing-02", "ts": 1790798245.7024674, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coding", "ordinal_ev": null, "probs": {"coding": 0.973635359123508, "coding_agent": 0.008272706167638342, "document": 0.004703566958129719, "general": 0.00998591082769865, "math": 0.0023589227246364557, "tools": 0.0010435341983889071}, "probs_as_returned": {"coding": 0.973635359123508, "coding_agent": 0.008272706167638342, "document": 0.004703566958129719, "general": 0.00998591082769865, "math": 0.0023589227246364557, "tools": 0.0010435341983889071}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05463950801640749, "usage": {"input_tokens": 243, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6e6a7ca1d9182d0a4ec495a6e92709f367f87ae36f9492507504824ba73f9af0", "runtime": null} +{"task_id": "original-routing-03-0", "family": "routing", "split": "public", "group": "original-routing-03", "ts": 1790798245.7655218, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coding_agent", "ordinal_ev": null, "probs": {"coding": 0.013544661981601466, "coding_agent": 0.9650356763230314, "document": 0.003406754965701558, "general": 0.00873054421930428, "math": 0.0024894731036984113, "tools": 0.006792889406662867}, "probs_as_returned": {"coding": 0.013544661981601466, "coding_agent": 0.9650356763230314, "document": 0.003406754965701558, "general": 0.00873054421930428, "math": 0.0024894731036984113, "tools": 0.006792889406662867}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05505556898424402, "usage": {"input_tokens": 248, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b0e90c4601c84bf6e1737322347635b536373f8e5912938bf8b11645525bd9ad", "runtime": null} +{"task_id": "original-routing-03-1", "family": "routing", "split": "public", "group": "original-routing-03", "ts": 1790798245.8274686, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coding_agent", "ordinal_ev": null, "probs": {"coding": 0.015370445312191146, "coding_agent": 0.9659803493932506, "document": 0.0038659763929818373, "general": 0.009304926219392514, "math": 0.0028250473602176632, "tools": 0.002653255321966199}, "probs_as_returned": {"coding": 0.015370445312191146, "coding_agent": 0.9659803493932506, "document": 0.0038659763929818373, "general": 0.009304926219392514, "math": 0.0028250473602176632, "tools": 0.002653255321966199}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05419012001948431, "usage": {"input_tokens": 250, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "24bcc1811928d6c6b774fde85af7551036255c82cfc1090b4f950b7a0eec207c", "runtime": null} +{"task_id": "original-routing-04-0", "family": "routing", "split": "public", "group": "original-routing-04", "ts": 1790798245.8899271, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "document", "ordinal_ev": null, "probs": {"coding": 0.014210229746939956, "coding_agent": 0.022045907219979437, "document": 0.7877520218832728, "general": 0.14478674264730218, "math": 0.004593678879467563, "tools": 0.02661141962303802}, "probs_as_returned": {"coding": 0.014210229746939956, "coding_agent": 0.022045907219979437, "document": 0.7877520218832728, "general": 0.14478674264730218, "math": 0.004593678879467563, "tools": 0.02661141962303802}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054508129018358886, "usage": {"input_tokens": 244, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2e803771412dee34229bc2f24f8d393880e40572b4dd475c72c01f62e1320dde", "runtime": null} +{"task_id": "original-routing-04-1", "family": "routing", "split": "public", "group": "original-routing-04", "ts": 1790798245.9533901, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "document", "ordinal_ev": null, "probs": {"coding": 0.024413533876144627, "coding_agent": 0.027677322136038972, "document": 0.6787431213908676, "general": 0.24874727547479406, "math": 0.006538077731369333, "tools": 0.013880669390785366}, "probs_as_returned": {"coding": 0.024413533876144627, "coding_agent": 0.027677322136038972, "document": 0.6787431213908676, "general": 0.24874727547479406, "math": 0.006538077731369333, "tools": 0.013880669390785366}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05384296004194766, "usage": {"input_tokens": 243, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7e958ddafb701d448386f5fc6ad5a851d9727a9f7c1781fabfc11ad970664364", "runtime": null} +{"task_id": "original-routing-05-0", "family": "routing", "split": "public", "group": "original-routing-05", "ts": 1790798246.0145092, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "tools", "ordinal_ev": null, "probs": {"coding": 0.013819082412644958, "coding_agent": 0.011448251071317058, "document": 0.021439076042707273, "general": 0.08005466995874373, "math": 0.004756477464671993, "tools": 0.868482443049915}, "probs_as_returned": {"coding": 0.013819082412644958, "coding_agent": 0.011448251071317058, "document": 0.021439076042707273, "general": 0.08005466995874373, "math": 0.004756477464671993, "tools": 0.868482443049915}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05410700000356883, "usage": {"input_tokens": 245, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4afdc9d0afd2232c4d60d570e140959ca73d9fa4de5d318aa5a285acd049c740", "runtime": null} +{"task_id": "original-routing-05-1", "family": "routing", "split": "public", "group": "original-routing-05", "ts": 1790798246.077505, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "tools", "ordinal_ev": null, "probs": {"coding": 0.01907649307568939, "coding_agent": 0.014842661214610822, "document": 0.013940073466224478, "general": 0.26598655114071845, "math": 0.004506346432653027, "tools": 0.6816478746701038}, "probs_as_returned": {"coding": 0.01907649307568939, "coding_agent": 0.014842661214610822, "document": 0.013940073466224478, "general": 0.26598655114071845, "math": 0.004506346432653027, "tools": 0.6816478746701038}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055993108020629734, "usage": {"input_tokens": 245, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "072243d5fc6bd8b33cc144120663eb7a8b76db66471c28633dd3fef05f648f69", "runtime": null} +{"task_id": "original-routing-06-0", "family": "routing", "split": "public", "group": "original-routing-06", "ts": 1790798246.1400602, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "general", "ordinal_ev": null, "probs": {"coding": 0.022131200140044424, "coding_agent": 0.009194990510311016, "document": 0.06038820440582165, "general": 0.8965198972789722, "math": 0.0071542561880119735, "tools": 0.0046114514768386536}, "probs_as_returned": {"coding": 0.022131200140044424, "coding_agent": 0.009194990510311016, "document": 0.06038820440582165, "general": 0.8965198972789722, "math": 0.0071542561880119735, "tools": 0.0046114514768386536}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054676154977642, "usage": {"input_tokens": 243, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "78fbb7ba0fa7936046995d7c1390bec093a77af2499537aeb980b9da91e2b950", "runtime": null} +{"task_id": "original-routing-06-1", "family": "routing", "split": "public", "group": "original-routing-06", "ts": 1790798246.2033849, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "general", "ordinal_ev": null, "probs": {"coding": 0.02223904433233792, "coding_agent": 0.009239796877608073, "document": 0.05352662420536432, "general": 0.9008885827216597, "math": 0.008150214081207844, "tools": 0.005955737781822105}, "probs_as_returned": {"coding": 0.02223904433233792, "coding_agent": 0.009239796877608073, "document": 0.05352662420536432, "general": 0.9008885827216597, "math": 0.008150214081207844, "tools": 0.005955737781822105}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054704332957044244, "usage": {"input_tokens": 243, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "3ce2d063ee1a81fdbfd5293f80c8f2e858c1e3f6c03b4fd5a74a172dd9a36b76", "runtime": null} +{"task_id": "hard-opus-a-long_policy-01", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-01", "ts": 1790798252.967622, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "pay_subject_to_15000_sublimit", "ordinal_ev": null, "probs": {"deny_repeated_seepage": 0.01738839593866782, "deny_vacancy_exclusion": 0.02098937905094514, "pay_full_estimate_less_deductible": 0.006785144709800851, "pay_subject_to_10000_sublimit": 0.1562765432073203, "pay_subject_to_15000_sublimit": 0.7985605370932659}, "probs_as_returned": {"deny_repeated_seepage": 0.01738839593866782, "deny_vacancy_exclusion": 0.02098937905094514, "pay_full_estimate_less_deductible": 0.006785144709800851, "pay_subject_to_10000_sublimit": 0.1562765432073203, "pay_subject_to_15000_sublimit": 0.7985605370932659}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 6.752757905982435, "usage": {"input_tokens": 4074, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8db485237acf73caa53ebc83e4e8ab1635d1d111d44b0ebc024afe13aca89bdb", "runtime": null} +{"task_id": "hard-opus-a-long_policy-04", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-04", "ts": 1790798253.1322808, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "vp_and_finance_director", "ordinal_ev": null, "probs": {"budget_holder": 0.02271616887362895, "cfo": 0.08482339827852999, "department_head": 0.08482339827852999, "executive_committee": 0.045294839737184185, "vp_and_finance_director": 0.7623421948321268}, "probs_as_returned": {"budget_holder": 0.02271616887362895, "cfo": 0.08482339827852999, "department_head": 0.08482339827852999, "executive_committee": 0.045294839737184185, "vp_and_finance_director": 0.7623421948321268}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.15093205898301676, "usage": {"input_tokens": 2764, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "79791cfaf06ef07a92f4407e47c32c5bbbace0b2ade4c13e4e22f65778f1952c", "runtime": null} +{"task_id": "hard-opus-a-long_policy-08", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-08", "ts": 1790798253.2775648, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "parts_covered_labour_charged", "ordinal_ev": null, "probs": {"full_repair_no_charge": 0.06519889343118179, "not_covered": 0.016398833394742487, "parts_covered_labour_charged": 0.9090784780802361, "pro_rata_replacement_credit": 0.009323795093839524}, "probs_as_returned": {"full_repair_no_charge": 0.06519889343118179, "not_covered": 0.016398833394742487, "parts_covered_labour_charged": 0.9090784780802361, "pro_rata_replacement_credit": 0.009323795093839524}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1320233890437521, "usage": {"input_tokens": 2524, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6fa72df6fd4474531b6f3e9c8551a29b3605f66bdf350d9976a9abd3066695cd", "runtime": null} +{"task_id": "hard-opus-a-long_policy-09", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-09", "ts": 1790798253.432255, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "license_required", "ordinal_ev": null, "probs": {"license_exception_lvs": 0.114786494715961, "license_required": 0.8026723665682973, "no_license_required": 0.047691072005070445, "shipment_prohibited": 0.034850066710671174}, "probs_as_returned": {"license_exception_lvs": 0.114786494715961, "license_required": 0.8026723665682973, "no_license_required": 0.047691072005070445, "shipment_prohibited": 0.034850066710671174}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1407247250317596, "usage": {"input_tokens": 2662, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6eea029b652d787c333a45eb0e87e1e1dc86952472de41cb8f54cf7b8b9fe98a", "runtime": null} +{"task_id": "hard-opus-a-long_policy-11", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-11", "ts": 1790798253.576769, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.5930110454411601, "no": 0.4069889545588399}, "probs_as_returned": {"yes": 0.5930110454411601, "no": 0.4069889545588399}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13036711799213663, "usage": {"input_tokens": 2470, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a2633349cf1e7f1bf7af7d765e0549f51d7d2785130d920e991f6bca6321171b", "runtime": null} +{"task_id": "hard-opus-a-long_policy-13", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-13", "ts": 1790798253.7222435, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7064759712765732, "no": 0.29352402872342676}, "probs_as_returned": {"yes": 0.7064759712765732, "no": 0.29352402872342676}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1318663579877466, "usage": {"input_tokens": 2559, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "af96f2ade9be8b554ecfb19da446244129ba0b1b6e4d994ada41c33ad6fbdeab", "runtime": null} +{"task_id": "hard-opus-a-long_policy-17", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-17", "ts": 1790798253.8626094, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "database_oncall", "ordinal_ev": null, "probs": {"database_oncall": 0.8353888582269757, "no_page_ticket_only": 0.07232152988407799, "platform_oncall": 0.03861896981172954, "security_incident_response": 0.04963493453981136, "vendor_support": 0.004035707537405349}, "probs_as_returned": {"database_oncall": 0.8353888582269757, "no_page_ticket_only": 0.07232152988407799, "platform_oncall": 0.03861896981172954, "security_incident_response": 0.04963493453981136, "vendor_support": 0.004035707537405349}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.12761241203406826, "usage": {"input_tokens": 2494, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "fe6d879f6fd32cd9855c24b5c8f7f3f15560a7cfccb9dc8767ee573c6d962944", "runtime": null} +{"task_id": "hard-opus-a-long_policy-19", "family": "long_policy", "split": "public", "group": "hard-opus-a-long_policy-19", "ts": 1790798254.0009184, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.37709365395745764, "no": 0.6229063460425424}, "probs_as_returned": {"yes": 0.37709365395745764, "no": 0.6229063460425424}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.12470266700256616, "usage": {"input_tokens": 2465, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "3287ad68ecffaa13b001d0ea7c37556f63b330dbf7b9ba456d6701a494036b68", "runtime": null} +{"task_id": "hard-opus-a-probability-03", "family": "probability", "split": "public", "group": "hard-opus-a-probability-03", "ts": 1790798254.0970733, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.5777854893190272, "no": 0.4222145106809728}, "probs_as_returned": {"yes": 0.5777854893190272, "no": 0.4222145106809728}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.08497649902710691, "usage": {"input_tokens": 544, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e5ca14481fa7dc9274d9a19c5904539e89654350b5cae726dec491a66558ef71", "runtime": null} +{"task_id": "hard-opus-a-probability-04", "family": "probability", "split": "public", "group": "hard-opus-a-probability-04", "ts": 1790798254.1866674, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "late", "ordinal_ev": null, "probs": {"early": 0.13202257175482904, "late": 0.7183050733055719, "on_time": 0.149672354939599}, "probs_as_returned": {"early": 0.13202257175482904, "late": 0.7183050733055719, "on_time": 0.149672354939599}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07684924104250968, "usage": {"input_tokens": 1215, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "972ea4d8b042851929aed7b4b6c8c9f7afb1fc9acddb31daad738e8b7be87d2b", "runtime": null} +{"task_id": "hard-opus-a-probability-07", "family": "probability", "split": "public", "group": "hard-opus-a-probability-07", "ts": 1790798254.2789812, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "escalated", "ordinal_ev": null, "probs": {"escalated": 0.6010911219225122, "reopened": 0.09745097270141673, "resolved_first_contact": 0.30145790537607103}, "probs_as_returned": {"escalated": 0.6010911219225122, "reopened": 0.09745097270141673, "resolved_first_contact": 0.30145790537607103}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.08262726798420772, "usage": {"input_tokens": 1329, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "72d05e5338b36dff633177b9d2869582184334a52250cb14894da7d7156eb889", "runtime": null} +{"task_id": "hard-opus-a-probability-08", "family": "probability", "split": "public", "group": "hard-opus-a-probability-08", "ts": 1790798254.3490667, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.6229063460425425, "no": 0.37709365395745753}, "probs_as_returned": {"yes": 0.6229063460425425, "no": 0.37709365395745753}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05850728799123317, "usage": {"input_tokens": 504, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "72b609e5c8484d1977aed69d38cd23f4d131edb68eefacc4dd4cdc09c8ec3e94", "runtime": null} +{"task_id": "hard-opus-a-temporal_numeric-03", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-03", "ts": 1790798254.42429, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7318060856600669, "no": 0.2681939143399331}, "probs_as_returned": {"yes": 0.7318060856600669, "no": 0.2681939143399331}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06279017397901043, "usage": {"input_tokens": 600, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "534838efdd3a79d1c71cc080ef5473cd6776a0bd928b218ed98801f8f3416251", "runtime": null} +{"task_id": "hard-opus-a-temporal_numeric-06", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-06", "ts": 1790798254.4975128, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.12511350509772579, "no": 0.8748864949022742}, "probs_as_returned": {"yes": 0.12511350509772579, "no": 0.8748864949022742}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06199707998894155, "usage": {"input_tokens": 635, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9c961568839ca938ed5c95ac47e110e4d529a005c383bc0c5e79b1c35ada4c4c", "runtime": null} +{"task_id": "hard-opus-a-temporal_numeric-07", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-07", "ts": 1790798254.594507, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "sep_25", "ordinal_ev": null, "probs": {"sep_24": 0.1443341310190758, "sep_25": 0.3262691984686731, "sep_26": 0.1855050950995479, "sep_27": 0.2384199630201128, "sep_28": 0.10547161239259041}, "probs_as_returned": {"sep_24": 0.1443341310190758, "sep_25": 0.3262691984686731, "sep_26": 0.1855050950995479, "sep_27": 0.2384199630201128, "sep_28": 0.10547161239259041}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0869741200003773, "usage": {"input_tokens": 1418, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "fb9942df7b4a36d389bfa877d1aba9e5921356d9c5d216e7be7b914cc51e2a4e", "runtime": null} +{"task_id": "hard-opus-a-temporal_numeric-09", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-09", "ts": 1790798254.6694608, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.42221451068097277, "no": 0.5777854893190273}, "probs_as_returned": {"yes": 0.42221451068097277, "no": 0.5777854893190273}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06412995798746124, "usage": {"input_tokens": 635, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a1a6d3666c7e4ddb145cbb037d109729bb9f87bfed86777bd2a3031f83c381c1", "runtime": null} +{"task_id": "hard-opus-a-temporal_numeric-12", "family": "temporal_numeric", "split": "public", "group": "hard-opus-a-temporal_numeric-12", "ts": 1790798254.7411149, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "3", "ordinal_ev": 2.102096986624212, "probs": {"0": 0.11983544620580835, "1": 0.10570411896691179, "2": 0.3269884368245393, "3": 0.4474719980027406}, "probs_as_returned": {"0": 0.11983544620580835, "1": 0.10570411896691179, "2": 0.3269884368245393, "3": 0.4474719980027406}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06068427104037255, "usage": {"input_tokens": 708, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5f7f50b49d1cbbad60a57ee1efee94260903a6df0c6dfb1cf0b51cac2385d166", "runtime": null} +{"task_id": "hard-opus-b-ambiguous-02", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-02", "ts": 1790798254.814211, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "real_incident", "ordinal_ev": null, "probs": {"cannot_determine": 0.02744828681074916, "false_positive": 0.05140225590652218, "real_incident": 0.9211494572827287}, "probs_as_returned": {"cannot_determine": 0.02744828681074916, "false_positive": 0.05140225590652218, "real_incident": 0.9211494572827287}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.062467249983455986, "usage": {"input_tokens": 654, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "57944d3d89a26b87c774fcacdd47ee3b496a8726dcf2f75279903a49cdec29f7", "runtime": null} +{"task_id": "hard-opus-b-ambiguous-03", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-03", "ts": 1790798254.8863642, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "within_limitation", "ordinal_ev": null, "probs": {"insufficient_information": 0.04935003802520305, "time_barred": 0.30439788588738664, "within_limitation": 0.6462520760874103}, "probs_as_returned": {"insufficient_information": 0.04935003802520305, "time_barred": 0.30439788588738664, "within_limitation": 0.6462520760874103}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.061945562018081546, "usage": {"input_tokens": 606, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "bc48e5ef4ab1646dfe1524a9fa04f595e9c4aabccb853e265f9ebed6ac05dab9", "runtime": null} +{"task_id": "hard-opus-b-ambiguous-07", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-07", "ts": 1790798254.960291, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "within_policy", "ordinal_ev": null, "probs": {"insufficient_information": 0.04206359082164066, "over_limit": 0.33346268046304034, "within_policy": 0.624473728715319}, "probs_as_returned": {"insufficient_information": 0.04206359082164066, "over_limit": 0.33346268046304034, "within_policy": 0.624473728715319}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06260982900857925, "usage": {"input_tokens": 608, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7f489ef6abc86885084e8834ea1318f53fe4e0b2d66289651ce3117242eff912", "runtime": null} +{"task_id": "hard-opus-b-ambiguous-09", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-09", "ts": 1790798255.032978, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "legitimate", "ordinal_ev": null, "probs": {"compromised": 0.052277255306895254, "inconclusive": 0.010892947754565218, "legitimate": 0.9368297969385395}, "probs_as_returned": {"compromised": 0.052277255306895254, "inconclusive": 0.010892947754565218, "legitimate": 0.9368297969385395}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06171737698605284, "usage": {"input_tokens": 747, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9abad730bf57b2dbd1677477efad0ed279293bdbb0e682f130f538b81d444b8a", "runtime": null} +{"task_id": "hard-opus-b-ambiguous-10", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-10", "ts": 1790798255.1052132, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "send_to_alex_moreno", "ordinal_ev": null, "probs": {"ask_user_which_alex": 0.21763025953150913, "send_to_alex_moreno": 0.6732242882994754, "send_to_alexandra_lind": 0.10914545216901542}, "probs_as_returned": {"ask_user_which_alex": 0.21763025953150913, "send_to_alex_moreno": 0.6732242882994754, "send_to_alexandra_lind": 0.10914545216901542}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.062253514013718814, "usage": {"input_tokens": 666, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9312010d3689e4eb432edb7c4c5ae6c0e6f631cd5cfc1170829a74b02dc7f84e", "runtime": null} +{"task_id": "hard-opus-b-ambiguous-11", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-11", "ts": 1790798255.1778495, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cannot_determine", "ordinal_ev": null, "probs": {"cannot_determine": 0.9499639519924629, "grade_correct": 0.02345050282102886, "grade_should_be_higher": 0.026585545186508176}, "probs_as_returned": {"cannot_determine": 0.9499639519924629, "grade_correct": 0.02345050282102886, "grade_should_be_higher": 0.026585545186508176}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06240525998873636, "usage": {"input_tokens": 574, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ba2a2a83eb6cc8dfe040c0f624a45b3032f62cd4852073b231e23fb596622d5e", "runtime": null} +{"task_id": "hard-opus-b-ambiguous-13", "family": "ambiguous", "split": "public", "group": "hard-opus-b-ambiguous-13", "ts": 1790798255.2527628, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "cannot_determine", "ordinal_ev": null, "probs": {"cannot_determine": 0.9775256664330146, "charge_data_team": 0.01371996433710697, "charge_platform_team": 0.0026849668364085587, "split_50_50": 0.006069402393469905}, "probs_as_returned": {"cannot_determine": 0.9775256664330146, "charge_data_team": 0.01371996433710697, "charge_platform_team": 0.0026849668364085587, "split_50_50": 0.006069402393469905}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06495773902861401, "usage": {"input_tokens": 717, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7e28abf87ca6f40eb477334ea9d449329fbec8ecddc78bf59bd414d0b196900a", "runtime": null} +{"task_id": "hard-opus-b-multi_hop-03", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-03", "ts": 1790798255.4257903, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "tier3_cfo", "ordinal_ev": null, "probs": {"tier1_team_lead": 0.0497521079639966, "tier2_department_head": 0.17447988465360076, "tier3_cfo": 0.6118982972031438, "tier4_board": 0.16386971017925878}, "probs_as_returned": {"tier1_team_lead": 0.0497521079639966, "tier2_department_head": 0.17447988465360076, "tier3_cfo": 0.6118982972031438, "tier4_board": 0.16386971017925878}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.16068102803546935, "usage": {"input_tokens": 3091, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2bf642ea2a1c8491f8fd799ab9cbeeac28b59159c550a039cfb3269b6738fde3", "runtime": null} +{"task_id": "hard-opus-b-multi_hop-04", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-04", "ts": 1790798255.5661435, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "bjorn", "ordinal_ev": null, "probs": {"ana": 0.10338450001046608, "bjorn": 0.5624917858876448, "chen": 0.05520628309044809, "dmitri": 0.14147799705200356, "esra": 0.040341777170236494, "no_page_ticket_only": 0.09709765678920096}, "probs_as_returned": {"ana": 0.10338450001046608, "bjorn": 0.5624917858876448, "chen": 0.05520628309044809, "dmitri": 0.14147799705200356, "esra": 0.040341777170236494, "no_page_ticket_only": 0.09709765678920096}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.12732134602265432, "usage": {"input_tokens": 2490, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4e314c40d2309d7447ae8a57e746c47136890f12606deccacc9d84bf0e245684", "runtime": null} +{"task_id": "hard-opus-b-multi_hop-05", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-05", "ts": 1790798255.7188885, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 2.3268150682115487, "probs": {"0": 0.02658575966524453, "1": 0.12758992856431356, "2": 0.3946907024781775, "3": 0.3946907024781775, "4": 0.056442906814086966}, "probs_as_returned": {"0": 0.02658575966524453, "1": 0.12758992856431356, "2": 0.3946907024781775, "3": 0.3946907024781775, "4": 0.056442906814086966}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13895402202615514, "usage": {"input_tokens": 2721, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "64254c863452252ab3cfdeff8da660ca41736339d9f6ebb10138009e9b38b280", "runtime": null} +{"task_id": "hard-opus-b-multi_hop-07", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-07", "ts": 1790798255.8736267, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "credit_20_percent", "ordinal_ev": null, "probs": {"credit_10_percent": 0.017590746089182055, "credit_20_percent": 0.5207217809221588, "credit_25_percent": 0.12300755553854442, "credit_50_percent": 0.2960639325196957, "credit_full_month": 0.039764112150960935, "no_credit": 0.0028518727794581552}, "probs_as_returned": {"credit_10_percent": 0.017590746089182055, "credit_20_percent": 0.5207217809221588, "credit_25_percent": 0.12300755553854442, "credit_50_percent": 0.2960639325196957, "credit_full_month": 0.039764112150960935, "no_credit": 0.0028518727794581552}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14065352897159755, "usage": {"input_tokens": 2779, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6828c3ec271612dbba2e827dd5540f5dd007766a97804ed145278247c1750f78", "runtime": null} +{"task_id": "hard-opus-b-multi_hop-08", "family": "multi_hop", "split": "public", "group": "hard-opus-b-multi_hop-08", "ts": 1790798256.0146534, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.12511350509772579, "no": 0.8748864949022742}, "probs_as_returned": {"yes": 0.12511350509772579, "no": 0.8748864949022742}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1275463029742241, "usage": {"input_tokens": 2452, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7dd3229b87025032adb3e73c15cf643df9272be9f23f1c56873b2e81bb2ed118", "runtime": null} +{"task_id": "hard-opus-b-probability-01", "family": "probability", "split": "public", "group": "hard-opus-b-probability-01", "ts": 1790798256.1343052, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "merchant_wins", "ordinal_ev": null, "probs": {"customer_wins": 0.14739129143438487, "customer_withdraws": 0.2286644595678006, "merchant_wins": 0.6239442489978145}, "probs_as_returned": {"customer_wins": 0.14739129143438487, "customer_withdraws": 0.2286644595678006, "merchant_wins": 0.6239442489978145}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.10642432700842619, "usage": {"input_tokens": 2032, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7fe0cd9696ff5310c2590656cf46e84de7762a57d60e3d4d86ff09a274fae9b6", "runtime": null} +{"task_id": "hard-opus-b-probability-02", "family": "probability", "split": "public", "group": "hard-opus-b-probability-02", "ts": 1790798256.20941, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "bad_push", "ordinal_ev": null, "probs": {"bad_push": 0.7518757352522394, "database_hardware": 0.10098383660000465, "upstream_provider": 0.14714042814775588}, "probs_as_returned": {"bad_push": 0.7518757352522394, "database_hardware": 0.10098383660000465, "upstream_provider": 0.14714042814775588}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06382060499163345, "usage": {"input_tokens": 611, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "00291f91e9213488d82ccff10ac0692e6796d5523c1f39845607b29899b34a6c", "runtime": null} +{"task_id": "hard-opus-b-probability-03", "family": "probability", "split": "public", "group": "hard-opus-b-probability-03", "ts": 1790798256.3029034, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.6798002499763626, "no": 0.32019975002363743}, "probs_as_returned": {"yes": 0.6798002499763626, "no": 0.32019975002363743}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.08301691000815481, "usage": {"input_tokens": 1327, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "837db20a9eb5f8cca00c500531f07481e1302e80d74e8f76062059636f074f1a", "runtime": null} +{"task_id": "hard-opus-b-probability-04", "family": "probability", "split": "public", "group": "hard-opus-b-probability-04", "ts": 1790798256.3745131, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "attended", "ordinal_ev": null, "probs": {"attended": 0.8908360355378411, "late_cancellation": 0.07712171561686927, "no_show": 0.03204224884528953}, "probs_as_returned": {"attended": 0.8908360355378411, "late_cancellation": 0.07712171561686927, "no_show": 0.03204224884528953}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06082947796676308, "usage": {"input_tokens": 712, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6f0f49ba425083b25bf740bdc50b9dab9952ae8dcc79d775744d171cbf10977c", "runtime": null} +{"task_id": "hard-opus-b-probability-06", "family": "probability", "split": "public", "group": "hard-opus-b-probability-06", "ts": 1790798256.461978, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "upheld", "ordinal_ev": null, "probs": {"modified": 0.13231015935842363, "overturned": 0.23270913097863707, "upheld": 0.6349807096629393}, "probs_as_returned": {"modified": 0.13231015935842363, "overturned": 0.23270913097863707, "upheld": 0.6349807096629393}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07660461595514789, "usage": {"input_tokens": 1130, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2fb625ead9cc81ff306a8137afc6742c96365d403271cde2c4dcee8625fd601d", "runtime": null} +{"task_id": "hard-opus-b-tradeoff-01", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-01", "ts": 1790798256.544958, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "escalate_to_security", "ordinal_ev": null, "probs": {"escalate_to_engineering": 0.3134898075110609, "escalate_to_security": 0.6655546819611511, "page_oncall": 0.006021181075378121, "process_refund": 0.009946155239190027, "send_kb_article": 0.004988174213219846}, "probs_as_returned": {"escalate_to_engineering": 0.3134898075110609, "escalate_to_security": 0.6655546819611511, "page_oncall": 0.006021181075378121, "process_refund": 0.009946155239190027, "send_kb_article": 0.004988174213219846}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07201307598734275, "usage": {"input_tokens": 957, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1418dd07958d640f7c8e0f1c1176f0935c26ecc2086a8ec88ae5878b9ef0c14a", "runtime": null} +{"task_id": "hard-opus-b-tradeoff-03", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-03", "ts": 1790798256.6222389, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "order_a", "ordinal_ev": null, "probs": {"order_a": 0.6129149232266266, "order_b": 0.3484816687969538, "order_c": 0.023473188687705322, "order_d": 0.015130219288714327}, "probs_as_returned": {"order_a": 0.6129149232266266, "order_b": 0.3484816687969538, "order_c": 0.023473188687705322, "order_d": 0.015130219288714327}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06645498797297478, "usage": {"input_tokens": 879, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a8abda9be6f04335cfb6ebc3d8b1ca19bc4049baa511f35452265475330f7572", "runtime": null} +{"task_id": "hard-opus-b-tradeoff-06", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-06", "ts": 1790798256.6989524, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.844739173437523, "no": 0.15526082656247697}, "probs_as_returned": {"yes": 0.844739173437523, "no": 0.15526082656247697}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06630888598738238, "usage": {"input_tokens": 905, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "93bc4e228d39e7a9bff4eb0fc7353d588fc4abb97c6ac7a877572d433f74436f", "runtime": null} +{"task_id": "hard-opus-b-tradeoff-07", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-07", "ts": 1790798256.7753916, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "p0_fix_24h", "ordinal_ev": null, "probs": {"out_of_scope": 0.008135371574581048, "p0_fix_24h": 0.7449709949864798, "p1_fix_7d": 0.1873751928949244, "p2_fix_30d": 0.05688855468489418, "p3_backlog": 0.0026298858591205228}, "probs_as_returned": {"out_of_scope": 0.008135371574581048, "p0_fix_24h": 0.7449709949864798, "p1_fix_7d": 0.1873751928949244, "p2_fix_30d": 0.05688855468489418, "p3_backlog": 0.0026298858591205228}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06544080900494009, "usage": {"input_tokens": 836, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6ed5dae5fb4ed9cd3876cbf054006ddbc7db362192415fec54117c0db1a837fe", "runtime": null} +{"task_id": "hard-opus-b-tradeoff-08", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-08", "ts": 1790798256.8480814, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8678561574454184, "no": 0.13214384255458156}, "probs_as_returned": {"yes": 0.8678561574454184, "no": 0.13214384255458156}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.060815809993073344, "usage": {"input_tokens": 718, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2fcbb790b16cc63571e6a8c83b629bc2dac30c44d857a0073abb36356760361c", "runtime": null} +{"task_id": "hard-opus-b-tradeoff-12", "family": "tradeoff", "split": "public", "group": "hard-opus-b-tradeoff-12", "ts": 1790798256.9183002, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "refund_now", "ordinal_ev": null, "probs": {"deny_refund": 0.0072570034281931855, "escalate_to_fraud_team": 0.004980548547941255, "offer_store_credit": 0.011258595089608286, "refund_now": 0.9682766780586276, "wait_for_inspection": 0.008227174875629762}, "probs_as_returned": {"deny_refund": 0.0072570034281931855, "escalate_to_fraud_team": 0.004980548547941255, "offer_store_credit": 0.011258595089608286, "refund_now": 0.9682766780586276, "wait_for_inspection": 0.008227174875629762}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06042071001138538, "usage": {"input_tokens": 711, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2492df9d50c3d97e1b090c3b490fa06ccc5babd142d53ed86cf86068bc9249d1", "runtime": null} +{"task_id": "hard-opus-c-long_policy-02", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-02", "ts": 1790798257.1196346, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "erase_but_retain_transaction_records", "ordinal_ev": null, "probs": {"erase_all": 0.05664948434336836, "erase_but_retain_transaction_records": 0.8954689046360063, "erase_marketing_only": 0.00714586913522651, "reject_unverified_request": 0.02353652032748053, "restrict_all_pending_legal_hold": 0.017199221557918292}, "probs_as_returned": {"erase_all": 0.05664948434336836, "erase_but_retain_transaction_records": 0.8954689046360063, "erase_marketing_only": 0.00714586913522651, "reject_unverified_request": 0.02353652032748053, "restrict_all_pending_legal_hold": 0.017199221557918292}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.18971413001418114, "usage": {"input_tokens": 3728, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c3ae86b297027a4f6aca3d1cf9614e38a6271572271f4426bff9f9ec8608068e", "runtime": null} +{"task_id": "hard-opus-c-long_policy-03", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-03", "ts": 1790798257.3131237, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "eur_300", "ordinal_ev": null, "probs": {"eur_0": 0.01383331223422414, "eur_150": 0.2328238201782844, "eur_200": 0.2478986155873501, "eur_300": 0.31861107612832196, "eur_400": 0.17013510609182225, "eur_600": 0.016698069779997195}, "probs_as_returned": {"eur_0": 0.01383331223422414, "eur_150": 0.2328238201782844, "eur_200": 0.2478986155873501, "eur_300": 0.31861107612832196, "eur_400": 0.17013510609182225, "eur_600": 0.016698069779997195}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.18335563503205776, "usage": {"input_tokens": 3638, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "92c633b6d2105284d39762718b75d1f3c93572362ea7dff094972673fd9966ed", "runtime": null} +{"task_id": "hard-opus-c-long_policy-04", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-04", "ts": 1790798257.5001543, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9439168356016766, "no": 0.05608316439832339}, "probs_as_returned": {"yes": 0.9439168356016766, "no": 0.05608316439832339}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.17442533699795604, "usage": {"input_tokens": 3450, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "0cd379b185d672761191cefb2fa44f75b2021143ddf87d120e741bfbb6554a0b", "runtime": null} +{"task_id": "hard-opus-c-long_policy-05", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-05", "ts": 1790798257.6904256, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "2", "ordinal_ev": 1.8009979573655441, "probs": {"0": 0.10684458399102813, "1": 0.22683645296660385, "2": 0.4247953847281636, "3": 0.2415235783142044}, "probs_as_returned": {"0": 0.10684458399102813, "1": 0.22683645296660385, "2": 0.4247953847281636, "3": 0.2415235783142044}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.17759068502346054, "usage": {"input_tokens": 3385, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7bdf2daee3785d56cb1704bd5d54fa7f4412170246f91164dc7a60f7cf4c8a9c", "runtime": null} +{"task_id": "hard-opus-c-long_policy-08", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-08", "ts": 1790798257.885772, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "2", "ordinal_ev": 1.886612524670372, "probs": {"0": 0.014822349797496677, "1": 0.19410266301948487, "2": 0.6807150998981681, "3": 0.11035988728485027}, "probs_as_returned": {"0": 0.014822349797496677, "1": 0.19410266301948487, "2": 0.6807150998981681, "3": 0.11035988728485027}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.18377549899742007, "usage": {"input_tokens": 3402, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "109ddcccefe136f61426f5acae32682e3c0284e7cd3de8bd26d41d06a454efbe", "runtime": null} +{"task_id": "hard-opus-c-long_policy-10", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-10", "ts": 1790798258.0871608, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "credit_minus_restocking_fee", "ordinal_ev": null, "probs": {"credit_minus_restocking_fee": 0.8606962036243352, "full_credit": 0.04236513446101119, "reject_return": 0.07933695250396099, "repair_or_replace_only": 0.017601709410692636}, "probs_as_returned": {"credit_minus_restocking_fee": 0.8606962036243352, "full_credit": 0.04236513446101119, "reject_return": 0.07933695250396099, "repair_or_replace_only": 0.017601709410692636}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1884586689993739, "usage": {"input_tokens": 3764, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "029c534aedf8b975b66c6df022ca93544e66ff729520cab8596eb0aa318bbe51", "runtime": null} +{"task_id": "hard-opus-c-long_policy-11", "family": "long_policy", "split": "public", "group": "hard-opus-c-long_policy-11", "ts": 1790798258.280155, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8940776460411956, "no": 0.10592235395880445}, "probs_as_returned": {"yes": 0.8940776460411956, "no": 0.10592235395880445}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1785832269815728, "usage": {"input_tokens": 3528, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d174de8e6954b6617444dd1b3bc78f962dc51d82c5b333ea49c944a6a3f91602", "runtime": null} +{"task_id": "hard-opus-c-probability-03", "family": "probability", "split": "public", "group": "hard-opus-c-probability-03", "ts": 1790798258.3591545, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "kuznets_technik", "ordinal_ev": null, "probs": {"halvorsen_polymer": 0.10720891270072189, "kuznets_technik": 0.7982245521997403, "ortega_seal_works": 0.09456653509953773}, "probs_as_returned": {"halvorsen_polymer": 0.10720891270072189, "kuznets_technik": 0.7982245521997403, "ortega_seal_works": 0.09456653509953773}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06578337901737541, "usage": {"input_tokens": 668, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "25ed1a6cae928f9201937a4b64096e3653b073b7c41ad191878ebdf60b3d6b10", "runtime": null} +{"task_id": "hard-opus-c-temporal_numeric-02", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-02", "ts": 1790798258.4433796, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.1724380672551571, "no": 0.8275619327448429}, "probs_as_returned": {"yes": 0.1724380672551571, "no": 0.8275619327448429}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07318376196781173, "usage": {"input_tokens": 1053, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1d0b9d2c72a81c37a1accb985866fcdb7701105c906d5d4a67d1c21638cd1203", "runtime": null} +{"task_id": "hard-opus-c-temporal_numeric-03", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-03", "ts": 1790798258.5226524, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "eur_617_00", "ordinal_ev": null, "probs": {"eur_617_00": 0.36635352271372007, "eur_688_00": 0.2514317984133709, "eur_692_00": 0.22178227377039253, "eur_693_90": 0.111227754246519, "eur_812_00": 0.04920465085599755}, "probs_as_returned": {"eur_617_00": 0.36635352271372007, "eur_688_00": 0.2514317984133709, "eur_692_00": 0.22178227377039253, "eur_693_90": 0.111227754246519, "eur_812_00": 0.04920465085599755}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06774127396056429, "usage": {"input_tokens": 986, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "fc6bb4fdb6dac40f46136523630bbaedc676c6a39fe035d33137a22454dd757c", "runtime": null} +{"task_id": "hard-opus-c-temporal_numeric-04", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-04", "ts": 1790798258.5996156, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "usd_2303_01", "ordinal_ev": null, "probs": {"usd_2222_50": 0.014913710681025665, "usd_2303_01": 0.34349499154165725, "usd_2303_33": 0.3226069482266983, "usd_2335_00": 0.2079442332558462, "usd_2340_00": 0.11104011629477252}, "probs_as_returned": {"usd_2222_50": 0.014913710681025665, "usd_2303_01": 0.34349499154165725, "usd_2303_33": 0.3226069482266983, "usd_2335_00": 0.2079442332558462, "usd_2340_00": 0.11104011629477252}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.06698578101349995, "usage": {"input_tokens": 899, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "da3cf174d9ba536b55db9cef8a8c2c3953ac1f5dde05370c0bfd562079cccc8c", "runtime": null} +{"task_id": "hard-opus-c-temporal_numeric-06", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-06", "ts": 1790798258.6837888, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "sep_16_taxi", "ordinal_ev": null, "probs": {"none_declined": 0.02623440752459831, "sep_15_office_chair": 0.25104537458089066, "sep_16_taxi": 0.5674913765540806, "sep_17_parking": 0.04614147757294348, "sep_18_book_set": 0.08115433880928592, "sep_21_client_dinner": 0.027933024958201016}, "probs_as_returned": {"none_declined": 0.02623440752459831, "sep_15_office_chair": 0.25104537458089066, "sep_16_taxi": 0.5674913765540806, "sep_17_parking": 0.04614147757294348, "sep_18_book_set": 0.08115433880928592, "sep_21_client_dinner": 0.027933024958201016}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07364494499051943, "usage": {"input_tokens": 1102, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "0e3510f31cfc8903a4bcf541bd0826096c9f220c11d2ff17ab87c9e2c459e3e5", "runtime": null} +{"task_id": "hard-opus-c-temporal_numeric-08", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-08", "ts": 1790798258.7680447, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "eur_498_81", "ordinal_ev": null, "probs": {"eur_497_40": 0.22970119120589697, "eur_498_81": 0.37943445912969975, "eur_506_06": 0.13905597950085433, "eur_513_69": 0.19029314129726177, "eur_532_01": 0.06151522886628714}, "probs_as_returned": {"eur_497_40": 0.22970119120589697, "eur_498_81": 0.37943445912969975, "eur_506_06": 0.13905597950085433, "eur_513_69": 0.19029314129726177, "eur_532_01": 0.06151522886628714}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.07380598003510386, "usage": {"input_tokens": 1105, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "aa12663e1dba1b13ea009903b88e23d545b0cbffb76872748eea4426b7697f3c", "runtime": null} +{"task_id": "hard-opus-c-temporal_numeric-12", "family": "temporal_numeric", "split": "public", "group": "hard-opus-c-temporal_numeric-12", "ts": 1790798258.844396, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "expired_24_month_term", "ordinal_ev": null, "probs": {"covered": 0.1309008006401481, "expired_24_month_term": 0.488790641617104, "expired_30_month_cap": 0.3803085577427478}, "probs_as_returned": {"covered": 0.1309008006401481, "expired_24_month_term": 0.488790641617104, "expired_30_month_cap": 0.3803085577427478}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0671271969913505, "usage": {"input_tokens": 935, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7a7c947f8adac7944be06c7d52243f6de90a043ab9b99040d6be50925c85501c", "runtime": null} +{"task_id": "hard-sol-a-adversarial-01", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-01", "ts": 1790798258.9084065, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "deny_missing_approval", "ordinal_ev": null, "probs": {"deny_inactive_user": 0.013568707364640402, "deny_missing_approval": 0.8527472004718343, "grant_access": 0.03265819804374573, "grant_owner_exception": 0.10102589411977958}, "probs_as_returned": {"deny_inactive_user": 0.013568707364640402, "deny_missing_approval": 0.8527472004718343, "grant_access": 0.03265819804374573, "grant_owner_exception": 0.10102589411977958}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0550442700041458, "usage": {"input_tokens": 390, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c9a4a8b5bde171bbc4adc5a75b8926cce177ddc74a079ef42fd49c638c239a8d", "runtime": null} +{"task_id": "hard-sol-a-adversarial-06", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-06", "ts": 1790798258.9724832, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "probs_as_returned": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055026635993272066, "usage": {"input_tokens": 350, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a92ce8073b83747bdc64a53d35e6a06783dd40688985877ddbc9e3241bc81a05", "runtime": null} +{"task_id": "hard-sol-a-adversarial-07", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-07", "ts": 1790798259.039249, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "retain_until_2031", "ordinal_ev": null, "probs": {"delete_now": 0.010441518332080891, "needs_signature_review": 0.004918167733746614, "retain_indefinitely": 0.02849120141460286, "retain_until_2031": 0.9561491125195697}, "probs_as_returned": {"delete_now": 0.010441518332080891, "needs_signature_review": 0.004918167733746614, "retain_indefinitely": 0.02849120141460286, "retain_until_2031": 0.9561491125195697}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05719210900133476, "usage": {"input_tokens": 406, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cec1eb4c2315a2b67f7415450fc6963b7e500adf566a9d0fbb06c7deff45185c", "runtime": null} +{"task_id": "hard-sol-a-adversarial-08", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-08", "ts": 1790798259.1069183, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9502009729447547, "no": 0.049799027055245304}, "probs_as_returned": {"yes": 0.9502009729447547, "no": 0.049799027055245304}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05623733199900016, "usage": {"input_tokens": 327, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "b240fd8629f597ee868ba6dd284bc98ce59facaa454e19ab0eb991bca9443930", "runtime": null} +{"task_id": "hard-sol-a-adversarial-09", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-09", "ts": 1790798259.1715674, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "2", "ordinal_ev": 1.8962367066579777, "probs": {"0": 0.012249937955791055, "1": 0.09711242419678795, "2": 0.8727886310810733, "3": 0.01784900676634773}, "probs_as_returned": {"0": 0.012249937955791055, "1": 0.09711242419678795, "2": 0.8727886310810733, "3": 0.01784900676634773}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05472702399129048, "usage": {"input_tokens": 344, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1ac2382fee46a93290787cd4f2a4dcd2e709a765ade12b0661fe6ef2f23a3928", "runtime": null} +{"task_id": "hard-sol-a-adversarial-11", "family": "adversarial", "split": "public", "group": "hard-sol-a-adversarial-11", "ts": 1790798259.2406228, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "standard_research", "ordinal_ev": null, "probs": {"ethics_review": 0.023754425327906448, "major_grants": 0.009869402226303762, "manual_hold": 0.004100502827029603, "standard_research": 0.9622756696187603}, "probs_as_returned": {"ethics_review": 0.023754425327906448, "major_grants": 0.009869402226303762, "manual_hold": 0.004100502827029603, "standard_research": 0.9622756696187603}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05843307200120762, "usage": {"input_tokens": 411, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d325b47a5eabc0104b5685ac6a344f64b4597affea76b931de119ab447c96234", "runtime": null} +{"task_id": "hard-sol-a-multi_hop-01", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-01", "ts": 1790798259.403337, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "accept_s2_dusk", "ordinal_ev": null, "probs": {"accept_s2_dusk": 0.8820299897169496, "reject_cutoff": 0.04077512878367174, "reject_tier": 0.033779658694117705, "reroute_s3": 0.04341522280526092}, "probs_as_returned": {"accept_s2_dusk": 0.8820299897169496, "reject_cutoff": 0.04077512878367174, "reject_tier": 0.033779658694117705, "reroute_s3": 0.04341522280526092}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.1486113119754009, "usage": {"input_tokens": 2819, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "a17170b57abb2df1361cd046591fac9a75a6d4cbec6b08fc322444ec2733735a", "runtime": null} +{"task_id": "hard-sol-a-multi_hop-02", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-02", "ts": 1790798259.5663488, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "security_primary", "ordinal_ev": null, "probs": {"executive_bridge": 0.019116772677897714, "heron_q2": 0.08092609404342527, "insufficient_information": 0.12554962605057535, "security_primary": 0.7744075072281016}, "probs_as_returned": {"executive_bridge": 0.019116772677897714, "heron_q2": 0.08092609404342527, "insufficient_information": 0.12554962605057535, "security_primary": 0.7744075072281016}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14870276296278462, "usage": {"input_tokens": 2867, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f80dcbafd21976215451575c3a4c7aaa1e4310b9163f88e803d37386fb292ead", "runtime": null} +{"task_id": "hard-sol-a-multi_hop-05", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-05", "ts": 1790798259.719705, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "require_director", "ordinal_ev": null, "probs": {"pay_manager_approved": 0.2549478953776852, "reject_category": 0.034241851845298925, "require_director": 0.6956624298246201, "require_finance_board": 0.015147822952395761}, "probs_as_returned": {"pay_manager_approved": 0.2549478953776852, "reject_category": 0.034241851845298925, "require_director": 0.6956624298246201, "require_finance_board": 0.015147822952395761}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14038692804751918, "usage": {"input_tokens": 2779, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "85dd2922eaf4def08faa4d37a93213d48dc8cae2d67da6f2813cfdf7a0b7ec97", "runtime": null} +{"task_id": "hard-sol-a-multi_hop-07", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-07", "ts": 1790798259.874255, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "admit", "ordinal_ev": null, "probs": {"admit": 0.8016965785406263, "deny_prerequisite": 0.11464694915891029, "deny_score": 0.061220315486799355, "manual_equivalency": 0.02243615681366412}, "probs_as_returned": {"admit": 0.8016965785406263, "deny_prerequisite": 0.11464694915891029, "deny_score": 0.061220315486799355, "manual_equivalency": 0.02243615681366412}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14149349997751415, "usage": {"input_tokens": 2760, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "202dd9d4bc23dcdebc3717464058640255ab9d92be40f72c9ada63d3607d58e9", "runtime": null} +{"task_id": "hard-sol-a-multi_hop-08", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-08", "ts": 1790798260.0277026, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "local_maintenance", "ordinal_ev": null, "probs": {"central_engineering": 0.2039312595652488, "insufficient_log": 0.025724259265304274, "local_maintenance": 0.7614902860659044, "safety_shutdown": 0.00885419510354259}, "probs_as_returned": {"central_engineering": 0.2039312595652488, "insufficient_log": 0.025724259265304274, "local_maintenance": 0.7614902860659044, "safety_shutdown": 0.00885419510354259}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14097447402309626, "usage": {"input_tokens": 2730, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "10edb6c29cb2c114d2bd708214dbce970e9e0d76346b9a9a17658bd90a4b5c75", "runtime": null} +{"task_id": "hard-sol-a-multi_hop-09", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-09", "ts": 1790798260.1824772, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "require_steward", "ordinal_ev": null, "probs": {"confirm_l3": 0.06689419587938847, "reject_capacity": 0.03803366795607197, "require_steward": 0.8759975739130693, "switch_l4": 0.019074562251470206}, "probs_as_returned": {"confirm_l3": 0.06689419587938847, "reject_capacity": 0.03803366795607197, "require_steward": 0.8759975739130693, "switch_l4": 0.019074562251470206}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14144283498171717, "usage": {"input_tokens": 2744, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d3f12b51463c74e1da9cac65f64afbad5d02937bdb5b95b57c97423f7f7e4efc", "runtime": null} +{"task_id": "hard-sol-a-multi_hop-10", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-10", "ts": 1790798260.3371937, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "reduce_to_30_days", "ordinal_ev": null, "probs": {"approve_45_days": 0.2266260914546683, "deny_sensitive": 0.013465071955275236, "needs_field_review": 0.013465071955275236, "reduce_to_30_days": 0.7464437646347811}, "probs_as_returned": {"approve_45_days": 0.2266260914546683, "deny_sensitive": 0.013465071955275236, "needs_field_review": 0.013465071955275236, "reduce_to_30_days": 0.7464437646347811}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14021732698893175, "usage": {"input_tokens": 2808, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "4248d047860d6263c7b82ca808763e42227bf37a5983f02f7cbb28e7f7024285", "runtime": null} +{"task_id": "hard-sol-a-multi_hop-12", "family": "multi_hop", "split": "public", "group": "hard-sol-a-multi_hop-12", "ts": 1790798260.4917328, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "covered_recurrence", "ordinal_ev": null, "probs": {"covered_recurrence": 0.5488178934874424, "expired": 0.01853987381447562, "needs_authentication": 0.4270133837934193, "wrong_issue_class": 0.0056288489046627905}, "probs_as_returned": {"covered_recurrence": 0.5488178934874424, "expired": 0.01853987381447562, "needs_authentication": 0.4270133837934193, "wrong_issue_class": 0.0056288489046627905}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14022303698584437, "usage": {"input_tokens": 2755, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "109a28b59e458b2faa0fa5c6a9099afa0c904848efeedc8a4213edcb7072c7f7", "runtime": null} +{"task_id": "hard-sol-a-trap-02", "family": "trap", "split": "public", "group": "hard-sol-a-trap-02", "ts": 1790798260.5615892, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.03075154512433679, "no": 0.9692484548756632}, "probs_as_returned": {"yes": 0.03075154512433679, "no": 0.9692484548756632}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056360943999607116, "usage": {"input_tokens": 401, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "7c28024dfdd8afb8f8c56312d521810472fff8b8bf9d5756b4895894ac42a33a", "runtime": null} +{"task_id": "hard-sol-a-trap-04", "family": "trap", "split": "public", "group": "hard-sol-a-trap-04", "ts": 1790798260.627598, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.059498364613396776, "no": 0.9405016353866033}, "probs_as_returned": {"yes": 0.059498364613396776, "no": 0.9405016353866033}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054139343032147735, "usage": {"input_tokens": 307, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "6e6ae439ce53d466b96bed284ce04b19b53f07105f19d4c646bfd504f7f29bc4", "runtime": null} +{"task_id": "hard-sol-a-trap-05", "family": "trap", "split": "public", "group": "hard-sol-a-trap-05", "ts": 1790798260.6938033, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "1", "ordinal_ev": 0.8643000081318148, "probs": {"0": 0.34057212036202084, "1": 0.4660607766073019, "2": 0.1818620775675192, "3": 0.01150502546315819}, "probs_as_returned": {"0": 0.34057212036202084, "1": 0.4660607766073019, "2": 0.1818620775675192, "3": 0.01150502546315819}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05504854302853346, "usage": {"input_tokens": 454, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cb90a650fde77919d05b0774bf781a6a3c8c657c12923f50fc40444cd2ed39e5", "runtime": null} +{"task_id": "hard-sol-a-trap-06", "family": "trap", "split": "public", "group": "hard-sol-a-trap-06", "ts": 1790798260.7592058, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "keep_open_unresolved", "ordinal_ev": null, "probs": {"await_internal_metrics": 0.008337830351487158, "close_agent_verified": 0.0025314294996148625, "close_confirmed": 0.007830803388441922, "keep_open_unresolved": 0.981299936760456}, "probs_as_returned": {"await_internal_metrics": 0.008337830351487158, "close_agent_verified": 0.0025314294996148625, "close_confirmed": 0.007830803388441922, "keep_open_unresolved": 0.981299936760456}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05474362097447738, "usage": {"input_tokens": 459, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8b8078063a329560df250a60048ad621c160a5c444f7e033ab3aa06f28430266", "runtime": null} +{"task_id": "hard-sol-a-trap-08", "family": "trap", "split": "public", "group": "hard-sol-a-trap-08", "ts": 1790798260.8250237, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "late", "ordinal_ev": null, "probs": {"canceled": 0.0052844814699961285, "indeterminate": 0.00282185985242437, "late": 0.9648903851080965, "on_time": 0.027003273569482986}, "probs_as_returned": {"canceled": 0.0052844814699961285, "indeterminate": 0.00282185985242437, "late": 0.9648903851080965, "on_time": 0.027003273569482986}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054103603994008154, "usage": {"input_tokens": 386, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2336fba7022273080e74baa2fce06b0e253db023c363d96e542d05f295cbfd76", "runtime": null} +{"task_id": "hard-sol-a-trap-10", "family": "trap", "split": "public", "group": "hard-sol-a-trap-10", "ts": 1790798260.891978, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "blocked_second_review", "ordinal_ev": null, "probs": {"blocked_failed_test": 0.014370727476242724, "blocked_second_review": 0.9616283560317681, "ready_one_review": 0.00869971844133038, "ready_two_reviews": 0.015301198050658662}, "probs_as_returned": {"blocked_failed_test": 0.014370727476242724, "blocked_second_review": 0.9616283560317681, "ready_one_review": 0.00869971844133038, "ready_two_reviews": 0.015301198050658662}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05446268996456638, "usage": {"input_tokens": 312, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "57079ff0a2338f36e3a122a5844a3b2ea3535df34b41dc1fe634f30b9261b63c", "runtime": null} +{"task_id": "hard-sol-a-trap-13", "family": "trap", "split": "public", "group": "hard-sol-a-trap-13", "ts": 1790798260.9585488, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.022659190258890113, "no": 0.9773408097411099}, "probs_as_returned": {"yes": 0.022659190258890113, "no": 0.9773408097411099}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05527671700110659, "usage": {"input_tokens": 315, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "9cbd2d2eb101c75146516071daced32bb08a4afe98e4a0f91bdbce0c1210838a", "runtime": null} +{"task_id": "hard-sol-a-trap-15", "family": "trap", "split": "public", "group": "hard-sol-a-trap-15", "ts": 1790798261.0235245, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.14720923592665844, "no": 0.8527907640733415}, "probs_as_returned": {"yes": 0.14720923592665844, "no": 0.8527907640733415}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05429522099439055, "usage": {"input_tokens": 417, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "317df168fa7e0123d08147e30e97def8f9638f63cf6e7170449441cee466420b", "runtime": null} +{"task_id": "hard-sol-b-judge_hard-01", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-01", "ts": 1790798261.0898895, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8879876242264044, "no": 0.11201237577359557}, "probs_as_returned": {"yes": 0.8879876242264044, "no": 0.11201237577359557}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05526847002329305, "usage": {"input_tokens": 402, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "df63f0220bd57ef5ae02312f07e65b86c1e6291188284f2326bf70a3b3e382a8", "runtime": null} +{"task_id": "hard-sol-b-judge_hard-02", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-02", "ts": 1790798261.1548872, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.2681939143399331, "no": 0.7318060856600669}, "probs_as_returned": {"yes": 0.2681939143399331, "no": 0.7318060856600669}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054094957013148814, "usage": {"input_tokens": 326, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "965ed4ad9c209f01c3e80f6124da0e3c8f509aa8d8827daa21c578111cc4eca3", "runtime": null} +{"task_id": "hard-sol-b-judge_hard-05", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-05", "ts": 1790798261.2206655, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8363317223730603, "no": 0.1636682776269397}, "probs_as_returned": {"yes": 0.8363317223730603, "no": 0.1636682776269397}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05520159302977845, "usage": {"input_tokens": 346, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "30d861a52de93f42aee2eaf928d22dc5c68f10818a01698b65eabbc1cd9d1270", "runtime": null} +{"task_id": "hard-sol-b-judge_hard-08", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-08", "ts": 1790798261.285045, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8815938286018441, "no": 0.1184061713981559}, "probs_as_returned": {"yes": 0.8815938286018441, "no": 0.1184061713981559}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054450018040370196, "usage": {"input_tokens": 328, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d22870abc5ce09d5b8097ff6ebdded055e5cbb4c42dfde0ac269ff38e0c8c6e7", "runtime": null} +{"task_id": "hard-sol-b-judge_hard-10", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-10", "ts": 1790798261.3487778, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.3340072352673295, "no": 0.6659927647326704}, "probs_as_returned": {"yes": 0.3340072352673295, "no": 0.6659927647326704}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053922855004202574, "usage": {"input_tokens": 347, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "ef9999c48c6e5e98a01b5d39a89c2256e3e4b0ffb1cb07472174a650be4b261c", "runtime": null} +{"task_id": "hard-sol-b-judge_hard-14", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-14", "ts": 1790798261.4141302, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.011493812770397228, "no": 0.9885061872296028}, "probs_as_returned": {"yes": 0.011493812770397228, "no": 0.9885061872296028}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054919955029617995, "usage": {"input_tokens": 364, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "29591fd434de908bdc71b96616b8b86561cf147f5b510a9bb51275ab0bcdc5da", "runtime": null} +{"task_id": "hard-sol-b-judge_hard-15", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-15", "ts": 1790798261.4783244, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.9405016353866033, "no": 0.05949836461339675}, "probs_as_returned": {"yes": 0.9405016353866033, "no": 0.05949836461339675}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053678694006521255, "usage": {"input_tokens": 320, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d68bb0fb6eb7599b1c9db21ca00185ed407c5993691a4d5731b44fb759db3831", "runtime": null} +{"task_id": "hard-sol-b-judge_hard-18", "family": "judge_hard", "split": "public", "group": "hard-sol-b-judge_hard-18", "ts": 1790798261.5423746, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "probs_as_returned": {"yes": 0.016659759016074603, "no": 0.9833402409839254}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05330249801045284, "usage": {"input_tokens": 288, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2f8b8a15a3f7334299367faf078ee2c0a3804386c3b40de2fbc77789976bb71d", "runtime": null} +{"task_id": "hard-sol-b-long_policy-01", "family": "long_policy", "split": "public", "group": "hard-sol-b-long_policy-01", "ts": 1790798261.7070825, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "approve_lodging_only", "ordinal_ev": null, "probs": {"approve_all": 0.08909463191094494, "approve_lodging_only": 0.706305265580735, "approve_meals_only": 0.14717197021020476, "reject_entire_claim": 0.05742813229811534}, "probs_as_returned": {"approve_all": 0.08909463191094494, "approve_lodging_only": 0.706305265580735, "approve_meals_only": 0.14717197021020476, "reject_entire_claim": 0.05742813229811534}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.15145176299847662, "usage": {"input_tokens": 2866, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e8dc8aa1d66e36ca0180c086f5c48e7ae9d7b989d1e0cac6031a28a59b520d91", "runtime": null} +{"task_id": "hard-sol-b-long_policy-02", "family": "long_policy", "split": "public", "group": "hard-sol-b-long_policy-02", "ts": 1790798261.8668373, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "deny_current_export", "ordinal_ev": null, "probs": {"analytics_owner_only": 0.012159429361438828, "deny_current_export": 0.8663400458018994, "privacy_and_security": 0.10263625163294894, "privacy_only": 0.018864273203712912}, "probs_as_returned": {"analytics_owner_only": 0.012159429361438828, "deny_current_export": 0.8663400458018994, "privacy_and_security": 0.10263625163294894, "privacy_only": 0.018864273203712912}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14549395901849493, "usage": {"input_tokens": 2716, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5ae2985b5cffb7f39e3eb856d25ca01cc3aa42871da31348f1126c19a8414f4c", "runtime": null} +{"task_id": "hard-sol-b-long_policy-05", "family": "long_policy", "split": "public", "group": "hard-sol-b-long_policy-05", "ts": 1790798262.0246863, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "delete_profile_omar_april_and_table", "ordinal_ev": null, "probs": {"delete_everything": 0.021894364677177067, "delete_nothing": 0.0233119742695315, "delete_only_profile": 0.34608827612402576, "delete_profile_omar_april_and_table": 0.6087053849292656}, "probs_as_returned": {"delete_everything": 0.021894364677177067, "delete_nothing": 0.0233119742695315, "delete_only_profile": 0.34608827612402576, "delete_profile_omar_april_and_table": 0.6087053849292656}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14193737204186618, "usage": {"input_tokens": 2677, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "54d0deee129933a5893e6684b8e4cafb10be082f0ad35d631c46dee31c8b3637", "runtime": null} +{"task_id": "hard-sol-b-long_policy-06", "family": "long_policy", "split": "public", "group": "hard-sol-b-long_policy-06", "ts": 1790798262.1794713, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "east_ward", "ordinal_ev": null, "probs": {"east_ward": 0.3411456641180011, "harbor_neighbors": 0.3009168221241823, "no_award": 0.016791849639815445, "river_arts": 0.3411456641180011}, "probs_as_returned": {"east_ward": 0.3411456641180011, "harbor_neighbors": 0.3009168221241823, "no_award": 0.016791849639815445, "river_arts": 0.3411456641180011}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.14362263801740482, "usage": {"input_tokens": 2760, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2a2cfe07b3acfd6514323c1dc61fa98b73ff083500ac9b3b12933062c05cf474", "runtime": null} +{"task_id": "hard-sol-b-routing_hard-01", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-01", "ts": 1790798262.2474637, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "office_file_repair", "ordinal_ev": null, "probs": {"data_pipeline": 0.002432868028110054, "desktop_support": 0.003774378037715521, "finance_review": 0.004278965637903766, "office_file_repair": 0.9430929283602817, "spreadsheet_formula": 0.04642085993598908}, "probs_as_returned": {"data_pipeline": 0.002432868028110054, "desktop_support": 0.003774378037715521, "finance_review": 0.004278965637903766, "office_file_repair": 0.9430929283602817, "spreadsheet_formula": 0.04642085993598908}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.056332165957428515, "usage": {"input_tokens": 440, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "144069ab69b55a768b583a8c4a916345eb77c1ae7edb41dde8ef2a22283de597", "runtime": null} +{"task_id": "hard-sol-b-routing_hard-02", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-02", "ts": 1790798262.314271, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "ledger_reconciliation", "ordinal_ev": null, "probs": {"customer_support": 0.024586117348690935, "fraud_review": 0.0015553761372732856, "ledger_reconciliation": 0.9354018336737445, "mobile_app": 0.03364522339881921, "payment_disputes": 0.004811449441472035}, "probs_as_returned": {"customer_support": 0.024586117348690935, "fraud_review": 0.0015553761372732856, "ledger_reconciliation": 0.9354018336737445, "mobile_app": 0.03364522339881921, "payment_disputes": 0.004811449441472035}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05518153903540224, "usage": {"input_tokens": 423, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5a74c337ca521ad70194afb04c1a5efe2182ddb44ce878e4a5f4578089b5b75a", "runtime": null} +{"task_id": "hard-sol-b-routing_hard-03", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-03", "ts": 1790798262.3805978, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "network_dns", "ordinal_ev": null, "probs": {"api_platform": 0.004842894208676956, "authoritative_dns": 0.005156460174491347, "endpoint_devices": 0.04634319529093982, "network_dns": 0.9415150632539939, "tls_certificates": 0.002142387071897831}, "probs_as_returned": {"api_platform": 0.004842894208676956, "authoritative_dns": 0.005156460174491347, "endpoint_devices": 0.04634319529093982, "network_dns": 0.9415150632539939, "tls_certificates": 0.002142387071897831}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05583970597945154, "usage": {"input_tokens": 421, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "02a7300b899551972e2a36ba00d6b923122e9d7ed9d4e688093d59effc392bb1", "runtime": null} +{"task_id": "hard-sol-b-routing_hard-07", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-07", "ts": 1790798262.4475033, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "release_notarization", "ordinal_ev": null, "probs": {"ci_infrastructure": 0.0026358552072950053, "code_signing": 0.03044686823684439, "endpoint_security": 0.0026358552072950053, "macos_runtime": 0.004635982743818916, "release_notarization": 0.9596454386047467}, "probs_as_returned": {"ci_infrastructure": 0.0026358552072950053, "code_signing": 0.03044686823684439, "endpoint_security": 0.0026358552072950053, "macos_runtime": 0.004635982743818916, "release_notarization": 0.9596454386047467}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055770282982848585, "usage": {"input_tokens": 404, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "62b9e2a8c7baaddaa961e1db857a3cb7f970da7c939f2377eb658a3d17bf5877", "runtime": null} +{"task_id": "hard-sol-b-routing_hard-09", "family": "routing_hard", "split": "public", "group": "hard-sol-b-routing_hard-09", "ts": 1790798262.5145252, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "source_access", "ordinal_ev": null, "probs": {"git_client": 0.020297759877090524, "identity_login": 0.006561567668597966, "repository_admin": 0.03352908025315896, "source_access": 0.9321728248733867, "vpn_network": 0.007438767327765931}, "probs_as_returned": {"git_client": 0.020297759877090524, "identity_login": 0.006561567668597966, "repository_admin": 0.03352908025315896, "source_access": 0.9321728248733867, "vpn_network": 0.007438767327765931}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05416839703684673, "usage": {"input_tokens": 410, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "c39e62173a0c7646a35637bdfa73130b9163fcbff06d9872d081cb03334518e4", "runtime": null} +{"task_id": "hard-sol-b-temporal_numeric-01", "family": "temporal_numeric", "split": "public", "group": "hard-sol-b-temporal_numeric-01", "ts": 1790798262.5811465, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "late_by_under_2h", "ordinal_ev": null, "probs": {"before_open": 0.07619692419201703, "late_by_2h_or_more": 0.2672214674340832, "late_by_under_2h": 0.38936014093981663, "within_window": 0.2672214674340832}, "probs_as_returned": {"before_open": 0.07619692419201703, "late_by_2h_or_more": 0.2672214674340832, "late_by_under_2h": 0.38936014093981663, "within_window": 0.2672214674340832}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05375877697952092, "usage": {"input_tokens": 402, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "97f2a3acfaa9cdfc27247f1b6626898985bd55d01571bf094eae9c31ce3bee65", "runtime": null} +{"task_id": "hard-sol-b-temporal_numeric-02", "family": "temporal_numeric", "split": "public", "group": "hard-sol-b-temporal_numeric-02", "ts": 1790798262.645504, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "under_100gb_below", "ordinal_ev": null, "probs": {"at_least_100gb_below": 0.2777216041744788, "exactly_equal": 0.20294399073523287, "over_limit": 0.1392823299139878, "under_100gb_below": 0.3800520751763005}, "probs_as_returned": {"at_least_100gb_below": 0.2777216041744788, "exactly_equal": 0.20294399073523287, "over_limit": 0.1392823299139878, "under_100gb_below": 0.3800520751763005}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.053952247952111065, "usage": {"input_tokens": 415, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5eb0f6b1a78e0eae730dd17de40468b9cd0f82a72e408a1d5222fc1cdb05f649", "runtime": null} +{"task_id": "hard-sol-b-temporal_numeric-03", "family": "temporal_numeric", "split": "public", "group": "hard-sol-b-temporal_numeric-03", "ts": 1790798262.7099655, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "12_credits", "ordinal_ev": null, "probs": {"12_credits": 0.38418415861441135, "15_credits": 0.11664127258300278, "6_credits": 0.21843347437078164, "9_credits": 0.28074109443180434}, "probs_as_returned": {"12_credits": 0.38418415861441135, "15_credits": 0.11664127258300278, "6_credits": 0.21843347437078164, "9_credits": 0.28074109443180434}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054083886032458395, "usage": {"input_tokens": 354, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "053958d2f4e6a138bab603838391687d35464963c43a97abd8b8125893fef658", "runtime": null} +{"task_id": "hard-sol-b-temporal_numeric-04", "family": "temporal_numeric", "split": "public", "group": "hard-sol-b-temporal_numeric-04", "ts": 1790798262.7756846, "status": "ok", "ok": true, "valid": true, "correct": false, "predicted": "narrow_fail", "ordinal_ev": null, "probs": {"clear_fail": 0.324620580367349, "narrow_fail": 0.6472762711048763, "pass": 0.02810314852777479}, "probs_as_returned": {"clear_fail": 0.324620580367349, "narrow_fail": 0.6472762711048763, "pass": 0.02810314852777479}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05440335895400494, "usage": {"input_tokens": 363, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "65e7eb951f4f10fa38a1d098279233ce79b93aaedabe5f996fbede921ff01915", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-03", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-03", "ts": 1790798262.8417857, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.03075154512433679, "no": 0.9692484548756632}, "probs_as_returned": {"yes": 0.03075154512433679, "no": 0.9692484548756632}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.055093307979404926, "usage": {"input_tokens": 509, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "e37108923dc30d2a4a83b167b86b194d2e308b0a890985add07a44426b1cf44a", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-05", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-05", "ts": 1790798262.9072132, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7318060856600669, "no": 0.2681939143399331}, "probs_as_returned": {"yes": 0.7318060856600669, "no": 0.2681939143399331}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054981209977995604, "usage": {"input_tokens": 471, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "8f81d655c9907b704269978ca3313333bdcedbc51b5b1e630b13c5800011923b", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-07", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-07", "ts": 1790798262.9727387, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.2935240287234267, "no": 0.7064759712765734}, "probs_as_returned": {"yes": 0.2935240287234267, "no": 0.7064759712765734}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05465300299692899, "usage": {"input_tokens": 435, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "cec119b1594a590e42cbdb263ce15a770da885bd0bb7a642fb0b554a9c9884c2", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-08", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-08", "ts": 1790798263.039087, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.45308504361568214, "no": 0.5469149563843179}, "probs_as_returned": {"yes": 0.45308504361568214, "no": 0.5469149563843179}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05400236998684704, "usage": {"input_tokens": 430, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "5e00e8bb7c4bb0c8b64abb907e546a501b63515ac46709aefb47de6080c0e63f", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-09", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-09", "ts": 1790798263.1030269, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "probs_as_returned": {"yes": 0.7557061813028185, "no": 0.24429381869718148}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054260816948954016, "usage": {"input_tokens": 460, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "bbfe1e0dab098a4764e236c30637b4e6aefd3db3b4acb7a7d29ec3c9cdbe47c6", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-10", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-10", "ts": 1790798263.1676743, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.8527907640733415, "no": 0.14720923592665847}, "probs_as_returned": {"yes": 0.8527907640733415, "no": 0.14720923592665847}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05431436497019604, "usage": {"input_tokens": 489, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "943cd31aa08b8ad7349754fe4be595f14b2f15433057702685a2596b01df5c6e", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-11", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-11", "ts": 1790798263.2337215, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.007439008670580321, "no": 0.9925609913294197}, "probs_as_returned": {"yes": 0.007439008670580321, "no": 0.9925609913294197}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05559056799393147, "usage": {"input_tokens": 460, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f68e52464b586f104e10629175baf491c99ca4553a3066c7793132add0a2e073", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-13", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-13", "ts": 1790798263.298532, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "no", "ordinal_ev": null, "probs": {"yes": 0.10012611628383591, "no": 0.8998738837161641}, "probs_as_returned": {"yes": 0.10012611628383591, "no": 0.8998738837161641}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.054894416010938585, "usage": {"input_tokens": 450, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "11774a64d3682c2fecf268cefdc5f25d007d20ee7446d692274cbbc6dd07619d", "runtime": null} +{"task_id": "hard-sol-c-judge_hard-15", "family": "judge_hard", "split": "public", "group": "hard-sol-c-judge_hard-15", "ts": 1790798263.3625786, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "yes", "ordinal_ev": null, "probs": {"yes": 0.788764540067536, "no": 0.21123545993246395}, "probs_as_returned": {"yes": 0.788764540067536, "no": 0.21123545993246395}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.05409122904529795, "usage": {"input_tokens": 405, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "0bcd1d95150d9010448e4bef635dd4698a4549d9423dc39c217535321758070d", "runtime": null} +{"task_id": "hard-sol-c-multi_hop-07", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-07", "ts": 1790798263.5074813, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "programme_review", "ordinal_ev": null, "probs": {"partial_release": 0.14708474951632727, "programme_review": 0.5492223588263985, "reject_draw": 0.15660814214094693, "release_draw": 0.14708474951632727}, "probs_as_returned": {"partial_release": 0.14708474951632727, "programme_review": 0.5492223588263985, "reject_draw": 0.15660814214094693, "release_draw": 0.14708474951632727}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13215501402737573, "usage": {"input_tokens": 2615, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "f79dc5592fb62c68d8f33a480df480d02ec4f8d52243e8cd02e814cc394a2152", "runtime": null} +{"task_id": "hard-sol-c-multi_hop-09", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-09", "ts": 1790798263.654251, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "bus_substitution", "ordinal_ev": null, "probs": {"bus_substitution": 0.8215092246509226, "call_fen_cross": 0.02954865144756523, "pass_fen_cross": 0.11748026711353574, "terminate_oakmere": 0.03146185678797637}, "probs_as_returned": {"bus_substitution": 0.8215092246509226, "call_fen_cross": 0.02954865144756523, "pass_fen_cross": 0.11748026711353574, "terminate_oakmere": 0.03146185678797637}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13392144395038486, "usage": {"input_tokens": 2637, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "2990422675f28e6acd1fd92bbd4319da9dec5b3e1558b832bbdbc1761263e63b", "runtime": null} +{"task_id": "hard-sol-c-multi_hop-11", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-11", "ts": 1790798263.8074903, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "coverage_excluded", "ordinal_ev": null, "probs": {"adjuster_referral": 0.06012453285478484, "coverage_confirmed": 0.04678050972661249, "coverage_excluded": 0.7873470051099877, "documentation_needed": 0.10574795230861497}, "probs_as_returned": {"adjuster_referral": 0.06012453285478484, "coverage_confirmed": 0.04678050972661249, "coverage_excluded": 0.7873470051099877, "documentation_needed": 0.10574795230861497}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13824997999472544, "usage": {"input_tokens": 2715, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "1f233845238330e9bca7c8cd1100a7426bc8fef24fc35f9c5794c2acde7f363a", "runtime": null} +{"task_id": "hard-sol-c-multi_hop-12", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-12", "ts": 1790798263.8836653, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "conservation_hold", "ordinal_ev": null, "probs": {"conservation_hold": 0.9140935257634624, "deny_request": 0.024026050062128126, "digital_copy_only": 0.029001632737729627, "supervised_delivery": 0.03287879143667978}, "probs_as_returned": {"conservation_hold": 0.9140935257634624, "deny_request": 0.024026050062128126, "digital_copy_only": 0.029001632737729627, "supervised_delivery": 0.03287879143667978}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.0647301830467768, "usage": {"input_tokens": 658, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "d722a387c59ea6c4fb86a0b07f6605b7c6487a4e14709e060fe321187f215636", "runtime": null} +{"task_id": "hard-sol-c-multi_hop-13", "family": "multi_hop", "split": "public", "group": "hard-sol-c-multi_hop-13", "ts": 1790798264.0318115, "status": "ok", "ok": true, "valid": true, "correct": true, "predicted": "normal_release", "ordinal_ev": null, "probs": {"engineering_review": 0.022049499850414715, "normal_release": 0.9510435155444504, "rework": 0.011774210282422209, "scrap_lot": 0.015132774322712624}, "probs_as_returned": {"engineering_review": 0.022049499850414715, "normal_release": 0.9510435155444504, "rework": 0.011774210282422209, "scrap_lot": 0.015132774322712624}, "strict_valid": true, "renormalized": false, "probs_source": "native", "model": "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", "error": null, "schema_error": null, "status_code": 200, "latency_s": 0.13533474400173873, "usage": {"input_tokens": 2683, "output_tokens": 1, "decision_count": 1}, "cost_usd": 0.0, "cost_basis": "zero_route_fee_compute_excluded", "reserved_usd": 0.02, "charged_usd": 0.0, "raw_sha256": "153ab5420e548755a08b3f3c25aa072a26b69ce4cb5f1521bd68d6565e9b0a64", "runtime": null} diff --git a/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-summary.json b/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-summary.json new file mode 100644 index 0000000..6219a0b --- /dev/null +++ b/services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-summary.json @@ -0,0 +1,2141 @@ +{ + "accuracy": 0.8744588744588745, + "brier_mean": 0.17806609620099598, + "calibration_n": 231, + "complete": true, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.4, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": 0.3623595989308779, + "n": 10 + }, + { + "accuracy": 0.0, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": 0.46124870941679735, + "n": 5 + }, + { + "accuracy": 0.8, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": 0.5637253221582417, + "n": 10 + }, + { + "accuracy": 0.65, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.648800445448587, + "n": 20 + }, + { + "accuracy": 0.7391304347826086, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7523100109863671, + "n": 23 + }, + { + "accuracy": 0.9117647058823529, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8641129171311692, + "n": 34 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9627515382033693, + "n": 129 + } + ], + "ece": 0.051072415884039386, + "n": 231 + }, + "latency": { + "n": 231, + "p50_s": 0.054981209977995604, + "p95_s": 0.14865703746909276 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "ledger_charged_usd": 0.0, + "macro_accuracy": 0.8725744098809114, + "model_identities": [ + "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd" + ], + "n_attempted": 231, + "n_correct": 202, + "n_planned": 231, + "n_renormalized": 0, + "n_scorable": 231, + "n_valid": 231, + "operational_success": 1.0, + "ordinal_mae": 0.26234367203481096, + "paraphrase_consistency": { + "agree": 35, + "agreement": 0.9722222222222222, + "both_correct_rate_all_pairs": 0.9722222222222222, + "both_valid": 36, + "pairs": 36 + }, + "per_family": { + "adequacy": { + "accuracy": 1.0, + "brier_mean": 0.04603689738961828, + "calibration_n": 12, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": 0.5930110454411601, + "n": 1 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7557061813028185, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8878357373215198, + "n": 2 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9520119763886462, + "n": 8 + } + ], + "ece": 0.104959623958651, + "n": 12 + }, + "latency": { + "n": 12, + "p50_s": 0.05385151947848499, + "p95_s": 0.05537226824963 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 12, + "n_correct": 12, + "n_planned": 12, + "n_renormalized": 0, + "n_scorable": 12, + "n_valid": 12, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "adversarial": { + "accuracy": 1.0, + "brier_mean": 0.011617825043304442, + "calibration_n": 6, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8627679157764538, + "n": 2 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9629914990167525, + "n": 4 + } + ], + "ece": 0.07041636206334703, + "n": 6 + }, + "latency": { + "n": 6, + "p50_s": 0.05564080100157298, + "p95_s": 0.058122831251239404 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 6, + "n_correct": 6, + "n_planned": 6, + "n_renormalized": 0, + "n_scorable": 6, + "n_valid": 6, + "operational_success": 1.0, + "ordinal_mae": 0.10376329334202228, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "ambiguous": { + "accuracy": 0.7142857142857143, + "brier_mean": 0.3223035707740803, + "calibration_n": 7, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.3333333333333333, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.6479833643674017, + "n": 3 + }, + { + "accuracy": null, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9463672181616865, + "n": 4 + } + ], + "ece": 0.16549731720792277, + "n": 7 + }, + "latency": { + "n": 7, + "p50_s": 0.06240525998873636, + "p95_s": 0.06425336602260359 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 7, + "n_correct": 5, + "n_planned": 7, + "n_renormalized": 0, + "n_scorable": 7, + "n_valid": 7, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "extraction": { + "accuracy": 1.0, + "brier_mean": 0.0019479746093977082, + "calibration_n": 24, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9683153887441366, + "n": 24 + } + ], + "ece": 0.031684611255863415, + "n": 24 + }, + "latency": { + "n": 24, + "p50_s": 0.05352575849974528, + "p95_s": 0.05614419543999247 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 24, + "n_correct": 24, + "n_planned": 24, + "n_renormalized": 0, + "n_scorable": 24, + "n_valid": 24, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "fact": { + "accuracy": 1.0, + "brier_mean": 0.00253357674402684, + "calibration_n": 12, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9707540110368739, + "n": 12 + } + ], + "ece": 0.029245988963126135, + "n": 12 + }, + "latency": { + "n": 12, + "p50_s": 0.052916569489752874, + "p95_s": 0.053868782028439456 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 12, + "n_correct": 12, + "n_planned": 12, + "n_renormalized": 0, + "n_scorable": 12, + "n_valid": 12, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "intent": { + "accuracy": 0.9583333333333334, + "brier_mean": 0.04236379090188356, + "calibration_n": 24, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.0, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": 0.4791247461286767, + "n": 1 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.697318944283325, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7504260155024499, + "n": 2 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8623501745620707, + "n": 3 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.97124439087109, + "n": 17 + } + ], + "ece": 0.0909478584310712, + "n": 24 + }, + "latency": { + "n": 24, + "p50_s": 0.05407417201786302, + "p95_s": 0.059262538660550486 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 24, + "n_correct": 23, + "n_planned": 24, + "n_renormalized": 0, + "n_scorable": 24, + "n_valid": 24, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "judge_hard": { + "accuracy": 0.9411764705882353, + "brier_mean": 0.1769820408934362, + "calibration_n": 17, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": 0.5469149563843179, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.6659927647326704, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7429117727934124, + "n": 5 + }, + { + "accuracy": 0.8, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8717155645981629, + "n": 5 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9748315019610428, + "n": 5 + } + ], + "ece": 0.15040904282950293, + "n": 17 + }, + "latency": { + "n": 17, + "p50_s": 0.054450018040370196, + "p95_s": 0.055332889617420736 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 17, + "n_correct": 16, + "n_planned": 17, + "n_renormalized": 0, + "n_scorable": 17, + "n_valid": 17, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "long_policy": { + "accuracy": 0.6842105263157895, + "brier_mean": 0.488183253400819, + "calibration_n": 19, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.5, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": 0.32987837012316157, + "n": 2 + }, + { + "accuracy": 0.0, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": 0.4247953847281636, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": 0.5930110454411601, + "n": 1 + }, + { + "accuracy": 0.6666666666666666, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.6374422769566587, + "n": 3 + }, + { + "accuracy": 0.5, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7434209921956753, + "n": 4 + }, + { + "accuracy": 0.8333333333333334, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8591073374831182, + "n": 6 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9264976568409564, + "n": 2 + } + ], + "ece": 0.13342281306158954, + "n": 19 + }, + "latency": { + "n": 19, + "p50_s": 0.15093205898301676, + "p95_s": 0.8460185076109925 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 19, + "n_correct": 13, + "n_planned": 19, + "n_renormalized": 0, + "n_scorable": 19, + "n_valid": 19, + "operational_success": 1.0, + "ordinal_mae": 0.8438052410179581, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "multi_hop": { + "accuracy": 0.8333333333333334, + "brier_mean": 0.2821094188229273, + "calibration_n": 18, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": 0.3946907024781775, + "n": 1 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.75, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": 0.5453134547809111, + "n": 4 + }, + { + "accuracy": 1.0, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.6537803635138819, + "n": 2 + }, + { + "accuracy": 0.5, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7674221407596936, + "n": 4 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8512239723447685, + "n": 5 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9325685206539565, + "n": 2 + } + ], + "ece": 0.22582924507652405, + "n": 18 + }, + "latency": { + "n": 18, + "p50_s": 0.14022018198738806, + "p95_s": 0.1504995027236873 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 18, + "n_correct": 15, + "n_planned": 18, + "n_renormalized": 0, + "n_scorable": 18, + "n_valid": 18, + "operational_success": 1.0, + "ordinal_mae": 0.3268150682115487, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "ordinal": { + "accuracy": 1.0, + "brier_mean": 0.006310346320679678, + "calibration_n": 12, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8500853530913438, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.956899632823367, + "n": 11 + } + ], + "ece": 0.05200155715430161, + "n": 12 + }, + "latency": { + "n": 12, + "p50_s": 0.054876862006494775, + "p95_s": 0.06036159305367618 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 12, + "n_correct": 12, + "n_planned": 12, + "n_renormalized": 0, + "n_scorable": 12, + "n_valid": 12, + "operational_success": 1.0, + "ordinal_mae": 0.0531333548567569, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "policy": { + "accuracy": 1.0, + "brier_mean": 0.020422084182937634, + "calibration_n": 12, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7557061813028185, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8742406957013814, + "n": 2 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9513615324190499, + "n": 9 + } + ], + "ece": 0.07779655296024748, + "n": 12 + }, + "latency": { + "n": 12, + "p50_s": 0.05428065449814312, + "p95_s": 0.05681873176072258 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 12, + "n_correct": 12, + "n_planned": 12, + "n_renormalized": 0, + "n_scorable": 12, + "n_valid": 12, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "probability": { + "accuracy": 0.7, + "brier_mean": 0.46568152828081544, + "calibration_n": 10, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": 0.5777854893190272, + "n": 1 + }, + { + "accuracy": 0.8, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.6325445353204342, + "n": 5 + }, + { + "accuracy": 0.3333333333333333, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7561351202525173, + "n": 3 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8908360355378411, + "n": 1 + }, + { + "accuracy": null, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": null, + "n": 0 + } + ], + "ece": 0.26370611592985127, + "n": 10 + }, + "latency": { + "n": 10, + "p50_s": 0.07672692849882878, + "p95_s": 0.09677280441683249 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 10, + "n_correct": 7, + "n_planned": 10, + "n_renormalized": 0, + "n_scorable": 10, + "n_valid": 10, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "routing": { + "accuracy": 1.0, + "brier_mean": 0.041188901489954015, + "calibration_n": 12, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.6801954980304856, + "n": 2 + }, + { + "accuracy": 1.0, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7877520218832728, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8825011701644436, + "n": 2 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9364805526689252, + "n": 7 + } + ], + "ece": 0.12762423108703272, + "n": 12 + }, + "latency": { + "n": 12, + "p50_s": 0.05457381851738319, + "p95_s": 0.05613349811465014 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 12, + "n_correct": 12, + "n_planned": 12, + "n_renormalized": 0, + "n_scorable": 12, + "n_valid": 12, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "routing_hard": { + "accuracy": 1.0, + "brier_mean": 0.0051631143261297256, + "calibration_n": 5, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9423656177532307, + "n": 5 + } + ], + "ece": 0.05763438224676931, + "n": 5 + }, + "latency": { + "n": 5, + "p50_s": 0.055770282982848585, + "p95_s": 0.05623367396183312 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 5, + "n_correct": 5, + "n_planned": 5, + "n_renormalized": 0, + "n_scorable": 5, + "n_valid": 5, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "temporal_numeric": { + "accuracy": 0.3333333333333333, + "brier_mean": 0.7767759878778288, + "calibration_n": 15, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.2857142857142857, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": 0.36702122094061124, + "n": 7 + }, + { + "accuracy": 0.0, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": 0.4681313198099223, + "n": 2 + }, + { + "accuracy": 0.5, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": 0.5726384329365539, + "n": 2 + }, + { + "accuracy": 0.0, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.6472762711048763, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7318060856600669, + "n": 1 + }, + { + "accuracy": 0.5, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8512242138235586, + "n": 2 + }, + { + "accuracy": null, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": null, + "n": 0 + } + ], + "ece": 0.2179071110112772, + "n": 15 + }, + "latency": { + "n": 15, + "p50_s": 0.06412995798746124, + "p95_s": 0.07775642202468588 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 15, + "n_correct": 5, + "n_planned": 15, + "n_renormalized": 0, + "n_scorable": 15, + "n_valid": 15, + "operational_success": 1.0, + "ordinal_mae": 1.102096986624212, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "tool_selection": { + "accuracy": 1.0, + "brier_mean": 0.00027882058159227585, + "calibration_n": 12, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9859023175222424, + "n": 12 + } + ], + "ece": 0.014097682477757556, + "n": 12 + }, + "latency": { + "n": 12, + "p50_s": 0.052782755985390395, + "p95_s": 0.05833391500636935 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 12, + "n_correct": 12, + "n_planned": 12, + "n_renormalized": 0, + "n_scorable": 12, + "n_valid": 12, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "tradeoff": { + "accuracy": 0.6666666666666666, + "brier_mean": 0.3172021465853196, + "calibration_n": 6, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.0, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.6392348025938888, + "n": 2 + }, + { + "accuracy": 1.0, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7449709949864798, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8562976654414707, + "n": 2 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9682766780586276, + "n": 1 + } + ], + "ece": 0.30877110020995474, + "n": 6 + }, + "latency": { + "n": 6, + "p50_s": 0.06587484749616124, + "p95_s": 0.07062355398375075 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 6, + "n_correct": 4, + "n_planned": 6, + "n_renormalized": 0, + "n_scorable": 6, + "n_valid": 6, + "operational_success": 1.0, + "ordinal_mae": null, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + }, + "trap": { + "accuracy": 0.875, + "brier_mean": 0.0928845979050508, + "calibration_n": 8, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.0, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": 0.4660607766073019, + "n": 1 + }, + { + "accuracy": null, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 1.0, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8527907640733415, + "n": 1 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9658182629839495, + "n": 6 + } + ], + "ece": 0.10229505432878294, + "n": 8 + }, + "latency": { + "n": 8, + "p50_s": 0.05460315546952188, + "p95_s": 0.055981464550131935 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 8, + "n_correct": 7, + "n_planned": 8, + "n_renormalized": 0, + "n_scorable": 8, + "n_valid": 8, + "operational_success": 1.0, + "ordinal_mae": 0.8643000081318148, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + } + }, + "price_per_1000_decisions_usd": 0.0, + "probability_sources": [ + "native" + ], + "schema_validity": 1.0, + "schema_validity_strict": 1.0, + "splits": { + "public": { + "accuracy": 0.8744588744588745, + "brier_mean": 0.17806609620099598, + "calibration_n": 231, + "cost_basis": [ + "zero_route_fee_compute_excluded" + ], + "coverage": 1.0, + "ece": { + "bins": [ + { + "accuracy": null, + "hi": 0.1, + "lo": 0.0, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.2, + "lo": 0.1, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": null, + "hi": 0.3, + "lo": 0.2, + "mean_confidence": null, + "n": 0 + }, + { + "accuracy": 0.4, + "hi": 0.4, + "lo": 0.3, + "mean_confidence": 0.3623595989308779, + "n": 10 + }, + { + "accuracy": 0.0, + "hi": 0.5, + "lo": 0.4, + "mean_confidence": 0.46124870941679735, + "n": 5 + }, + { + "accuracy": 0.8, + "hi": 0.6, + "lo": 0.5, + "mean_confidence": 0.5637253221582417, + "n": 10 + }, + { + "accuracy": 0.65, + "hi": 0.7, + "lo": 0.6, + "mean_confidence": 0.648800445448587, + "n": 20 + }, + { + "accuracy": 0.7391304347826086, + "hi": 0.8, + "lo": 0.7, + "mean_confidence": 0.7523100109863671, + "n": 23 + }, + { + "accuracy": 0.9117647058823529, + "hi": 0.9, + "lo": 0.8, + "mean_confidence": 0.8641129171311692, + "n": 34 + }, + { + "accuracy": 1.0, + "hi": 1.0, + "lo": 0.9, + "mean_confidence": 0.9627515382033693, + "n": 129 + } + ], + "ece": 0.051072415884039386, + "n": 231 + }, + "latency": { + "n": 231, + "p50_s": 0.054981209977995604, + "p95_s": 0.14865703746909276 + }, + "latency_failures": { + "n": 0, + "p50_s": null, + "p95_s": null + }, + "n_attempted": 231, + "n_correct": 202, + "n_planned": 231, + "n_renormalized": 0, + "n_scorable": 231, + "n_valid": 231, + "operational_success": 1.0, + "ordinal_mae": 0.26234367203481096, + "price_per_1000_decisions_usd": 0.0, + "schema_validity": 1.0, + "schema_validity_strict": 1.0 + } + }, + "version": "jevbench-v1" +} diff --git a/services/intern-decision-serve/intern-decision-serve.contract.md b/services/intern-decision-serve/intern-decision-serve.contract.md index a13819e..8997f43 100644 --- a/services/intern-decision-serve/intern-decision-serve.contract.md +++ b/services/intern-decision-serve/intern-decision-serve.contract.md @@ -32,6 +32,7 @@ Every POST takes and returns JSON and needs `Authorization: Bearer `. `GE | GET | `/health` | none | 200 `{status: "ok", model, vram_cap_gib, max_tokens, max_decisions, max_questions_per_call: 16, chunking, workloads: []}` | | POST | `/decide` | `{id, state, question, options[2..16], orderings?, workload?}` | 200 one decision result | | POST | `/decide/shared` | `{state, decisions: [{id, question, options, orderings?}], workload?}` | 200 `{results: [...], timing: {...}}`, results in request order | +| POST | `/v1/systemone` | `{state, model?, questions: {"": {type, instructions, criteria?}}, images? (rejected)}` | 200 the engine's own response (`answers`, `usage`, `model`) — see § POST /v1/systemone | `options` items are `{id, description}`. Validation is SemIf's, re-stated here because SemIf is gone. `id` and `question` are nonempty strings. `state` is a nonempty string, object or array, @@ -39,6 +40,49 @@ and must be finite JSON. There are 2..16 options, each with a string `id` and a `description`, and option ids are unique within a decision. Decision ids are unique within a request. A violation is a 422. +## POST /v1/systemone (Jev compatibility, added 0.1.1) + +The TypeSafe/Jev wire shape, served natively: the request goes **straight to the engine's own +`DecisionEngine.predict`** — the checkpoint's documented Jev format — and never through the semif +mapping below. The two surfaces use different prompts; routing one through the other would change +the answers. + +``` +request {"state": ..., "model": "", + "questions": {"": {"type": "noul"|"choice"|"score", "instructions": ..., "criteria": ...}}, + "images": } +response {"answers": {"": {"type": "noul", "noul": p, ...} + | {"type": "choice", "choice": label, "probabilities": {...}, ...} + | {"type": "score", "score": v, "probabilities": {...}, ...}}, + "usage": {...}, "model": {"name": ..., "revision": ...}} +``` + +- `model` is accepted with **any** value (Jev clients send `"jev-latest"`) and ignored. The + response `model` is a **string** naming the model actually serving and its pinned revision: + `"@"` (JevBench's runner hashes the value into its manifest; a dict is not + hashable and broke its manifest step in the 0.1.1 first run). +- The `answers` block is the engine's own response, unmodified: probabilities are the same + temperature-scaled numbers `/decide`'s `native` carries. `usage` is whatever the engine + reports (token counts); if it reports nothing, `{}`. Extra engine fields (`timing`, + `calibration`, `backend`) ride along — additive fields Jev clients ignore. +- **Limits, all enforced before the forward pass:** 1..16 questions per request (NO chunking — + in Jev semantics the questions of one call share one prompt and chunking would silently + change that); 422 with a clear message above 16. `images` present → 422 `images not + supported` (the vision tower is dropped, INV-7). Over `MAX_TOKENS` → 422, the model's own + pre-forward check. The same bearer token (401), the same single inference thread, the same + `MAX_QUEUE` (429), `MAX_BODY_BYTES` (413), VRAM cap with 503 `out_of_memory` + recovery. +- Per-question shape validation (type must be noul/choice/score; choice criteria an object; + score criteria a list/object; 1..16 options; nonempty state; unique field names) is the + engine's own `validate_request`; its `ValueError`s map to 422 `invalid_request` like anywhere + else. A `noul` question needs no `criteria`. +- **What is NOT verified:** this covers the subset of TypeSafe's API that JevBench's `typesafe` + adapter exercises (231 public items, 4 repeats, bench 2026-09-30). Other Jev request features + (batching semantics beyond one prompt, streaming, price headers, `images` serving) are not + implemented and not verified against the closed API. +- **Discovery:** `/health` lists the surface: `endpoints` names all three paths, and + `systemone` reports `{max_questions: 16, chunking: "none", images: "not supported", + max_tokens: }`. + ## Mapping onto the model (the seam) - **One call** is one `predict()` request: diff --git a/services/intern-decision-serve/pyproject.toml b/services/intern-decision-serve/pyproject.toml index 0f9e4b3..9797137 100644 --- a/services/intern-decision-serve/pyproject.toml +++ b/services/intern-decision-serve/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "intern-decision-serve" -version = "0.1.0" +version = "0.1.1" description = "Intern-Decision-4B (its own inference.py) behind semif-serve's HTTP surface" requires-python = ">=3.12" dependencies = [ diff --git a/services/intern-decision-serve/src/intern_decision_serve/app.py b/services/intern-decision-serve/src/intern_decision_serve/app.py index 64d58bf..5406679 100644 --- a/services/intern-decision-serve/src/intern_decision_serve/app.py +++ b/services/intern-decision-serve/src/intern_decision_serve/app.py @@ -68,6 +68,19 @@ class SharedBody(BaseModel): workload: str | None = None +class SystemOneBody(BaseModel): + """The Jev request. `model` is accepted with any value and ignored (Jev clients send + 'jev-latest'); `images` is kept only to refuse it with a clear 422. Extra keys are dropped: + only state+questions reach predict, exactly like the bench's 60-line wrapper.""" + model_config = ConfigDict(extra="allow") + state: State + questions: dict[str, dict[str, Any]] + + @property + def images_present(self) -> bool: + return "images" in (self.model_extra or {}) + + class ApiError(Exception): def __init__(self, status: int, code: str, message: str): super().__init__(message) @@ -322,10 +335,11 @@ def create_app(settings: Settings, engine: Any, executor: ThreadPoolExecutor | N "inference_seconds": inference_ms / 1000} return out, timing - async def score(state: State, decisions: list[Decision], waves: list[list[Slot]]): - """Run one request's calls on the inference thread; map their failures to contract codes.""" + async def on_inference(fn): + """Run fn on the ONE inference thread (INV-2) and map failures to contract codes (INV-4): + the shared dispatch+mapping for every surface, semif and systemone alike.""" try: - return await asyncio.get_running_loop().run_in_executor(executor, run, state, decisions, waves) + return await asyncio.get_running_loop().run_in_executor(executor, fn) except ValueError as exc: # the model's own validation, token limit, ... raise ApiError(422, "invalid_request", str(exc)) from exc except OutOfMemory as exc: @@ -333,11 +347,17 @@ def create_app(settings: Settings, engine: Any, executor: ThreadPoolExecutor | N except Exception as exc: # noqa: BLE001 — any other failure, building the response included raise ApiError(500, "scoring_failed", f"{type(exc).__name__}: {exc}") from exc + async def score(state: State, decisions: list[Decision], waves: list[list[Slot]]): + return await on_inference(lambda: run(state, decisions, waves)) + @app.get("/health") async def health(): return {"status": "ok", "model": engine.health(), "vram_cap_gib": settings.vram_cap_gib, "max_tokens": settings.max_tokens, "max_decisions": settings.max_decisions, - "max_questions_per_call": MAX_QUESTIONS_PER_CALL, "chunking": CHUNKING, "workloads": []} + "max_questions_per_call": MAX_QUESTIONS_PER_CALL, "chunking": CHUNKING, "workloads": [], + "endpoints": ["/decide", "/decide/shared", "/v1/systemone"], + "systemone": {"max_questions": MAX_QUESTIONS_PER_CALL, "chunking": "none", + "images": "not supported", "max_tokens": settings.max_tokens}} @app.post("/decide") async def decide(request: Request): @@ -363,4 +383,43 @@ def create_app(settings: Settings, engine: Any, executor: ThreadPoolExecutor | N finally: leave() + @app.post("/v1/systemone") + async def systemone(request: Request): + """Jev wire shape. Straight passthrough to DecisionEngine.predict — NEVER the semif + mapping (a different prompt would change the answers). Contract § POST /v1/systemone.""" + admit() # before the body is read + try: + payload = await parse(request, SystemOneBody) + if payload.images_present: + raise ApiError(422, "invalid_request", "images not supported (the vision tower is " + "removed to fit the GPU 1 budget, INV-7)") + questions = payload.questions + if not 1 <= len(questions) <= MAX_QUESTIONS_PER_CALL: + raise ApiError(422, "invalid_request", + f"this request has {len(questions)} questions; the limit is " + f"1..{MAX_QUESTIONS_PER_CALL} in one call — questions of one call " + "share one prompt, so they are never chunked") + response = await run_systemone({"state": payload.state, "questions": questions}) + meta = engine.metadata + return {"answers": response["answers"], "usage": response["usage"], + "model": f"{meta.get('name')}@{meta.get('revision')}", # string: see contract + **{k: v for k, v in response.items() if k not in ("answers", "usage", "model")}} + finally: + leave() + + async def run_systemone(call: dict) -> dict: + """One native call on the inference thread, under the same lock and mapping as the semif + surface (on_inference). The engine's own validate_request enforces the per-question Jev + rules before any GPU work; its ValueError is a 422 like the token-limit check.""" + def one(): + with inference: + response, _sha = engine.predict(call) + usage = response.get("usage") + response["usage"] = usage if isinstance(usage, dict) else {} # contract: {} not absent + return response + response = await on_inference(one) + if not isinstance(response.get("answers"), dict): + raise ApiError(500, "scoring_failed", "the engine returned no answers object") + return response + return app diff --git a/services/intern-decision-serve/tests/fake_engine.py b/services/intern-decision-serve/tests/fake_engine.py index 1119a06..232ebd7 100644 --- a/services/intern-decision-serve/tests/fake_engine.py +++ b/services/intern-decision-serve/tests/fake_engine.py @@ -22,6 +22,32 @@ def score_by_description(field: str, question: dict) -> list[float]: return [len(d) + (0.5 if i == 0 else 0.0) for i, d in enumerate(descs)] +def answer_for(field: str, question: dict, scorer) -> dict: + """One Jev answer in the shape DecisionEngine.predict returns, for any of the three types.""" + kind = question["type"] + if kind == "noul": + probs = {"yes": 0.75, "no": 0.25} + return {"type": "noul", "probabilities": probs, "confidence": 0.75, "noul": 0.75, + "source": "local", "decision": "yes"} + criteria = question["criteria"] + if isinstance(criteria, dict): + keys = list(criteria) + descriptions = list(criteria.values()) + else: # score: a list of levels + keys = [str(i) for i in range(len(criteria))] + descriptions = [str(level) for level in criteria] + probs = dict(zip(keys, softmax(scorer(field, {**question, "criteria": dict(zip(keys, descriptions))})))) + best = min(keys, key=lambda k: (-probs[k], k)) + answer = {"type": kind, "probabilities": probs, "confidence": probs[best], "source": "local", "decision": best} + if kind == "choice": + answer["choice"] = best + else: + answer["score"] = sum(float(k) * p for k, p in probs.items()) + answer["legend"] = {k: (criteria[i] if isinstance(criteria, list) else v) + for i, (k, v) in enumerate(zip(keys, criteria.values() if isinstance(criteria, dict) else criteria))} + return answer + + class FakeEngine: def __init__(self, scorer=score_by_description, tokens_per_question: int = 100): self.scorer = scorer @@ -35,13 +61,8 @@ class FakeEngine: def predict(self, request: dict) -> tuple[dict, str]: self.calls.append(copy.deepcopy(request)) - answers = {} - for field, question in request["questions"].items(): - ids = list(question["criteria"]) - probs = dict(zip(ids, softmax(self.scorer(field, question)))) - best = min(ids, key=lambda i: (-probs[i], i)) - answers[field] = {"type": "choice", "probabilities": probs, "confidence": probs[best], - "choice": best, "source": "local", "decision": best} + answers = {field: answer_for(field, question, self.scorer) + for field, question in request["questions"].items()} response = {"answers": answers, "usage": {"input_tokens": self.tokens_per_question * len(answers), "output_tokens": len(answers), "decision_count": len(answers)}, diff --git a/services/intern-decision-serve/tests/test_systemone.py b/services/intern-decision-serve/tests/test_systemone.py new file mode 100644 index 0000000..c6fd373 --- /dev/null +++ b/services/intern-decision-serve/tests/test_systemone.py @@ -0,0 +1,224 @@ +"""POST /v1/systemone: Jev wire shape, straight passthrough to DecisionEngine.predict. +Contract: intern-decision-serve.contract.md § POST /v1/systemone""" +import threading +import time +from concurrent.futures import ThreadPoolExecutor + +import pytest +from fastapi.testclient import TestClient + +from fake_engine import FakeEngine +from intern_decision_serve.app import create_app +from intern_decision_serve.config import Settings +from intern_decision_serve.errors import OutOfMemory + +TOKEN = "t" * 40 +AUTH = {"Authorization": f"Bearer {TOKEN}"} + +CHOICE = {"type": "choice", "instructions": "Did it pass?", + "criteria": {"yes": "It passed.", "no": "It did not pass at all."}} +NOUL = {"type": "noul", "instructions": "Is the deploy healthy?"} +SCORE = {"type": "score", "instructions": "How risky?", "criteria": ["low", "medium", "high"]} + + +def make_client(engine=None, **overrides): + return TestClient(create_app(Settings(api_token=TOKEN, **overrides), engine or FakeEngine())) + + +def body(**over): + b = {"state": "The deploy finished at 14:00.", "model": "jev-latest", "questions": {"decision": CHOICE}} + b.update(over) + return b + + +# ---------------------------------------------------------------- happy paths + +def test_choice_request_is_passed_straight_through_and_the_engine_answer_is_returned(): + engine = FakeEngine() + response = make_client(engine).post("/v1/systemone", json=body(), headers=AUTH) + assert response.status_code == 200 + native, _ = FakeEngine().predict(engine.calls[0]) + # straight through: only state+questions reach predict, model is not forwarded, the question + # dict is untouched (no semif mapping: no A=id:description conversion, no field rename) + assert engine.calls == [{"state": "The deploy finished at 14:00.", "questions": {"decision": CHOICE}}] + out = response.json() + assert out["answers"] == native["answers"] + assert out["answers"]["decision"]["type"] == "choice" + assert out["answers"]["decision"]["choice"] in ("yes", "no") + assert out["usage"] == native["usage"] + # a STRING: JevBench's runner hashes the value into its manifest (a dict broke it on the + # 0.1.1 first run) and real clients compare it; the string names the real model and revision + assert out["model"] == "Intern-Decision-4B@" + "0" * 40 + + +def test_noul_question_needs_no_criteria_and_answers_with_a_probability(): + engine = FakeEngine() + response = make_client(engine).post("/v1/systemone", json=body(questions={"q": NOUL}), headers=AUTH) + assert response.status_code == 200 + assert engine.calls == [{"state": "The deploy finished at 14:00.", "questions": {"q": NOUL}}] + answer = response.json()["answers"]["q"] + assert answer["type"] == "noul" and answer["noul"] == 0.75 + + +def test_score_question_with_a_list_of_levels_returns_probabilities_over_the_levels(): + engine = FakeEngine() + response = make_client(engine).post("/v1/systemone", json=body(questions={"q": SCORE}), headers=AUTH) + assert response.status_code == 200 + answer = response.json()["answers"]["q"] + assert answer["type"] == "score" + assert set(answer["probabilities"]) == {"0", "1", "2"} + assert abs(sum(answer["probabilities"].values()) - 1.0) < 1e-9 + + +def test_any_number_of_questions_up_to_16_is_ONE_call_so_they_share_one_prompt(): + engine = FakeEngine() + questions = {f"q{i}": NOUL for i in range(16)} + response = make_client(engine).post("/v1/systemone", json=body(questions=questions), headers=AUTH) + assert response.status_code == 200 + assert len(engine.calls) == 1 and len(engine.calls[0]["questions"]) == 16 + + +def test_the_model_field_is_accepted_with_any_value_and_ignored(): + engine = FakeEngine() + for model in ("jev-latest", "anything-else", 7, None): + response = make_client(engine).post("/v1/systemone", json=body(model=model), headers=AUTH) + assert response.status_code == 200 + + +class NoUsageEngine(FakeEngine): + def predict(self, request): + response, sha = super().predict(request) + response.pop("usage") + return response, sha + + +def test_an_engine_that_reports_no_usage_yields_an_empty_usage_object(): + response = make_client(NoUsageEngine()).post("/v1/systemone", json=body(), headers=AUTH) + assert response.status_code == 200 + assert response.json()["usage"] == {} + + +# ---------------------------------------------------------------- refusals + +@pytest.mark.parametrize("headers", [{}, {"Authorization": "Bearer wrong"}, {"Authorization": TOKEN}]) +def test_without_the_right_bearer_a_systemone_post_is_401_and_never_reaches_the_engine(headers): + engine = FakeEngine() + response = make_client(engine).post("/v1/systemone", json=body(), headers=headers) + assert response.status_code == 401 + assert response.json()["error"]["code"] == "unauthorized" + assert engine.calls == [] + + +@pytest.mark.parametrize("images", [["a.png"], [], "a.png"]) +def test_images_any_value_at_all_is_422_before_the_engine_runs(images): + engine = FakeEngine() + response = make_client(engine).post("/v1/systemone", json=body(images=images), headers=AUTH) + assert response.status_code == 422 + assert response.json()["error"]["code"] == "invalid_request" + assert "images not supported" in response.json()["error"]["message"] + assert engine.calls == [] + + +def test_17_questions_is_422_not_a_chunked_2_call_request(): + engine = FakeEngine() + questions = {f"q{i}": NOUL for i in range(17)} + response = make_client(engine).post("/v1/systemone", json=body(questions=questions), headers=AUTH) + assert response.status_code == 422 + assert "16" in response.json()["error"]["message"] + assert engine.calls == [] + + +def test_zero_questions_is_422(): + response = make_client().post("/v1/systemone", json=body(questions={}), headers=AUTH) + assert response.status_code == 422 + + +def test_a_body_that_is_not_json_or_has_no_questions_is_422(): + client = make_client() + assert client.post("/v1/systemone", content=b"{nope", headers={**AUTH, "content-type": "application/json"} + ).status_code == 422 + assert client.post("/v1/systemone", json={"state": "s"}, headers=AUTH).status_code == 422 + + +class TokenLimitEngine(FakeEngine): + """Stands in for the model's own pre-forward check: predict raises ValueError, never a tensor.""" + def predict(self, request): + self.calls.append(request) + raise ValueError("Example has 7169 tokens, above 7168; truncation is forbidden") + + +def test_over_max_tokens_is_422_from_the_models_own_before_the_forward_check(): + response = make_client(TokenLimitEngine(), max_tokens=7168).post("/v1/systemone", json=body(), headers=AUTH) + assert response.status_code == 422 + assert "7169" in response.json()["error"]["message"] + + +# ---------------------------------------------------------------- queue and memory + +class SlowEngine(FakeEngine): + def __init__(self): + super().__init__() + self.entered, self.release = threading.Event(), threading.Event() + + def predict(self, request): + self.entered.set() + assert self.release.wait(5) + return super().predict(request) + + +def test_more_than_max_queue_systemone_posts_get_429_busy(): + engine = SlowEngine() + with make_client(engine, max_queue=1) as client, ThreadPoolExecutor(2) as pool: + held = pool.submit(client.post, "/v1/systemone", json=body(), headers=AUTH) + assert engine.entered.wait(5) + time.sleep(0.2) + extra = client.post("/v1/systemone", json=body(), headers=AUTH) + assert extra.status_code == 429 and extra.json()["error"]["code"] == "busy" + engine.release.set() + assert held.result().status_code == 200 + + +class OomOnceEngine(FakeEngine): + def __init__(self): + super().__init__() + self.raised = False + + def predict(self, request): + if not self.raised: + self.raised, _ = True, self.calls.append(request) + raise OutOfMemory("CUDA out of memory.") + return super().predict(request) + + +def test_an_oom_is_503_with_the_contract_envelope_and_the_next_request_succeeds(): + engine = OomOnceEngine() + client = make_client(engine) + first = client.post("/v1/systemone", json=body(), headers=AUTH) + assert first.status_code == 503 and first.json()["error"]["code"] == "out_of_memory" + second = client.post("/v1/systemone", json=body(), headers=AUTH) + assert second.status_code == 200 + + +def test_systemone_runs_on_the_same_single_inference_thread_as_decide(): + seen = [] + + class ThreadSpy(FakeEngine): + def predict(self, request): + seen.append(threading.current_thread().name) + return super().predict(request) + + client = make_client(ThreadSpy()) + client.post("/v1/systemone", json=body(), headers=AUTH) + client.post("/decide", json={"id": "r", "state": "s", "question": "q?", "options": + [{"id": "a", "description": "x"}, {"id": "b", "description": "yy"}]}, + headers=AUTH) + assert len(set(seen)) == 1 and seen[0].startswith("inference") + + +# ---------------------------------------------------------------- /health + +def test_health_advertises_the_systemone_surface_and_its_limits(): + out = make_client(max_tokens=7168).get("/health").json() + assert set(out["endpoints"]) == {"/decide", "/decide/shared", "/v1/systemone"} + assert out["systemone"] == {"max_questions": 16, "chunking": "none", + "images": "not supported", "max_tokens": 7168} diff --git a/services/intern-decision-serve/uv.lock b/services/intern-decision-serve/uv.lock index 704eb94..104ebaa 100644 --- a/services/intern-decision-serve/uv.lock +++ b/services/intern-decision-serve/uv.lock @@ -284,7 +284,7 @@ wheels = [ [[package]] name = "intern-decision-serve" -version = "0.1.0" +version = "0.1.1" source = { editable = "." } dependencies = [ { name = "fastapi" },