{ "report": { "scenario": "wyrd-scene-vigil", "cases": 6, "runs": 3, "latency_per_turn": { "e2e_ms": { "median": 133.2, "min": 130.8, "max": 155.9, "n": 18 }, "srv_ms": { "median": 101.1, "min": 100.4, "max": 101.8, "n": 18 } }, "by_decision": { "place": { "evidence": { "n": 6, "correct": 4, "acc": 0.667 }, "blind_null": { "n": 6, "correct": 4, "acc": 0.667 }, "controls": { "n": 2, "correct": 1, "acc": 0.5 }, "non_controls": { "n": 4, "correct": 3, "acc": 0.75 }, "by_label": { "holds": { "evidence": { "n": 4, "correct": 4, "acc": 1.0 }, "blind_null": { "n": 4, "correct": 4, "acc": 1.0 } }, "moved": { "evidence": { "n": 2, "correct": 0, "acc": 0.0 }, "blind_null": { "n": 2, "correct": 0, "acc": 0.0 } } }, "unanimous": { "n": 5, "correct": 4, "acc": 0.8 }, "split": { "n": 1, "correct": 0, "acc": 0.0 }, "egregious": 0, "blind_egregious": 0, "misses": [ "v-step-out: said holds (p=0.731, agree=1.0) want moved", "v-to-pub: said holds (p=0.637, agree=0.5) want moved" ] }, "exit": { "evidence": { "n": 6, "correct": 5, "acc": 0.833 }, "blind_null": { "n": 6, "correct": 5, "acc": 0.833 }, "controls": { "n": 2, "correct": 2, "acc": 1.0 }, "non_controls": { "n": 4, "correct": 3, "acc": 0.75 }, "by_label": { "outside": { "evidence": { "n": 1, "correct": 1, "acc": 1.0 }, "blind_null": { "n": 1, "correct": 0, "acc": 0.0 } }, "stay": { "evidence": { "n": 5, "correct": 4, "acc": 0.8 }, "blind_null": { "n": 5, "correct": 5, "acc": 1.0 } } }, "unanimous": { "n": 6, "correct": 5, "acc": 0.833 }, "split": { "n": 0, "correct": 0, "acc": null }, "egregious": 0, "blind_egregious": 0, "misses": [ "v-to-pub: said outside (p=0.86, agree=1.0) want stay" ] }, "place2": { "evidence": { "n": 6, "correct": 6, "acc": 1.0 }, "blind_null": { "n": 6, "correct": 4, "acc": 0.667 }, "controls": { "n": 2, "correct": 2, "acc": 1.0 }, "non_controls": { "n": 4, "correct": 4, "acc": 1.0 }, "by_label": { "elsewhere": { "evidence": { "n": 2, "correct": 2, "acc": 1.0 }, "blind_null": { "n": 2, "correct": 0, "acc": 0.0 } }, "same": { "evidence": { "n": 4, "correct": 4, "acc": 1.0 }, "blind_null": { "n": 4, "correct": 4, "acc": 1.0 } } }, "unanimous": { "n": 6, "correct": 6, "acc": 1.0 }, "split": { "n": 0, "correct": 0, "acc": null }, "egregious": 0, "blind_egregious": 0, "misses": [] }, "exit2": { "evidence": { "n": 6, "correct": 6, "acc": 1.0 }, "blind_null": { "n": 6, "correct": 5, "acc": 0.833 }, "controls": { "n": 2, "correct": 2, "acc": 1.0 }, "non_controls": { "n": 4, "correct": 4, "acc": 1.0 }, "by_label": { "outside": { "evidence": { "n": 1, "correct": 1, "acc": 1.0 }, "blind_null": { "n": 1, "correct": 0, "acc": 0.0 } }, "stay": { "evidence": { "n": 5, "correct": 5, "acc": 1.0 }, "blind_null": { "n": 5, "correct": 5, "acc": 1.0 } } }, "unanimous": { "n": 6, "correct": 6, "acc": 1.0 }, "split": { "n": 0, "correct": 0, "acc": null }, "egregious": 0, "blind_egregious": 0, "misses": [] } } }, "rows": [ { "case": "v-talk", "tag": "control", "decision": "place", "label": "holds", "top": "holds", "p_top": 0.999, "agreement": 1.0, "probs": { "moved": 0.001, "holds": 0.999 }, "blind_top": "holds", "input_tokens": 266, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-talk", "tag": "control", "decision": "exit", "label": "stay", "top": "stay", "p_top": 0.86, "agreement": 1.0, "probs": { "stay": 0.86, "outside": 0.14 }, "blind_top": "stay", "input_tokens": 296, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-talk", "tag": "control", "decision": "place2", "label": "same", "top": "same", "p_top": 0.999, "agreement": 1.0, "probs": { "same": 0.999, "elsewhere": 0.001 }, "blind_top": "same", "input_tokens": 276, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-talk", "tag": "control", "decision": "exit2", "label": "stay", "top": "stay", "p_top": 1.0, "agreement": 1.0, "probs": { "stay": 1.0, "outside": 0.0 }, "blind_top": "stay", "input_tokens": 308, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-step-out", "tag": "control", "decision": "place", "label": "moved", "top": "holds", "p_top": 0.731, "agreement": 1.0, "probs": { "moved": 0.269, "holds": 0.731 }, "blind_top": "holds", "input_tokens": 262, "ok": false, "blind_ok": false, "egregious": false, "blind_egregious": false }, { "case": "v-step-out", "tag": "control", "decision": "exit", "label": "outside", "top": "outside", "p_top": 0.998, "agreement": 1.0, "probs": { "stay": 0.002, "outside": 0.998 }, "blind_top": "stay", "input_tokens": 292, "ok": true, "blind_ok": false, "egregious": false, "blind_egregious": false }, { "case": "v-step-out", "tag": "control", "decision": "place2", "label": "elsewhere", "top": "elsewhere", "p_top": 0.997, "agreement": 1.0, "probs": { "same": 0.003, "elsewhere": 0.997 }, "blind_top": "same", "input_tokens": 272, "ok": true, "blind_ok": false, "egregious": false, "blind_egregious": false }, { "case": "v-step-out", "tag": "control", "decision": "exit2", "label": "outside", "top": "outside", "p_top": 0.835, "agreement": 1.0, "probs": { "stay": 0.165, "outside": 0.835 }, "blind_top": "stay", "input_tokens": 304, "ok": true, "blind_ok": false, "egregious": false, "blind_egregious": false }, { "case": "v-plan-pub", "tag": "case", "decision": "place", "label": "holds", "top": "holds", "p_top": 0.999, "agreement": 1.0, "probs": { "moved": 0.001, "holds": 0.999 }, "blind_top": "holds", "input_tokens": 267, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-plan-pub", "tag": "case", "decision": "exit", "label": "stay", "top": "stay", "p_top": 0.844, "agreement": 1.0, "probs": { "stay": 0.844, "outside": 0.156 }, "blind_top": "stay", "input_tokens": 297, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-plan-pub", "tag": "case", "decision": "place2", "label": "same", "top": "same", "p_top": 0.986, "agreement": 1.0, "probs": { "same": 0.986, "elsewhere": 0.014 }, "blind_top": "same", "input_tokens": 277, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-plan-pub", "tag": "case", "decision": "exit2", "label": "stay", "top": "stay", "p_top": 1.0, "agreement": 1.0, "probs": { "stay": 1.0, "outside": 0.0 }, "blind_top": "stay", "input_tokens": 309, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-to-pub", "tag": "case", "decision": "place", "label": "moved", "top": "holds", "p_top": 0.637, "agreement": 0.5, "probs": { "moved": 0.363, "holds": 0.637 }, "blind_top": "holds", "input_tokens": 271, "ok": false, "blind_ok": false, "egregious": false, "blind_egregious": false }, { "case": "v-to-pub", "tag": "case", "decision": "exit", "label": "stay", "top": "outside", "p_top": 0.86, "agreement": 1.0, "probs": { "stay": 0.14, "outside": 0.86 }, "blind_top": "stay", "input_tokens": 301, "ok": false, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-to-pub", "tag": "case", "decision": "place2", "label": "elsewhere", "top": "elsewhere", "p_top": 0.999, "agreement": 1.0, "probs": { "same": 0.001, "elsewhere": 0.999 }, "blind_top": "same", "input_tokens": 281, "ok": true, "blind_ok": false, "egregious": false, "blind_egregious": false }, { "case": "v-to-pub", "tag": "case", "decision": "exit2", "label": "stay", "top": "stay", "p_top": 0.943, "agreement": 1.0, "probs": { "stay": 0.943, "outside": 0.057 }, "blind_top": "stay", "input_tokens": 313, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-vision", "tag": "case", "decision": "place", "label": "holds", "top": "holds", "p_top": 0.999, "agreement": 1.0, "probs": { "moved": 0.001, "holds": 0.999 }, "blind_top": "holds", "input_tokens": 269, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-vision", "tag": "case", "decision": "exit", "label": "stay", "top": "stay", "p_top": 0.881, "agreement": 1.0, "probs": { "stay": 0.881, "outside": 0.119 }, "blind_top": "stay", "input_tokens": 299, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-vision", "tag": "case", "decision": "place2", "label": "same", "top": "same", "p_top": 0.991, "agreement": 1.0, "probs": { "same": 0.991, "elsewhere": 0.009 }, "blind_top": "same", "input_tokens": 279, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-vision", "tag": "case", "decision": "exit2", "label": "stay", "top": "stay", "p_top": 1.0, "agreement": 1.0, "probs": { "stay": 1.0, "outside": 0.0 }, "blind_top": "stay", "input_tokens": 311, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-demon-enters", "tag": "case", "decision": "place", "label": "holds", "top": "holds", "p_top": 0.994, "agreement": 1.0, "probs": { "moved": 0.006, "holds": 0.994 }, "blind_top": "holds", "input_tokens": 258, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-demon-enters", "tag": "case", "decision": "exit", "label": "stay", "top": "stay", "p_top": 0.86, "agreement": 1.0, "probs": { "stay": 0.86, "outside": 0.14 }, "blind_top": "stay", "input_tokens": 288, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-demon-enters", "tag": "case", "decision": "place2", "label": "same", "top": "same", "p_top": 0.993, "agreement": 1.0, "probs": { "same": 0.993, "elsewhere": 0.007 }, "blind_top": "same", "input_tokens": 268, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false }, { "case": "v-demon-enters", "tag": "case", "decision": "exit2", "label": "stay", "top": "stay", "p_top": 0.999, "agreement": 1.0, "probs": { "stay": 0.999, "outside": 0.001 }, "blind_top": "stay", "input_tokens": 300, "ok": true, "blind_ok": true, "egregious": false, "blind_egregious": false } ] }