BabyYarros: raw-surface scoring and a memorization check with both controls

2026-09-15 13:23:27 -07:00
parent 713e83dd5e
commit efb734586b
3 changed files with 96 additions and 11 deletions
@@ -92,7 +92,9 @@ with out.open("w", encoding="utf-8") as fh:
            hit = sum(1 for k in kws if k[:5] in para.lower())
            w = len(para.split())
            fh.write(json.dumps({"format": a.arm, "id": b["id"], "beat": b["beat"], "seed": seed,
-                                 "prompt": a.user_prefix + b["beat"], "paragraph": para,
+                                 "prompt": a.user_prefix + b["beat"], "paragraph": para, "raw": raw,
+                                 "raw_words": len(raw.split()),
+                                 "raw_blocks": len(STOP.split(raw)),
                                 "ran_on": m is None, "words": w,
                                 "in_band": 90 <= w <= 140,
                                 "beat_keywords": kws, "keyword_hits": hit}) + "\n")