JesseMarkowitzandClaude Opus 5
fa3769d0fe
Research toward building a content pack from a story corpus, kept on its own branch and independent of the game. Records the selection experiments against blind labels, and settles selection as gate G2 followed by a human review: review.py writes REVIEW.md and a review.json form, apply_review.py checks the filled form and writes situations.json for the next stage. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01C6UDQ9o6L6Ey173U7XVou6
9 lines
254 B
Plaintext
9 lines
254 B
Plaintext
V1: k=100 seed=15: 59 candidates, sampled 30
|
|
V2: k=40 seed=14: 32 candidates, sampled 30
|
|
V3: k=60 seed=16: 46 candidates, G2 accepts 13; growth stopped by gate 2, by cap 11
|
|
blind sheet: 73 clusters, 1600 lines
|
|
|
|
real 0m39.098s
|
|
user 0m37.786s
|
|
sys 0m1.160s
|