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
18 lines
530 B
Plaintext
18 lines
530 B
Plaintext
co-association run k=50 seed=21
|
|
co-association run k=50 seed=22
|
|
co-association run k=60 seed=21
|
|
co-association run k=60 seed=22
|
|
co-association run k=70 seed=21
|
|
co-association run k=70 seed=22
|
|
co-association run k=80 seed=21
|
|
co-association run k=80 seed=22
|
|
co-association run k=90 seed=21
|
|
co-association run k=90 seed=22
|
|
co-association run k=100 seed=21
|
|
co-association run k=100 seed=22
|
|
dev: 40 clusters; prose cross-story baseline 0.5858; wrote signals-dev.json
|
|
|
|
real 2m49.256s
|
|
user 2m37.464s
|
|
sys 0m1.440s
|