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
12 lines
644 B
Plaintext
12 lines
644 B
Plaintext
embeddings.json: 838 chunks from 94 stories, seeds (11, 12, 13)
|
|
|
|
k sized>=5 median dom recurring coverage tight rec tight cov
|
|
----------------------------------------------------------------------
|
|
25 25 0.25 21 93% 9 29%
|
|
40 39 0.36 21 71% 5 9%
|
|
60 55 0.57 20 55% 3 2%
|
|
100 78 0.67 16 30% 0 0%
|
|
|
|
recurring = size>=5, stories>=4, dominant share<=40%; tight = coherence at or above this file's median cluster. Judge at k>=60. Wrote embeddings.measure.json
|
|
exit 0
|