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
22 lines
221 B
JSON
22 lines
221 B
JSON
{
|
|
"rule": [
|
|
[
|
|
"S1",
|
|
">=",
|
|
0.61185
|
|
],
|
|
[
|
|
"S6",
|
|
"<=",
|
|
0.16025
|
|
]
|
|
],
|
|
"test": {
|
|
"accepted": 5,
|
|
"label2": 2,
|
|
"label1plus": 5,
|
|
"precision2": 0.4,
|
|
"precision1plus": 1.0,
|
|
"recall2": 0.4
|
|
}
|
|
} |