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
50 lines
385 B
JSON
50 lines
385 B
JSON
{
|
|
"criteria": [
|
|
false,
|
|
false,
|
|
false,
|
|
false
|
|
],
|
|
"V1": [
|
|
4,
|
|
2,
|
|
0,
|
|
0.5
|
|
],
|
|
"V2": [
|
|
2,
|
|
2,
|
|
1,
|
|
1.0
|
|
],
|
|
"small_G3": [
|
|
11,
|
|
3,
|
|
0,
|
|
0.2727272727272727
|
|
],
|
|
"small_G2": [
|
|
3,
|
|
1,
|
|
0,
|
|
0.3333333333333333
|
|
],
|
|
"V3": [
|
|
10,
|
|
3,
|
|
6,
|
|
0.6
|
|
],
|
|
"pooled_G3": [
|
|
17,
|
|
8,
|
|
1,
|
|
0.47058823529411764
|
|
],
|
|
"pooled_G2": [
|
|
13,
|
|
9,
|
|
2,
|
|
0.6923076923076923
|
|
]
|
|
} |