chore: snapshot in-progress question-gen work before preflight fixes

This commit is contained in:
2026-07-16 04:12:21 -04:00
parent 11a5545f57
commit a4c429b247
39 changed files with 738 additions and 283 deletions
+12 -4
View File
@@ -14,10 +14,18 @@ video_split:
val_wrong_min: 20 # validation 池最少错题数(McNemar 检验功效阈 ≈ 20,低于则信号不足)
val_ratio: 0.3 # validation 占 trainval 视频组总数的比例
seed: 7 # 贪心选择器预洗牌 + 视频组题级切分种子(打破等增益 / 等槽平局)
floor_k: # 各高信号 task_type 的 T2 defect 下限(硬约束)—— 占位,标定后替换
Counting Problem: 3 # 取克制值 min(诊断可用 defect 数, 3),避免把信号全抽进 trainval
Object Reasoning: 3
Action Reasoning: 3
floor_k: # 各 task_type 的 T2 defect 下限(硬约束)—— 均衡覆盖全 11 类,标定于 1cb1c203 真实 T2 分布
Object Reasoning: 5 # T2=25
Information Synopsis: 5 # T2=13
Action Reasoning: 5 # T2=11
Counting Problem: 5 # T2=10
Temporal Reasoning: 2 # T2=5
Object Recognition: 2 # T2=5
Action Recognition: 2 # T2=5
Attribute Perception: 1 # T2=3
Temporal Perception: 1 # T2=2
OCR Problems: 1 # T2=2
Spatial Perception: 1 # T2=1
diag: # 诊断口径指纹三分量(隔离不同诊断配置的信号,参与主键)
prompt_version: diagnose_v1 # 诊断 prompt 版本标识(换 prompt 即换指纹,旧记录不被覆盖)