anhtld commited on
Commit
7bbb281
·
verified ·
1 Parent(s): 5aa4c25

Auto-sync: 2026-06-29 02:37:51

Browse files
scripts/build_paper_analysis.py CHANGED
@@ -195,6 +195,22 @@ METHODS = [
195
  "k4s040_safe_margin0p25_mean_by_type_srcscorebonus0p02_summary.json"
196
  ),
197
  ),
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
198
  MethodSpec(
199
  key="residual_k4_consensus_nooponly_noopbonus003",
200
  label="K4 mean-by-type tangent consensus, no-op-only residuals, no-op bonus 0.03",
 
195
  "k4s040_safe_margin0p25_mean_by_type_srcscorebonus0p02_summary.json"
196
  ),
197
  ),
198
+ MethodSpec(
199
+ key="residual_k4_consensus_grid035040045_noopbonus003",
200
+ label="K4 mean-by-type tangent consensus, scales 0.35/0.40/0.45, no-op bonus 0.03",
201
+ summary_path=(
202
+ "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_"
203
+ "k4_grid035040045_safe_margin0p20_mean_by_type_noopbonus0p03_summary.json"
204
+ ),
205
+ ),
206
+ MethodSpec(
207
+ key="residual_k4_consensus_grid035040045_srcscorebonus002",
208
+ label="K4 mean-by-type tangent consensus, scales 0.35/0.40/0.45, source-score bonus 0.02",
209
+ summary_path=(
210
+ "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_"
211
+ "k4_grid035040045_safe_margin0p20_mean_by_type_srcscorebonus0p02_summary.json"
212
+ ),
213
+ ),
214
  MethodSpec(
215
  key="residual_k4_consensus_nooponly_noopbonus003",
216
  label="K4 mean-by-type tangent consensus, no-op-only residuals, no-op bonus 0.03",
scripts/build_paper_table_status.py CHANGED
@@ -505,6 +505,26 @@ SPECS = [
505
  story_role="advantage-abstention margin fine sweep with measured train-source prior",
506
  pending_job="14897844/14897848",
507
  ),
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
508
  ResultSpec(
509
  key="retrieval_residual_k4_mean_nooponly_noopbonus003",
510
  label="K4 mean-by-type residual retrieval, scale 0.40, margin 0.20, no-op-only residuals, no-op bonus 0.03",
 
505
  story_role="advantage-abstention margin fine sweep with measured train-source prior",
506
  pending_job="14897844/14897848",
507
  ),
508
+ ResultSpec(
509
+ key="retrieval_residual_k4_mean_grid035040045_noopbonus003",
510
+ label="K4 mean-by-type residual retrieval, scales 0.35/0.40/0.45, margin 0.20, no-op bonus 0.03",
511
+ path="h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_grid035040045_safe_margin0p20_mean_by_type_noopbonus0p03_summary.json",
512
+ clean_deployment="yes",
513
+ same_state_proposals="no",
514
+ expert_proposal="no",
515
+ story_role="scale-grid diagnostic for sparse mean-consensus residual transport",
516
+ pending_job="14897988/14897990",
517
+ ),
518
+ ResultSpec(
519
+ key="retrieval_residual_k4_mean_grid035040045_srcscorebonus002",
520
+ label="K4 mean-by-type residual retrieval, scales 0.35/0.40/0.45, margin 0.20, source-score bonus 0.02",
521
+ path="h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_grid035040045_safe_margin0p20_mean_by_type_srcscorebonus0p02_summary.json",
522
+ clean_deployment="yes",
523
+ same_state_proposals="no",
524
+ expert_proposal="no",
525
+ story_role="scale-grid diagnostic for measured-prior mean-consensus residual transport",
526
+ pending_job="14897989/14897991",
527
+ ),
528
  ResultSpec(
529
  key="retrieval_residual_k4_mean_nooponly_noopbonus003",
530
  label="K4 mean-by-type residual retrieval, scale 0.40, margin 0.20, no-op-only residuals, no-op bonus 0.03",