Auto-sync: 2026-06-29 01:53:54
Browse files- results/README.md +11 -2
results/README.md
CHANGED
|
@@ -46,6 +46,9 @@ Use these summaries for the current paper tables:
|
|
| 46 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_noopbonus0p03_srcprog0p75_summary.md`,
|
| 47 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_srcprogbonus0p03_summary.md`,
|
| 48 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_srcprogbonus0p05_summary.md`,
|
|
|
|
|
|
|
|
|
|
| 49 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_fieldsoftmax_grid_safe_margin0p20_summary.md`,
|
| 50 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_fieldsoftmax_grid_safe_margin0p10_noopbonus0p03_summary.md`,
|
| 51 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_policy_anchor_scale0p35_safe_noexpert_summary.md`,
|
|
@@ -98,9 +101,9 @@ Completed deployment-clean diagnostics:
|
|
| 98 |
|
| 99 |
Completed residual transport jobs:
|
| 100 |
|
| 101 |
-
Last checked: `2026-06-29
|
| 102 |
completed after passing CPU/unit smokes, and the paper table/paired analysis now
|
| 103 |
-
include
|
| 104 |
|
| 105 |
- Code supports `--retrieval-residual-scale`, defaulting to `1.0` so the
|
| 106 |
completed 32.12% result is unchanged.
|
|
@@ -217,6 +220,12 @@ include both threshold gates and continuous train-source progress priors.
|
|
| 217 |
no-op prior. Bonus `0.03` ties the current best at 35.25%, while bonus `0.05`
|
| 218 |
reaches 35.13%. Summary jobs `14894676`/`14894677` completed; rebuild job
|
| 219 |
`14894678` was queued after them.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
- Job `14869627` completed the CPU Apptainer smoke for the residual scale-grid
|
| 221 |
selector: selected index `3` and returned action `0.20` on the toy ray-search
|
| 222 |
case, validating candidate expansion before rollout.
|
|
|
|
| 46 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_noopbonus0p03_srcprog0p75_summary.md`,
|
| 47 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_srcprogbonus0p03_summary.md`,
|
| 48 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_srcprogbonus0p05_summary.md`,
|
| 49 |
+
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_srcscorebonus0p015_summary.md`,
|
| 50 |
+
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_srcscorebonus0p02_summary.md`,
|
| 51 |
+
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_srcscorebonus0p025_summary.md`,
|
| 52 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_fieldsoftmax_grid_safe_margin0p20_summary.md`,
|
| 53 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_fieldsoftmax_grid_safe_margin0p10_noopbonus0p03_summary.md`,
|
| 54 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_policy_anchor_scale0p35_safe_noexpert_summary.md`,
|
|
|
|
| 101 |
|
| 102 |
Completed residual transport jobs:
|
| 103 |
|
| 104 |
+
Last checked: `2026-06-29 05:54 UTC`. The source-score bonus-prior batch
|
| 105 |
completed after passing CPU/unit smokes, and the paper table/paired analysis now
|
| 106 |
+
include progress and reward-score train-outcome priors.
|
| 107 |
|
| 108 |
- Code supports `--retrieval-residual-scale`, defaulting to `1.0` so the
|
| 109 |
completed 32.12% result is unchanged.
|
|
|
|
| 220 |
no-op prior. Bonus `0.03` ties the current best at 35.25%, while bonus `0.05`
|
| 221 |
reaches 35.13%. Summary jobs `14894676`/`14894677` completed; rebuild job
|
| 222 |
`14894678` was queued after them.
|
| 223 |
+
- Jobs `14897121`/`14897122` completed unit and CPU rollout smokes for the
|
| 224 |
+
train-source reward-score bonus path.
|
| 225 |
+
- Jobs `14897123`/`14897124`/`14897125` completed source-score bonus arrays.
|
| 226 |
+
Bonuses `0.015` and `0.020` tie the current best at 35.25%, while bonus
|
| 227 |
+
`0.025` reaches 35.19%. Summary jobs `14897126`/`14897127`/`14897128` and
|
| 228 |
+
rebuild job `14897129` completed.
|
| 229 |
- Job `14869627` completed the CPU Apptainer smoke for the residual scale-grid
|
| 230 |
selector: selected index `3` and returned action `0.20` on the toy ray-search
|
| 231 |
case, validating candidate expansion before rollout.
|