Auto-sync: 2026-06-28 22:04:20 (part 2)
Browse files- results/README.md +16 -3
results/README.md
CHANGED
|
@@ -41,6 +41,8 @@ Use these summaries for the current paper tables:
|
|
| 41 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p35_safe_types_margin0p20_summary.md`,
|
| 42 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_knn2_scale0p40_safe_types_margin0p20_summary.md`,
|
| 43 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_summary.md`,
|
|
|
|
|
|
|
| 44 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_policy_anchor_scale0p35_safe_noexpert_summary.md`,
|
| 45 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p35_type_success010_summary.md`,
|
| 46 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p35_type_success025_summary.md`
|
|
@@ -91,9 +93,9 @@ Completed deployment-clean diagnostics:
|
|
| 91 |
|
| 92 |
Completed residual transport jobs:
|
| 93 |
|
| 94 |
-
Last checked: `2026-06-29
|
| 95 |
-
completed
|
| 96 |
-
|
| 97 |
|
| 98 |
- Code supports `--retrieval-residual-scale`, defaulting to `1.0` so the
|
| 99 |
completed 32.12% result is unchanged.
|
|
@@ -177,6 +179,17 @@ passing CPU smoke.
|
|
| 177 |
35.19%, and 35.19%. These are near-tie/negative diagnostics below the current
|
| 178 |
35.25% equal mean-consensus no-op plateau. Summary jobs `14891083`/
|
| 179 |
`14891085`/`14891087`/`14891088` and rebuild job `14891089` completed.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
- Job `14869627` completed the CPU Apptainer smoke for the residual scale-grid
|
| 181 |
selector: selected index `3` and returned action `0.20` on the toy ray-search
|
| 182 |
case, validating candidate expansion before rollout.
|
|
|
|
| 41 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p35_safe_types_margin0p20_summary.md`,
|
| 42 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_knn2_scale0p40_safe_types_margin0p20_summary.md`,
|
| 43 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_summary.md`,
|
| 44 |
+
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_fieldsoftmax_grid_safe_margin0p20_summary.md`,
|
| 45 |
+
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_fieldsoftmax_grid_safe_margin0p10_noopbonus0p03_summary.md`,
|
| 46 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_policy_anchor_scale0p35_safe_noexpert_summary.md`,
|
| 47 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p35_type_success010_summary.md`,
|
| 48 |
`h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p35_type_success025_summary.md`
|
|
|
|
| 93 |
|
| 94 |
Completed residual transport jobs:
|
| 95 |
|
| 96 |
+
Last checked: `2026-06-29 02:00 UTC`. The field-conditioned tangent-barycenter
|
| 97 |
+
batch completed after passing CPU smokes, and the paper table rebuild now includes
|
| 98 |
+
the field-softmax rows.
|
| 99 |
|
| 100 |
- Code supports `--retrieval-residual-scale`, defaulting to `1.0` so the
|
| 101 |
completed 32.12% result is unchanged.
|
|
|
|
| 179 |
35.19%, and 35.19%. These are near-tie/negative diagnostics below the current
|
| 180 |
35.25% equal mean-consensus no-op plateau. Summary jobs `14891083`/
|
| 181 |
`14891085`/`14891087`/`14891088` and rebuild job `14891089` completed.
|
| 182 |
+
- Jobs `14891889`/`14891902`/`14891923` completed the K4/K8 field-softmax
|
| 183 |
+
residual-barycenter sweeps after CPU smokes `14891870` and `14892092`. K4
|
| 184 |
+
field-softmax reaches 34.96% with or without no-op 0.03 at margin `0.20`; K8
|
| 185 |
+
with no-op 0.03 reaches 34.84%. Summary jobs `14891934`/`14891946`/`14891960`
|
| 186 |
+
completed.
|
| 187 |
+
- Jobs `14892958`/`14892975`/`14892990` completed the K4 field-softmax no-op
|
| 188 |
+
margin sweep. Margins `0.10`, `0.05`, and `0.00` reach 35.19%, 35.07%, and
|
| 189 |
+
34.84%. Lower margins select many more field-softmax aggregates, but the
|
| 190 |
+
overall success drops, so this is a useful negative/near-tie diagnostic rather
|
| 191 |
+
than a new clean best. Summary jobs `14893002`/`14893016`/`14893028` and
|
| 192 |
+
rebuild job `14893069` completed.
|
| 193 |
- Job `14869627` completed the CPU Apptainer smoke for the residual scale-grid
|
| 194 |
selector: selected index `3` and returned action `0.20` on the toy ray-search
|
| 195 |
case, validating candidate expansion before rollout.
|