Finalize report nonlinear env_clip verification
Browse files
workspace/reports/2026-07-03.md
CHANGED
|
@@ -649,6 +649,10 @@ Action-bound audit status: new rollout artifacts now log action-bound safety lab
|
|
| 649 |
- `latexmk -pdf -interaction=nonstopmode main.tex`: PDF rebuilt successfully at 30 pages; only existing overfull/underfull layout and font warnings remain.
|
| 650 |
- Overclaim scan for selector-gap closure, submission-tier, leaderboard-style, and internal acceptance phrasing in `latex/main.tex`, `reports/2026-07-03.md`, `reports/draft_audit_ctt.md`, and `docs/cil_format.md` returned no matches.
|
| 651 |
- HF forced-download SHA verification matched local files for `workspace/latex/main.{tex,pdf}`, `workspace/scripts/eval_ctt_generated_rollout.py`, `workspace/tests/test_ctt.py`, all three `env_clip` aggregate metrics, the best train-clean `env_clip` learned-dominance metrics, and representative validation/test/train-calibration seed measured-candidate files.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 652 |
|
| 653 |
## Hugging Face Sync Status
|
| 654 |
|
|
@@ -696,6 +700,10 @@ Action-bound audit status: new rollout artifacts now log action-bound safety lab
|
|
| 696 |
- uploaded/checked aggregate and train-to-test dominance artifacts under commit `d78d4fe43424c713aa4dffb9bdee31f84ff178b7`.
|
| 697 |
- uploaded/checked validation/test/train-calibration seed rollout artifacts under commit `ee45c3c3c8c26cd1d19726ba00dd2c4a7ff4b53e`.
|
| 698 |
- verified SHA-256 prefixes: `latex/main.tex` `d7c8d1007d12`, `latex/main.pdf` `121e6bd969e8`, rollout evaluator `443e11c5e6ad`, `tests/test_ctt.py` `b36c71068eff`, validation aggregate metrics `92075c45030c`, held-out test aggregate metrics `a0447025c9b6`, train-calibration aggregate metrics `3ea089764ef9`, best learned-dominance metrics `88d8c26c0f31`, validation seed0 candidates `2cf3b8c30987`, test seed0 candidates `9f1bfc68f58d`, and train-calibration seed0 candidates `0ef3bf6e29b7`.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 699 |
|
| 700 |
## Next Actions
|
| 701 |
|
|
|
|
| 649 |
- `latexmk -pdf -interaction=nonstopmode main.tex`: PDF rebuilt successfully at 30 pages; only existing overfull/underfull layout and font warnings remain.
|
| 650 |
- Overclaim scan for selector-gap closure, submission-tier, leaderboard-style, and internal acceptance phrasing in `latex/main.tex`, `reports/2026-07-03.md`, `reports/draft_audit_ctt.md`, and `docs/cil_format.md` returned no matches.
|
| 651 |
- HF forced-download SHA verification matched local files for `workspace/latex/main.{tex,pdf}`, `workspace/scripts/eval_ctt_generated_rollout.py`, `workspace/tests/test_ctt.py`, all three `env_clip` aggregate metrics, the best train-clean `env_clip` learned-dominance metrics, and representative validation/test/train-calibration seed measured-candidate files.
|
| 652 |
+
- Verification after adding nonlinear `env_clip` selector diagnostics:
|
| 653 |
+
- `latexmk -pdf -interaction=nonstopmode main.tex`: PDF rebuilt successfully at 30 pages; only existing overfull/underfull layout and font warnings remain.
|
| 654 |
+
- Overclaim scan for selector-gap closure, submission-tier, leaderboard-style, and internal acceptance phrasing in `latex/main.tex`, `reports/2026-07-03.md`, `reports/draft_audit_ctt.md`, and `docs/cil_format.md` returned no matches.
|
| 655 |
+
- HF forced-download SHA verification matched local files for `workspace/latex/main.{tex,pdf}` and all four nonlinear `env_clip` dominance metrics.
|
| 656 |
|
| 657 |
## Hugging Face Sync Status
|
| 658 |
|
|
|
|
| 700 |
- uploaded/checked aggregate and train-to-test dominance artifacts under commit `d78d4fe43424c713aa4dffb9bdee31f84ff178b7`.
|
| 701 |
- uploaded/checked validation/test/train-calibration seed rollout artifacts under commit `ee45c3c3c8c26cd1d19726ba00dd2c4a7ff4b53e`.
|
| 702 |
- verified SHA-256 prefixes: `latex/main.tex` `d7c8d1007d12`, `latex/main.pdf` `121e6bd969e8`, rollout evaluator `443e11c5e6ad`, `tests/test_ctt.py` `b36c71068eff`, validation aggregate metrics `92075c45030c`, held-out test aggregate metrics `a0447025c9b6`, train-calibration aggregate metrics `3ea089764ef9`, best learned-dominance metrics `88d8c26c0f31`, validation seed0 candidates `2cf3b8c30987`, test seed0 candidates `9f1bfc68f58d`, and train-calibration seed0 candidates `0ef3bf6e29b7`.
|
| 703 |
+
- Nonlinear `env_clip` targeted HF upload completed and was verified by forced download SHA-256 comparison.
|
| 704 |
+
- uploaded/checked LaTeX artifacts under commit `0b623a505a550824ad54e6b16cf67ec40c2d8bee`.
|
| 705 |
+
- uploaded/checked nonlinear dominance artifacts under commit `4e5d6d59df24734530a0d8c377ac31442d54e5d6`.
|
| 706 |
+
- verified SHA-256 prefixes: `latex/main.tex` `b88870d9f6b6`, `latex/main.pdf` `ff900a7c1452`, nonlinear basic-positive metrics `2e3c66b6319a`, nonlinear context-tangent-positive metrics `efac5950b09b`, nonlinear basic-success metrics `2d16a1a26abd`, and nonlinear context-tangent-success metrics `0fd09bf9b7d2`.
|
| 707 |
|
| 708 |
## Next Actions
|
| 709 |
|