verdict-gate 0.1.0__tar.gz

verdict_gate-0.1.0/.gitignore

@@ -0,0 +1,31 @@
+# Python
+__pycache__/
+*.py[oc]
+build/
+dist/
+*.egg-info
+.venv/
+.pytest_cache/
+.ruff_cache/
+.ipynb_checkpoints/
+
+# Secrets: copy .env.example to .env and fill it in
+.env
+
+# Raw experiment output and large corpora (compact copies of finished runs live in results/runs/)
+harness/runs/
+harness/data/officeqa/
+/runs/
+
+# Ephemeral run-queue state for the status line
+ledger/queue.json
+ledger/status.json
+ledger/*.lock
+
+# Raw benchmark downloads for the finance transfer test (E12 draft); the loader re-downloads the pinned revision
+data/finance_candidates/
+# FreshQA CSV export for E13 (the loader pins its sha256 and can re-download it)
+data/freshqa/
+runs_e1[0-9]*.log
+# SimpleQA Verified CSV for E16 (the loader pins its revision and sha256 and can re-download it)
+data/simpleqa_verified/

verdict_gate-0.1.0/CITATION.cff

@@ -0,0 +1,9 @@
+cff-version: 1.2.0
+message: "If you use VERDICT, please cite it as below."
+title: "VERDICT: evidence-governed admission of self-evolved skills for small LLM agents"
+type: software
+authors:
+  - name: "Kunal"
+  - name: "Sahil Jain"
+license: Apache-2.0
+version: 0.1.0

verdict_gate-0.1.0/LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

verdict_gate-0.1.0/PKG-INFO

@@ -0,0 +1,137 @@
+Metadata-Version: 2.5
+Name: verdict-gate
+Version: 0.1.0
+Summary: VERDICT: evidence-governed admission of self-evolved skills for small LLM agents
+Author: Kunal, Sahil Jain
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Python: >=3.12
+Requires-Dist: jsonschema>=4.23
+Requires-Dist: numpy>=2.1
+Requires-Dist: pydantic>=2.13.5
+Requires-Dist: pyyaml>=6.0.3
+Requires-Dist: typer>=0.15
+Description-Content-Type: text/markdown
+
+# VERDICT
+
+**Evidence-governed admission of self-evolved skills for small LLM agents.**
+
+Self-improving agents keep an edited skill when it scores higher than its parent. With small models, repeated runs
+of an *unchanged* skill already differ by several points, so many of those "improvements" are noise: in our
+measurements keep-if-better admits a large share of skills that did not change at all (noise floors and gate
+simulations in [results/tables/noisegate/](results/tables/noisegate/)). VERDICT is the package
+that decides, from paired evidence, whether an evolved skill is really better, and records each decision as an
+admission card.
+
+> **Status:** pre-release. The `verdict` package (paired evidence, policies, evidence cards, replay, budget guard,
+> freeze manifests; CLI `verdict`) is working and tested; the distribution name is not final (see "Release status").
+
+## Repository layout
+
+```
+src/verdict/      the VERDICT package: core/ (statistics, policies, cards), adapters/, runners/, budget/, cli.py
+tests/            offline tests for verdict (synthetic fixtures in tests/fixtures/)
+schemas/          evidence_card.schema.json, the JSON Schema every card is validated against
+examples/         long-format CSV import format and an offline quickstart
+configs/          policies, frozen splits, experiment configs, noise floors (frozen at prereg-v1)
+prereg/           pre-registration and freeze manifests (checked by scripts/freeze_check.py)
+scripts/          experiment runners (paid, budget-guarded) and offline analyses
+harness/          experiment harness that produced the results (own pyproject, see harness/README.md)
+  metaskill/      from-scratch replication of MetaSkill-Evolve (arXiv:2607.05297): SealQA, OfficeQA, ALFWorld, ALE, GSM8K
+  noisegate/      NoiseGate, the stdlib-only admission gate prototype (noise floor, paired tests, admission card)
+  scripts/        run wrappers and analyses (index in harness/scripts/README.md)
+  configs/        one YAML per model configuration; gate settings; ALE presets
+  data/           frozen splits (SHA256SUMS) and a 10-question OfficeQA sample
+  tests/          offline tests for metaskill and the scripts
+results/          every result, as small files: run summaries, per-item outcomes, tables, ledger (see results/README.md)
+docs/             replication notes, research records (plans, decisions, run log), release checklist (see docs/README.md)
+```
+
+## Install
+
+```bash
+uv sync                  # verdict + its dev group (pytest, ruff, the harness workspace member the tests need)
+cp .env.example .env     # only for commands that call a model or a gated dataset; nothing below needs it
+```
+
+From PyPI: `pip install verdict-gate` (the import name and the CLI stay `verdict`).
+
+Requires Python 3.12+ ([uv](https://docs.astral.sh/uv/) recommended; `.python-version` pins 3.13). Without uv,
+`pip install .` (or `pip install -e .`) in a checkout installs the `verdict` package alone (numpy, pydantic, pyyaml,
+jsonschema, typer), without the harness. A wheel carries the card schema and the policy, validity, strata and floor
+configs it needs (`verdict/_data`); inside a checkout the package reads `schemas/` and `configs/` from the checkout.
+
+## Quickstart (offline)
+
+```bash
+uv run python examples/quickstart.py
+```
+
+It imports `examples/long_format.csv` (the generic import format, [examples/README.md](examples/README.md)), then
+decides three synthetic candidates against their parent under keep-if-higher and under the moderate policy, and
+writes one evidence card (`card.json`, valid against [schemas/evidence_card.schema.json](schemas/evidence_card.schema.json),
+and `card.md`). The same decision from the CLI:
+
+```bash
+uv run verdict compare --baseline tests/fixtures/replay/s0.json --candidate tests/fixtures/replay/c_good.json --policy configs/policies/moderate.yaml --fnoise tests/fixtures/replay/fnoise_m.yaml --out card.json
+uv run verdict card render card.json
+```
+
+`verdict compare` exits with a code per decision (0 = PASS_GLOBAL; see `src/verdict/cli.py`), `verdict replay`
+recomputes decisions for many arms, `verdict freeze` writes a freeze manifest, `verdict budget status` reads the
+spend ledger.
+
+## Tests
+
+```bash
+uv run pytest            # all offline tests: no network (blocked by conftest.py), no API keys, no raw runs needed
+uv run ruff check .
+```
+
+## Reproducing the results
+
+None of the commands below makes a model call or needs a key; they read tracked files only.
+
+| What | Command | Check |
+|---|---|---|
+| Frozen splits, configs and H48 artifacts are the ones pre-registered | `uv run python scripts/freeze_check.py` | prints `all hashes match` |
+| E2 replication summary by provenance tier | `uv run python scripts/analyze_e2.py` | `git diff --exit-code results/outcomes/p3_e2/` |
+| The decision core on synthetic evidence | `uv run python examples/quickstart.py` | three decisions printed, cards schema-valid |
+| Paper tables and figure data from committed artifacts | `uv run python scripts/make_tables.py` (`make paper-tables`) | `git diff --exit-code reports/paper/` |
+
+Every number in [results/](results/README.md) cites the run it came from;
+[docs/plan/RUNLOG.md](docs/plan/RUNLOG.md) (thesis experiments) and [docs/research/RUNLOG.md](docs/research/RUNLOG.md)
+(earlier NoiseGate work) give the exact command of each logged run. The paid runners (`scripts/run_*.py`) all have a
+`--dry-run` that prints the planned runs and the estimated cost; model calls go through OpenRouter and cost money.
+
+Not yet reproducible from tracked data: the E3 decision analysis (`scripts/analyze_e3.py`), H48 Event 1, the E8
+evolution and H48 Event 2 read raw arm files under `runs/` (not tracked). Harness commands run from `harness/`; see
+[harness/README.md](harness/README.md).
+
+## Data and licenses
+
+Code is licensed under [Apache-2.0](LICENSE). Datasets keep their own licenses. What is in this repository:
+
+| Benchmark | License | What is tracked here |
+|---|---|---|
+| SealQA (`vtllms/sealqa`) | Apache-2.0 | Question ids in frozen splits, per-question scores, evolved skills; no question text |
+| FRAMES (`google/frames-benchmark`) | Apache-2.0 | Question ids in frozen splits; a synthetic test fixture (no real rows) |
+| FinSearchComp (`ByteSeedXpert/FinSearchComp`) | CC-BY-4.0 (attribution required) | Task ids in frozen splits and summary scores; raw rows are downloaded at the pinned revision, never committed |
+| τ²-bench / τ³ retail (`sierra-research/tau2-bench`) | MIT | Task ids, per-task rewards, self-proposed retail skills; the environment is checked out separately at the pinned commit |
+| GSM8K | MIT | Ids and scores |
+| OfficeQA | CC-BY-SA-4.0 | A 10-question sample, see [harness/data/officeqa_sample/LICENSE.md](harness/data/officeqa_sample/LICENSE.md) |
+| Agents' Last Exam | (task data contains hidden reference answers) | **Never included**: task ids and scores only |
+
+All of the above can be redistributed in this form; the CC-BY-4.0 and CC-BY-SA-4.0 rows need the attribution kept.
+
+## Release status
+
+The distribution name is still open (RUNLOG D10: `verdict` is taken on PyPI); it lives only in `pyproject.toml` and
+`src/verdict/`, so the rename is one change. The implementation spec's `revision-eval` CLI is the `verdict` command
+here.
+
+## Citation
+
+A CITATION.cff will be added with the thesis title. Until then, cite MetaSkill-Evolve (arXiv:2607.05297) for the
+method the harness replicates.

verdict_gate-0.1.0/README.md

@@ -0,0 +1,122 @@
+# VERDICT
+
+**Evidence-governed admission of self-evolved skills for small LLM agents.**
+
+Self-improving agents keep an edited skill when it scores higher than its parent. With small models, repeated runs
+of an *unchanged* skill already differ by several points, so many of those "improvements" are noise: in our
+measurements keep-if-better admits a large share of skills that did not change at all (noise floors and gate
+simulations in [results/tables/noisegate/](results/tables/noisegate/)). VERDICT is the package
+that decides, from paired evidence, whether an evolved skill is really better, and records each decision as an
+admission card.
+
+> **Status:** pre-release. The `verdict` package (paired evidence, policies, evidence cards, replay, budget guard,
+> freeze manifests; CLI `verdict`) is working and tested; the distribution name is not final (see "Release status").
+
+## Repository layout
+
+```
+src/verdict/      the VERDICT package: core/ (statistics, policies, cards), adapters/, runners/, budget/, cli.py
+tests/            offline tests for verdict (synthetic fixtures in tests/fixtures/)
+schemas/          evidence_card.schema.json, the JSON Schema every card is validated against
+examples/         long-format CSV import format and an offline quickstart
+configs/          policies, frozen splits, experiment configs, noise floors (frozen at prereg-v1)
+prereg/           pre-registration and freeze manifests (checked by scripts/freeze_check.py)
+scripts/          experiment runners (paid, budget-guarded) and offline analyses
+harness/          experiment harness that produced the results (own pyproject, see harness/README.md)
+  metaskill/      from-scratch replication of MetaSkill-Evolve (arXiv:2607.05297): SealQA, OfficeQA, ALFWorld, ALE, GSM8K
+  noisegate/      NoiseGate, the stdlib-only admission gate prototype (noise floor, paired tests, admission card)
+  scripts/        run wrappers and analyses (index in harness/scripts/README.md)
+  configs/        one YAML per model configuration; gate settings; ALE presets
+  data/           frozen splits (SHA256SUMS) and a 10-question OfficeQA sample
+  tests/          offline tests for metaskill and the scripts
+results/          every result, as small files: run summaries, per-item outcomes, tables, ledger (see results/README.md)
+docs/             replication notes, research records (plans, decisions, run log), release checklist (see docs/README.md)
+```
+
+## Install
+
+```bash
+uv sync                  # verdict + its dev group (pytest, ruff, the harness workspace member the tests need)
+cp .env.example .env     # only for commands that call a model or a gated dataset; nothing below needs it
+```
+
+From PyPI: `pip install verdict-gate` (the import name and the CLI stay `verdict`).
+
+Requires Python 3.12+ ([uv](https://docs.astral.sh/uv/) recommended; `.python-version` pins 3.13). Without uv,
+`pip install .` (or `pip install -e .`) in a checkout installs the `verdict` package alone (numpy, pydantic, pyyaml,
+jsonschema, typer), without the harness. A wheel carries the card schema and the policy, validity, strata and floor
+configs it needs (`verdict/_data`); inside a checkout the package reads `schemas/` and `configs/` from the checkout.
+
+## Quickstart (offline)
+
+```bash
+uv run python examples/quickstart.py
+```
+
+It imports `examples/long_format.csv` (the generic import format, [examples/README.md](examples/README.md)), then
+decides three synthetic candidates against their parent under keep-if-higher and under the moderate policy, and
+writes one evidence card (`card.json`, valid against [schemas/evidence_card.schema.json](schemas/evidence_card.schema.json),
+and `card.md`). The same decision from the CLI:
+
+```bash
+uv run verdict compare --baseline tests/fixtures/replay/s0.json --candidate tests/fixtures/replay/c_good.json --policy configs/policies/moderate.yaml --fnoise tests/fixtures/replay/fnoise_m.yaml --out card.json
+uv run verdict card render card.json
+```
+
+`verdict compare` exits with a code per decision (0 = PASS_GLOBAL; see `src/verdict/cli.py`), `verdict replay`
+recomputes decisions for many arms, `verdict freeze` writes a freeze manifest, `verdict budget status` reads the
+spend ledger.
+
+## Tests
+
+```bash
+uv run pytest            # all offline tests: no network (blocked by conftest.py), no API keys, no raw runs needed
+uv run ruff check .
+```
+
+## Reproducing the results
+
+None of the commands below makes a model call or needs a key; they read tracked files only.
+
+| What | Command | Check |
+|---|---|---|
+| Frozen splits, configs and H48 artifacts are the ones pre-registered | `uv run python scripts/freeze_check.py` | prints `all hashes match` |
+| E2 replication summary by provenance tier | `uv run python scripts/analyze_e2.py` | `git diff --exit-code results/outcomes/p3_e2/` |
+| The decision core on synthetic evidence | `uv run python examples/quickstart.py` | three decisions printed, cards schema-valid |
+| Paper tables and figure data from committed artifacts | `uv run python scripts/make_tables.py` (`make paper-tables`) | `git diff --exit-code reports/paper/` |
+
+Every number in [results/](results/README.md) cites the run it came from;
+[docs/plan/RUNLOG.md](docs/plan/RUNLOG.md) (thesis experiments) and [docs/research/RUNLOG.md](docs/research/RUNLOG.md)
+(earlier NoiseGate work) give the exact command of each logged run. The paid runners (`scripts/run_*.py`) all have a
+`--dry-run` that prints the planned runs and the estimated cost; model calls go through OpenRouter and cost money.
+
+Not yet reproducible from tracked data: the E3 decision analysis (`scripts/analyze_e3.py`), H48 Event 1, the E8
+evolution and H48 Event 2 read raw arm files under `runs/` (not tracked). Harness commands run from `harness/`; see
+[harness/README.md](harness/README.md).
+
+## Data and licenses
+
+Code is licensed under [Apache-2.0](LICENSE). Datasets keep their own licenses. What is in this repository:
+
+| Benchmark | License | What is tracked here |
+|---|---|---|
+| SealQA (`vtllms/sealqa`) | Apache-2.0 | Question ids in frozen splits, per-question scores, evolved skills; no question text |
+| FRAMES (`google/frames-benchmark`) | Apache-2.0 | Question ids in frozen splits; a synthetic test fixture (no real rows) |
+| FinSearchComp (`ByteSeedXpert/FinSearchComp`) | CC-BY-4.0 (attribution required) | Task ids in frozen splits and summary scores; raw rows are downloaded at the pinned revision, never committed |
+| τ²-bench / τ³ retail (`sierra-research/tau2-bench`) | MIT | Task ids, per-task rewards, self-proposed retail skills; the environment is checked out separately at the pinned commit |
+| GSM8K | MIT | Ids and scores |
+| OfficeQA | CC-BY-SA-4.0 | A 10-question sample, see [harness/data/officeqa_sample/LICENSE.md](harness/data/officeqa_sample/LICENSE.md) |
+| Agents' Last Exam | (task data contains hidden reference answers) | **Never included**: task ids and scores only |
+
+All of the above can be redistributed in this form; the CC-BY-4.0 and CC-BY-SA-4.0 rows need the attribution kept.
+
+## Release status
+
+The distribution name is still open (RUNLOG D10: `verdict` is taken on PyPI); it lives only in `pyproject.toml` and
+`src/verdict/`, so the rename is one change. The implementation spec's `revision-eval` CLI is the `verdict` command
+here.
+
+## Citation
+
+A CITATION.cff will be added with the thesis title. Until then, cite MetaSkill-Evolve (arXiv:2607.05297) for the
+method the harness replicates.

verdict_gate-0.1.0/configs/fnoise/ibm-granite--granite-4.2-8b.yaml

@@ -0,0 +1,126 @@
+model: ibm-granite/granite-4.2-8b
+paired_fnoise:
+  8: 0.25
+  16: 0.1875
+  24: 0.16666666666666666
+  32: 0.125
+  40: 0.125
+  48: 0.10416666666666667
+  56: 0.10714285714285714
+  60: 0.1
+legacy_fnoise: 0.08388888888888885
+sensitivity: 0.09439056847898962
+source_run_ids:
+- R131_e1v3_granite42_v90_inline_cache_r0_s11
+- R132_e1v3_granite42_v90_inline_cache_r1_s22
+- R133_e1v3_granite42_v90_inline_cache_r2_s33
+- R134_e1v3_granite42_v90_inline_cache_r3_s44
+- R135_e1v3_granite42_v90_inline_cache_r4_s55
+rng_seed: 9001
+draws: 10000
+quantile: 0.95
+pairing: symmetric
+task: T15
+created: '2026-11-03T14:19:53+00:00'
+git_commit: 3600cae65c82b4c559e992b1e7860f1c222b11d1 (working tree modified)
+config:
+  file: configs/experiments/e1.yaml
+  sha256: 6b196a0f7b2eca5346ce7f92df6484c282aa2a9b875f0be49d48bb202e00f654
+block_sizes:
+- 8
+- 16
+- 24
+- 32
+- 40
+- 48
+- 56
+- 60
+split: sealqa_v90
+n_questions: 90
+excluded_questions: []
+source_runs:
+- run_id: R131_e1v3_granite42_v90_inline_cache_r0_s11
+  seed: 11
+  accuracy: 0.2
+  n: 90
+  invalid: 0
+  files:
+    config.json: 0e78607b568c2d2f25cd318d42b5ccc666d48e81e97ca1b6f1406eb187ff1dcc
+    split.json: 5dcbd32f156bdcbf3b9b2389d019c8c4dd82193e835b494405b3e60d5b3fde80
+    result.json: ace30ba78e7d556463dfceb880a1290de12fac077bb91d3d09cbe41431327e1a
+    test_traces.jsonl: 651159e97021b7bb0dfded7f6c19de5178e4e509a08c49f54b33a77b055ee7b7
+- run_id: R132_e1v3_granite42_v90_inline_cache_r1_s22
+  seed: 22
+  accuracy: 0.23333333333333334
+  n: 90
+  invalid: 0
+  files:
+    config.json: a09a1d3871dea2f2c01d7eafe7693d950d04d722fba96092ac2a09c3cc294147
+    split.json: 5dcbd32f156bdcbf3b9b2389d019c8c4dd82193e835b494405b3e60d5b3fde80
+    result.json: fb66523d870b19b257e0b3193f9805f0e18c0be8a66493a960ab704495024cfa
+    test_traces.jsonl: 51ef070db03970fa341beaf251d385fce2be432902aa4f7391b1f1a1d75fa4b8
+- run_id: R133_e1v3_granite42_v90_inline_cache_r2_s33
+  seed: 33
+  accuracy: 0.2111111111111111
+  n: 90
+  invalid: 0
+  files:
+    config.json: 27772d99731eacf028679cdfb09279cd7585efb3d1e7b0184ebe8ce6a8419dbd
+    split.json: 5dcbd32f156bdcbf3b9b2389d019c8c4dd82193e835b494405b3e60d5b3fde80
+    result.json: bbd126b8094b4d0e143a80cd53bf155ebd1163cc117b4615e22b9f0e385e426c
+    test_traces.jsonl: 823670922ce6f7dd95170d725897858abda57504c6d2099e48186686fcb4b46b
+- run_id: R134_e1v3_granite42_v90_inline_cache_r3_s44
+  seed: 44
+  accuracy: 0.28888888888888886
+  n: 90
+  invalid: 0
+  files:
+    config.json: fc54e2d2a91d182c476c63d810329914510d55865aaad2d4bc0fae5366b722f3
+    split.json: 5dcbd32f156bdcbf3b9b2389d019c8c4dd82193e835b494405b3e60d5b3fde80
+    result.json: d5fb2076c28d6f181e82c8fbdc1e0f6f8d833dae3836f2714dee7e3f5b2c1db9
+    test_traces.jsonl: 9f2f09ed331298900b62e04cae588da57195289b2d4b16d1a64a53b9b06c7726
+- run_id: R135_e1v3_granite42_v90_inline_cache_r4_s55
+  seed: 55
+  accuracy: 0.24444444444444444
+  n: 90
+  invalid: 0
+  files:
+    config.json: df73e6b506371556ee7d75301d4d10e7fe81835303fa558087a6b7119c06e312
+    split.json: 5dcbd32f156bdcbf3b9b2389d019c8c4dd82193e835b494405b3e60d5b3fde80
+    result.json: bcec9e8a5cc0463c049a4128e2ce4e98df6f687e3f1f7e2b34b5a377a857c4d8
+    test_traces.jsonl: 302ae0a30432f6a571b8f42ab092c85c3bacf0fa5f8388c8d3a0bf3cc88e301f
+accuracy_mean: 0.23555555555555557
+accuracy_sd: 0.034605358894216516
+flip:
+  mean_pair_discordance: 0.1511111111111111
+  share_questions_flipping: 0.32222222222222224
+  by_question:
+    seal_0-0: 0.4
+    seal_0-101: 0.4
+    seal_0-11: 0.4
+    seal_0-23: 0.6
+    seal_0-29: 0.4
+    seal_0-38: 0.4
+    seal_0-39: 0.4
+    seal_0-40: 0.6
+    seal_0-44: 0.4
+    seal_0-57: 0.6
+    seal_0-62: 0.4
+    seal_0-69: 0.6
+    seal_0-74: 0.4
+    seal_0-77: 0.6
+    seal_0-84: 0.4
+    seal_0-91: 0.4
+    seal_0-96: 0.4
+    seal_0-97: 0.6
+    seal_hard-1: 0.4
+    seal_hard-147: 0.4
+    seal_hard-165: 0.4
+    seal_hard-195: 0.6
+    seal_hard-20: 0.4
+    seal_hard-210: 0.4
+    seal_hard-63: 0.6
+    seal_hard-70: 0.4
+    seal_hard-83: 0.4
+    seal_hard-86: 0.6
+    seal_hard-98: 0.6