quantum-reasoning-skill 1.0.0 → 1.1.1

package/.github/ISSUE_TEMPLATE/feature-request.yml

@@ -1,31 +0,0 @@
-name: Feature request
-description: Propose a change to the reasoning protocol, tooling, benchmarks, or integration contract.
-title: "[Feature]: "
-labels: ["enhancement"]
-body:
-  - type: textarea
-    id: problem
-    attributes:
-      label: Problem or limitation
-      description: What concrete limitation does this proposal address?
-    validations:
-      required: true
-  - type: textarea
-    id: proposal
-    attributes:
-      label: Proposed change
-      description: Describe the behavior or interface you want to add or change.
-    validations:
-      required: true
-  - type: textarea
-    id: evidence
-    attributes:
-      label: Evidence or evaluation plan
-      description: If this affects reasoning quality, explain how it could be tested without relying on anecdotal examples alone.
-  - type: checkboxes
-    id: scope
-    attributes:
-      label: Scope check
-      options:
-        - label: This proposal does not present unverified benchmark claims as established results.
-          required: true

package/.github/PULL_REQUEST_TEMPLATE.md

@@ -1,15 +0,0 @@
-## Summary
-
-Describe the change and the behavior it affects.
-
-## Validation
-
-- [ ] I ran `python -m unittest discover -s tests -v`.
-- [ ] I ran `python benchmark/evaluate.py --help`.
-- [ ] I added or updated tests when executable behavior changed.
-- [ ] I updated documentation when the public contract changed.
-- [ ] I did not include private chain-of-thought, secrets, credentials, or fabricated benchmark telemetry.
-
-## Benchmark-impacting changes
-
-If this changes `SKILL.md`, scoring, collapse/revival behavior, benchmark schemas, or evaluation logic, explain how existing results should be interpreted and whether new community runs are needed.

package/.github/workflows/npm-publish.yml

@@ -1,32 +0,0 @@
-name: npm Publish  
-  
-on:  
-  workflow_dispatch:  
-  push:  
-    branches: [main]  
-    paths:  
-      - "package.json"  
-      - "index.js"  
-  
-concurrency:  
-  group: npm-publish  
-  cancel-in-progress: false  
-  
-permissions:  
-  contents: read  
-  
-jobs:  
-  publish:  
-    runs-on: ubuntu-latest  
-    steps:  
-      - uses: actions/checkout@v4  
-  
-      - uses: actions/setup-node@v4  
-        with:  
-          node-version: "20"  
-          registry-url: "https://registry.npmjs.org"  
-  
-      - name: Publish to npm  
-        run: npm publish --access public  
-        env:  
-          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }} 

package/.github/workflows/publish-release.yml

@@ -1,79 +0,0 @@
-name: publish-release
-
-on:
-  workflow_run:
-    workflows: ["validate-skill"]
-    types: [completed]
-    branches: [main]
-
-permissions:
-  contents: write
-
-concurrency:
-  group: publish-release
-  cancel-in-progress: false
-
-jobs:
-  publish:
-    if: ${{ github.event.workflow_run.conclusion == 'success' }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@fbc6f3992d24b796d5a048ff273f7fcc4a7b6c09 # v5
-        with:
-          ref: ${{ github.event.workflow_run.head_sha }}
-          fetch-depth: 0
-
-      - name: Resolve and validate version
-        id: version
-        shell: bash
-        run: |
-          set -euo pipefail
-          test -s VERSION
-          version="$(tr -d '[:space:]' < VERSION)"
-          version="${version#v}"
-          if [[ ! "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+([.-][0-9A-Za-z.-]+)?$ ]]; then
-            echo "Invalid release version: $version" >&2
-            exit 1
-          fi
-          echo "version=$version" >> "$GITHUB_OUTPUT"
-          echo "tag=v${version}" >> "$GITHUB_OUTPUT"
-
-      - name: Require matching changelog entry
-        shell: bash
-        env:
-          VERSION: ${{ steps.version.outputs.version }}
-        run: |
-          set -euo pipefail
-          grep -Fq "## [$VERSION]" CHANGELOG.md || {
-            echo "CHANGELOG.md must contain a ## [$VERSION] section before release." >&2
-            exit 1
-          }
-
-      - name: Check existing release
-        id: existing
-        shell: bash
-        env:
-          GH_TOKEN: ${{ github.token }}
-          TAG: ${{ steps.version.outputs.tag }}
-        run: |
-          set -euo pipefail
-          if gh release view "$TAG" >/dev/null 2>&1; then
-            echo "exists=true" >> "$GITHUB_OUTPUT"
-            echo "$TAG already exists; nothing to publish."
-          else
-            echo "exists=false" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: Create tag and GitHub Release
-        if: steps.existing.outputs.exists != 'true'
-        shell: bash
-        env:
-          GH_TOKEN: ${{ github.token }}
-          TAG: ${{ steps.version.outputs.tag }}
-          TARGET_SHA: ${{ github.event.workflow_run.head_sha }}
-        run: |
-          set -euo pipefail
-          gh release create "$TAG" \
-            --target "$TARGET_SHA" \
-            --title "$TAG" \
-            --generate-notes

package/.github/workflows/validate-skill.yml

@@ -1,154 +0,0 @@
-name: validate-skill
-
-on:
-  push:
-  pull_request:
-
-permissions:
-  contents: read
-
-jobs:
-  validate:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@fbc6f3992d24b796d5a048ff273f7fcc4a7b6c09 # v5
-
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
-        with:
-          python-version: "3.12"
-
-      - name: Validate skill repository contract
-        shell: bash
-        run: |
-          set -euo pipefail
-          for required in \
-            SKILL.md README.md LICENSE CHANGELOG.md VERSION CONTRIBUTING.md SECURITY.md CITATION.cff \
-            examples/usage.md examples/host-integration.md \
-            reference/branch_controller.py \
-            docs/MEASUREMENT.md docs/COMPATIBILITY.md \
-            benchmark/README.md benchmark/cases.jsonl benchmark/evaluate.py benchmark/validate_submission.py \
-            benchmark/schemas/case.schema.json benchmark/schemas/result.schema.json \
-            benchmark/schemas/metadata.schema.json benchmark/schemas/comparison.schema.json \
-            tests/test_reference.py tests/test_benchmark.py tests/test_submission_validation.py \
-            .github/ISSUE_TEMPLATE/benchmark-result.yml .github/ISSUE_TEMPLATE/bug-report.yml \
-            .github/ISSUE_TEMPLATE/feature-request.yml .github/PULL_REQUEST_TEMPLATE.md; do
-            test -s "$required"
-          done
-
-          python - <<'PY'
-          from pathlib import Path
-          import json
-          import re
-
-          root = Path.cwd().resolve()
-          skill = (root / "SKILL.md").read_text(encoding="utf-8")
-          lines = skill.splitlines()
-          if not lines or lines[0].strip() != "---":
-              raise SystemExit("SKILL.md must start with YAML front matter")
-          try:
-              end = next(i for i, line in enumerate(lines[1:], start=1) if line.strip() == "---")
-          except StopIteration as exc:
-              raise SystemExit("SKILL.md front matter is not closed") from exc
-          fields = {}
-          for line in lines[1:end]:
-              if ":" in line:
-                  key, value = line.split(":", 1)
-                  fields[key.strip()] = value.strip()
-          if fields.get("name") != "quantum-reasoning":
-              raise SystemExit("SKILL.md front matter must declare name: quantum-reasoning")
-          if not fields.get("description"):
-              raise SystemExit("SKILL.md front matter must contain a non-empty description")
-          if len(lines[end + 1:]) < 20:
-              raise SystemExit("SKILL.md body is unexpectedly short")
-
-          readme = (root / "README.md").read_text(encoding="utf-8")
-          for required in (
-              "SKILL.md", "examples/usage.md", "examples/host-integration.md",
-              "reference/branch_controller.py", "docs/MEASUREMENT.md", "docs/COMPATIBILITY.md",
-              "benchmark/README.md", "CONTRIBUTING.md", "SECURITY.md", "CITATION.cff",
-          ):
-              if required not in readme:
-                  raise SystemExit(f"README.md must reference {required}")
-
-          markdown_files = [
-              root / "README.md", root / "SKILL.md", root / "CONTRIBUTING.md", root / "SECURITY.md",
-              root / "examples/usage.md", root / "examples/host-integration.md",
-              root / "benchmark/README.md", root / "docs/MEASUREMENT.md", root / "docs/COMPATIBILITY.md",
-          ]
-          link_pattern = re.compile(r"\[[^\]]*\]\(([^)]+)\)")
-          for document in markdown_files:
-              text = document.read_text(encoding="utf-8")
-              for raw_target in link_pattern.findall(text):
-                  target = raw_target.strip().split("#", 1)[0].split("?", 1)[0]
-                  if not target or "://" in target or target.startswith(("mailto:", "#")):
-                      continue
-                  resolved = (document.parent / target).resolve()
-                  try:
-                      resolved.relative_to(root)
-                  except ValueError as exc:
-                      raise SystemExit(f"{document.relative_to(root)} links outside repository: {raw_target}") from exc
-                  if not resolved.exists():
-                      raise SystemExit(f"Broken relative link in {document.relative_to(root)}: {raw_target}")
-
-          case_path = root / "benchmark" / "cases.jsonl"
-          seen_ids = set()
-          for line_number, raw in enumerate(case_path.read_text(encoding="utf-8").splitlines(), start=1):
-              if not raw.strip():
-                  continue
-              try:
-                  case = json.loads(raw)
-              except json.JSONDecodeError as exc:
-                  raise SystemExit(f"benchmark/cases.jsonl:{line_number}: invalid JSON: {exc}") from exc
-              required = {"id", "domain", "prompt", "accepted_answers"}
-              missing = required - set(case)
-              if missing:
-                  raise SystemExit(f"benchmark/cases.jsonl:{line_number}: missing {sorted(missing)}")
-              case_id = str(case["id"])
-              if case_id in seen_ids:
-                  raise SystemExit(f"duplicate benchmark case id: {case_id}")
-              seen_ids.add(case_id)
-              if not isinstance(case["accepted_answers"], list) or not case["accepted_answers"]:
-                  raise SystemExit(f"benchmark/cases.jsonl:{line_number}: accepted_answers must be non-empty")
-
-          schemas = sorted((root / "benchmark" / "schemas").glob("*.schema.json"))
-          if len(schemas) < 4:
-              raise SystemExit("expected case, result, metadata and comparison JSON Schemas")
-          for schema_path in schemas:
-              schema = json.loads(schema_path.read_text(encoding="utf-8"))
-              if schema.get("$schema") != "https://json-schema.org/draft/2020-12/schema":
-                  raise SystemExit(f"{schema_path}: expected JSON Schema draft 2020-12")
-              if schema.get("type") != "object" or not schema.get("required"):
-                  raise SystemExit(f"{schema_path}: must define an object with required fields")
-
-          version = (root / "VERSION").read_text(encoding="utf-8").strip().lstrip("v")
-          if not re.fullmatch(r"[0-9]+\.[0-9]+\.[0-9]+(?:[.-][0-9A-Za-z.-]+)?", version):
-              raise SystemExit("VERSION is not a valid semantic version")
-          cff = (root / "CITATION.cff").read_text(encoding="utf-8")
-          for marker in ("cff-version: 1.2.0", "title:", "authors:", "repository-code:", "license: MIT"):
-              if marker not in cff:
-                  raise SystemExit(f"CITATION.cff missing {marker!r}")
-          if f"version: {version}" not in cff:
-              raise SystemExit("CITATION.cff version must match VERSION")
-
-          action_use = re.compile(r"uses:\s+(actions/[A-Za-z0-9_.-]+)@([^\s#]+)")
-          for workflow in (root / ".github" / "workflows").glob("*.yml"):
-              for action, ref in action_use.findall(workflow.read_text(encoding="utf-8")):
-                  if not re.fullmatch(r"[0-9a-f]{40}", ref):
-                      raise SystemExit(f"{workflow}: {action} must be pinned to an exact commit SHA")
-
-          print("Skill repository contract validated successfully.")
-          PY
-
-      - name: Compile Python sources
-        run: python -m compileall -q reference benchmark tests
-
-      - name: Run behavioral tests
-        run: python -m unittest discover -s tests -v
-
-      - name: Validate community benchmark bundles
-        run: python benchmark/validate_submission.py --root benchmark/results/community --allow-empty
-
-      - name: Check benchmark CLIs
-        run: |
-          python benchmark/evaluate.py --help > /dev/null
-          python benchmark/validate_submission.py --help > /dev/null

package/CHANGELOG.md

@@ -1,51 +0,0 @@
-# Changelog
-
-All notable changes to this project are documented here.
-
-## [Unreleased]
-
-## [0.3.1] - 2026-09-07
-
-### Added
-
-- Community benchmark contribution policy in `CONTRIBUTING.md`.
-- GitHub **Benchmark result**, **Bug report**, and **Feature request** issue forms.
-- Pull-request checklist for tests, documentation, benchmark integrity, and sensitive-data hygiene.
-- Draft 2020-12 JSON Schemas for benchmark cases, result rows, experiment metadata, and comparison output.
-- `benchmark/validate_submission.py` for machine-validating reproducible community benchmark bundles.
-- Tests that reject missing benchmark artifacts, tampered comparisons, and incomplete integrity metadata.
-- Capability-based host compatibility contract in `docs/COMPATIBILITY.md`.
-- Generic native-skill, persistent-instruction, and controller-assisted integration examples.
-- `SECURITY.md` vulnerability-reporting policy.
-- `CITATION.cff` research-software citation metadata.
-
-### Changed
-
-- Benchmark documentation now explicitly assigns real-model evaluation to users and contributors rather than requiring maintainer-run access to every model/provider.
-- Community benchmark PRs now include the exact `cases.jsonl` used and are re-evaluated by CI from their raw baseline/skill files.
-- Third-party benchmark submissions are treated as reproducible external measurements, not automatic project endorsements or universal performance claims.
-- Release publishing now runs only after `validate-skill` succeeds on `main`; a failed validation cannot publish a release.
-- GitHub Actions dependencies are pinned to exact commit SHAs and CI enforces future pinning.
-- CI now validates schemas, version/citation consistency, host/documentation links, and community result bundles.
-
-## [0.3.0] - 2026-09-07
-
-### Added
-
-- Deterministic reference branch controller with explicit scoring and state transitions.
-- Shared-assumption and semantic-correlation penalty.
-- Quantified dormant/rejected state rules and branch revival triggers.
-- Uncertainty-based recommended search width.
-- Explicit collapse criteria and leader-margin checks.
-- Measurement specification documenting formulas and calibration requirements.
-- Reproducible baseline-vs-skill benchmark protocol.
-- Seed benchmark cases and JSONL result schema.
-- Benchmark evaluator for accuracy, token/tool cost, latency, branch diversity, error recovery and contradiction resolution.
-- Behavioral unit tests for the branch controller and benchmark evaluator.
-- CI checks for Python compilation, benchmark schema validation and behavioral tests.
-- Automated GitHub tag and Release publishing driven by the `VERSION` file.
-
-### Changed
-
-- `SKILL.md` now distinguishes qualitative protocol rules from unvalidated reference thresholds.
-- `README.md` now documents the measurable framework and makes clear that empirical performance improvement has not yet been demonstrated.

package/CITATION.cff

@@ -1,17 +0,0 @@
-cff-version: 1.2.0
-message: "If you use this software or reasoning protocol, please cite it using the metadata below."
-title: "Quantum Reasoning Skill"
-type: software
-authors:
-  - name: "Furox-Art"
-repository-code: "https://github.com/Furox-Art/quantum-reasoning-skill"
-url: "https://github.com/Furox-Art/quantum-reasoning-skill"
-license: MIT
-version: 0.3.1
-date-released: 2026-09-07
-keywords:
-  - reasoning
-  - language-models
-  - agent-systems
-  - test-time-compute
-  - benchmarking

package/CONTRIBUTING.md

@@ -1,88 +0,0 @@
-# Contributing
-
-Contributions are welcome for the reasoning protocol, reference controller, tests, documentation, benchmark cases, host integrations and independently run model evaluations.
-
-Before changing host-facing behavior, read [`docs/COMPATIBILITY.md`](./docs/COMPATIBILITY.md). Executable behavior changes should include tests.
-
-## Community-run benchmarks
-
-The project does **not** require the maintainer to purchase access to every model or provider. Real model evaluations are intentionally community-run.
-
-The repository provides:
-
-- the benchmark protocol;
-- deterministic seed cases;
-- machine-readable JSON Schemas;
-- the result evaluator;
-- a reproducible submission validator;
-- CI validation and comparison tooling.
-
-Users may run controlled baseline-vs-skill experiments on models and providers they already have access to and submit the results for review.
-
-### Required metadata
-
-Every submitted model evaluation must identify at least:
-
-- provider;
-- exact model and model version when available;
-- run date;
-- skill version/commit when available;
-- baseline and skill prompt/instruction configuration;
-- temperature/sampling parameters;
-- context and output limits;
-- tool availability;
-- number of repetitions per case;
-- random seed when supported;
-- local hardware/runtime details for local models;
-- whether failures, refusals and timeouts were retained.
-
-Do not omit failed runs.
-
-### Required artifacts for a benchmark PR
-
-Place each submitted run under:
-
-```text
-benchmark/results/community/<provider>-<model>-<YYYY-MM-DD>/
-```
-
-Every bundle must include:
-
-```text
-metadata.json
-cases.jsonl
-baseline.jsonl
-skill.jsonl
-comparison.json
-README.md
-```
-
-The exact contracts are in [`benchmark/schemas/`](./benchmark/schemas/). `cases.jsonl` must contain the exact evaluated cases, including custom cases when used.
-
-`comparison.json` must be produced by `benchmark/evaluate.py` from the submitted raw result files rather than edited manually. Before submitting, run:
-
-```bash
-python benchmark/validate_submission.py --root benchmark/results/community
-```
-
-CI recomputes the comparison and rejects a bundle when its raw evidence and reported comparison disagree.
-
-### Result integrity
-
-- Use the same model/version, task set, tools, sampling settings and budget policy for baseline and skill conditions.
-- Do not expose or submit private chain-of-thought.
-- Do not fabricate missing telemetry.
-- Clearly disclose custom benchmark cases, prompt wrappers, provider-specific adapters and any modifications to `SKILL.md`.
-- Third-party benchmark submissions are measurements from their submitters, not project-maintainer endorsements.
-- A single positive run is not sufficient to establish a general performance claim.
-
-### How to submit
-
-You can either:
-
-1. open a **Benchmark result** issue using the repository issue template and link to your artifacts; or
-2. open a pull request containing the reproducible result bundle described above.
-
-For ordinary defects, use the **Bug report** form. For proposed behavior or protocol changes, use the **Feature request** form.
-
-For code or protocol changes, include tests when the change is executable and explain which behavior is being changed. Follow the pull-request checklist in `.github/PULL_REQUEST_TEMPLATE.md`.

package/SECURITY.md

@@ -1,17 +0,0 @@
-# Security policy
-
-## Supported versions
-
-Security fixes are applied to the current `main` branch and the latest published release.
-
-## Reporting a vulnerability
-
-Do not publish exploit details, credentials, tokens, private benchmark data, or other sensitive material in a public issue.
-
-Prefer GitHub's private **Report a vulnerability** / Security Advisory flow when it is available for this repository. If that private channel is unavailable, open a minimal public issue that only requests a private contact path and does not include vulnerability details.
-
-## Scope
-
-Relevant reports include vulnerabilities in repository automation, benchmark ingestion/validation, release workflows, or reference code that could cause untrusted contributed content to execute unexpectedly, alter releases, or expose secrets.
-
-Reasoning-quality disagreements and ordinary protocol bugs are not security vulnerabilities; use the normal bug-report issue form for those.

package/benchmark/README.md

@@ -1,134 +0,0 @@
-# Benchmark protocol
-
-This directory measures whether the skill improves results rather than merely producing more reasoning text.
-
-## Who runs the benchmarks
-
-Real model evaluations are intentionally **community-run**. The repository supplies the benchmark protocol, seed cases, JSON Schemas, evaluator and submission validator; users run experiments on the models/providers they have access to.
-
-Maintainer-run access to every commercial or local model is not required. The project therefore separates **benchmark infrastructure** from **third-party empirical results**.
-
-Submitted results are evidence from the contributor who produced them. They are not automatically endorsed by the project and should not be generalized beyond the tested model/version/configuration without replication.
-
-## Principle
-
-Run the **same model, model version, task set, tool access, temperature/sampling settings, and token budget policy** twice:
-
-1. baseline: normal instructions without `SKILL.md`
-2. skill: the same setup with `SKILL.md`
-
-Do not compare different models and attribute the difference to the skill.
-
-## Seed cases
-
-`cases.jsonl` contains deterministic smoke-test cases. They are intentionally small and are **not sufficient evidence of reasoning improvement**. A serious evaluation should add difficult held-out tasks from the target domains and report their provenance/licensing.
-
-Each case has:
-
-```json
-{"id":"...","domain":"...","prompt":"...","accepted_answers":["..."]}
-```
-
-## Machine-readable schemas
-
-The contracts are versioned with the repository:
-
-- [`schemas/case.schema.json`](./schemas/case.schema.json) — one benchmark case
-- [`schemas/result.schema.json`](./schemas/result.schema.json) — one baseline/skill result row
-- [`schemas/metadata.schema.json`](./schemas/metadata.schema.json) — experiment metadata
-- [`schemas/comparison.schema.json`](./schemas/comparison.schema.json) — evaluator comparison output
-
-A result row requires:
-
-```json
-{
-  "case_id": "math-arithmetic-001",
-  "answer": "323",
-  "tokens": 120,
-  "tool_calls": 0,
-  "latency_ms": 950
-}
-```
-
-Failed/refused runs should still be represented rather than silently removed. The optional `status` field may be `ok`, `refusal`, `timeout`, or `error`.
-
-Skill-aware runners may additionally record observable aggregate telemetry such as `branches_total`, `branches_distinct`, `revived_branches`, `recovered_errors`, `contradictions_found`, and `contradictions_resolved`. Do not store private chain-of-thought.
-
-## Evaluate one run
-
-```bash
-python benchmark/evaluate.py \
-  --cases benchmark/cases.jsonl \
-  --skill path/to/skill-results.jsonl
-```
-
-## Compare baseline vs skill
-
-```bash
-python benchmark/evaluate.py \
-  --cases benchmark/cases.jsonl \
-  --baseline path/to/baseline-results.jsonl \
-  --skill path/to/skill-results.jsonl \
-  --output comparison.json
-```
-
-The evaluator reports exact-answer accuracy, mean token use, tool calls, latency, branch diversity, revival/error recovery, contradiction resolution, and baseline-to-skill deltas.
-
-## Required experimental controls
-
-For a publishable comparison, record at minimum:
-
-- provider and exact model/version
-- date of the run
-- decoding/sampling parameters
-- context and output limits
-- tool availability
-- prompt wrapper/system instructions
-- number of repetitions per case
-- random seed when the provider supports one
-- hardware/runtime details for local models
-- failures, refusals and timeouts rather than silently dropping them
-
-Use multiple repetitions for stochastic models and report confidence intervals. Keep benchmark cases separate from any prompts used while designing or tuning the skill.
-
-## Submitting community results
-
-Results can be submitted in either of two ways:
-
-1. Open a **Benchmark result** issue and provide the required metadata plus links/attachments to the result artifacts.
-2. Open a pull request containing a reproducible result bundle under:
-
-```text
-benchmark/results/community/<provider>-<model>-<YYYY-MM-DD>/
-```
-
-Every benchmark-result PR bundle must contain:
-
-```text
-metadata.json
-cases.jsonl
-baseline.jsonl
-skill.jsonl
-comparison.json
-README.md
-```
-
-Including `cases.jsonl` inside the bundle makes the exact evaluated case set immutable and reviewable even when custom cases are used.
-
-Generate `comparison.json` with `benchmark/evaluate.py`; do not hand-edit it. Before opening a PR, validate the bundle:
-
-```bash
-python benchmark/validate_submission.py --root benchmark/results/community
-```
-
-CI runs the same validator. It rejects missing artifacts, incomplete metadata, duplicate/missing case results, and a `comparison.json` that differs from a fresh evaluator recomputation.
-
-See [`../CONTRIBUTING.md`](../CONTRIBUTING.md) for the complete submission and integrity policy.
-
-## Interpretation
-
-A useful result is not simply "skill accuracy is higher". Report the trade-off between accuracy and compute. A skill that gains 1 percentage point while using 5x tokens may be undesirable for many workloads.
-
-The reference thresholds in `reference/branch_controller.py` are defaults to test, not validated constants. Benchmark evidence should drive later calibration.
-
-The project makes no universal performance claim from a single model, provider, benchmark or contributor submission. Independent replication is preferred.

package/benchmark/cases.jsonl

@@ -1,6 +0,0 @@
-{"id":"math-arithmetic-001","domain":"mathematics","prompt":"Compute 17 * 19.","accepted_answers":["323"],"notes":"Exact-answer sanity case."}
-{"id":"math-algebra-001","domain":"mathematics","prompt":"Solve x^2 - 5x + 6 = 0. Return the roots in ascending order separated by a comma.","accepted_answers":["2, 3","2,3"],"notes":"Checks independent verification of a simple factorization."}
-{"id":"logic-contradiction-001","domain":"logic","prompt":"Premises: All A are B. No B are C. Some A are C. Are the premises jointly consistent? Answer yes or no.","accepted_answers":["no"],"notes":"Requires contradiction detection."}
-{"id":"debug-python-001","domain":"debugging","prompt":"A Python function is intended to return the first item of xs: def first(xs): return xs[1]. What integer index should replace 1?","accepted_answers":["0"],"notes":"Minimal root-cause diagnosis."}
-{"id":"science-units-001","domain":"scientific-reasoning","prompt":"A car travels at 20 m/s for 15 s at constant speed. How many meters does it travel? Return only the number.","accepted_answers":["300"],"notes":"Simple quantitative verification case."}
-{"id":"probability-001","domain":"probability","prompt":"A fair coin is flipped twice. What is the probability of exactly one head? Return a decimal.","accepted_answers":["0.5",".5"],"notes":"Checks enumeration versus shortcut reasoning."}