13a4b05d62
Phase B of the curriculum-license-loop arc. Stacked on the ADR-0264 branch. The invariant: conservative_floor is a one-sided Wilson lower bound and Wilson assumes INDEPENDENT trials. CORE's pipeline is deterministic, so replaying an identical case is not a second trial -- it is the same trial with a guaranteed outcome. A ledger's `committed` count is an upper bound on its evidence; the defensible figure is its distinct-decision count. Phase B was scoped as a precaution for a curriculum producer that does not exist yet. Running the instrument against the producers that DO exist found it already violated: 21 of the 25 ratified deduction_serve bands do not clear theta_SERVE=0.99 on distinct evidence. Three inflate 28 distinct cases into 720 committed (honest floor 0.8084 vs claimed 0.9909). deduction_serving_enabled was ratified ON 2026-07-24 and is live. The estimation producer (ADR-0175) is clean -- 660 committed, 660 distinct, zero repeats, evidently chosen just above the 657 a perfect record needs. So this is a regression from a standard already established in the repo, not an architectural gap. `claimed` is identical for all 25 deduction bands because every band commits 720 with a perfect record: the gate sees 25 indistinguishable passes while honest floors span 0.8084..0.9909. NOT REPAIRED. The ledger is SHA-sealed, ratified, and gating a live flag, so re-sealing it is Shay's ratification, not a test's. wrong=0 still holds -- no band answered anything incorrectly. What is not established is reliability at the volume claimed. Measured, pinned in both directions, written down. Added: - core/reliability_gate/evidence.py -- pure measurement, imported by no serving path. volume_for_theta() DERIVES 657 from conservative_floor rather than restating it, so a WILSON_Z change cannot leave a stale literal behind. - tests/test_volume_honesty.py -- 13 tests. AUDIT_SOURCES is checked against CAPABILITY_LEDGERS, so a new licensed capability cannot ship unaudited; the curriculum entry is a declared None that fails the moment its ledger exists. That is Phase C's forcing function against repeating the pattern. - docs/research/distinct-evidence-audit-2026-07-25.md -- full audit + the open outcome-mix ruling for Shay. - ADR-0264 R9 amended with the measured exposure. Decision key is case TEXT deliberately: a tighter key (normalized atom) would collapse spelling variants and report MORE inflation, so text-identity under-reports and every number is a floor on the real gap. Outcome mix is deliberately NOT pinned. ClassTally has no verdict axis, the deduction producer already balances 240/240/240 by construction, and imposing a per-verdict-class floor would retroactively fail all 25 bands on a criterion no ADR has ratified (smallest per-band class count is 120). Recorded for a ruling with numbers instead. [Verification]: uv sync --locked on canonical CPython 3.12.13; in-worktree smoke 569 passed (556 baseline + 13), deductive 285 passed. Registered in the `smoke` curated suite -- not left to `full`, which gates nothing. Mutation- checked: doubling CASES_PER_BAND -> 2 failed; reporting committed as distinct -> 4 failed; gating on `claimed` instead of `honest` -> 3 failed; tree restores to 13 passed. |
||
|---|---|---|
| .. | ||
| adr | ||
| agents/grok | ||
| analysis | ||
| architecture | ||
| audit | ||
| benchmarks | ||
| briefs | ||
| curriculum | ||
| decisions | ||
| evals | ||
| examples | ||
| handoff | ||
| handoffs | ||
| implementation | ||
| issues | ||
| lab | ||
| outreach | ||
| paradigm-archive | ||
| plans | ||
| research | ||
| sessions | ||
| specs | ||
| workbench | ||
| zig | ||
| 3lang-depth-pr-plan.md | ||
| admissibility-exemplars.md | ||
| ci-optimization.md | ||
| core-rd-base-prompts.md | ||
| ethics_packs.md | ||
| EVAL_AUDIT_2026-05-20.md | ||
| eval_methodology.md | ||
| frontier_baselines.md | ||
| gaps.md | ||
| handoff_template.md | ||
| hitl-backpressure.md | ||
| holdout_recipients.txt | ||
| identity_packs.md | ||
| master-plan-post-substrate-audit.md | ||
| memo.html | ||
| model_dependency_size_tally.md | ||
| pack_inventory_2026-05-21.md | ||
| position_paper.md | ||
| PROGRESS.md | ||
| README.md | ||
| recognizer-registry.md | ||
| refusal-taxonomy.md | ||
| reviewers.yaml | ||
| RUST.md | ||
| safety_packs.md | ||
| sponsors.md | ||
| teaching_order.md | ||
| test-debt-quarantine.md | ||
| testing-lanes.md | ||
| Whitepaper.md | ||
| Yellowpaper.md | ||
CORE Documentation Index
This is the central index for all documentation in the CORE project.
Canonical Root Documents
- Whitepaper.md - The CORE architectural and philosophical whitepaper.
- Yellowpaper.md - Technical specifications and mathematical formulation of the CORE engine.
- PROGRESS.md - High-level project progress tracking.
- specs/runtime_contracts.md - Critical invariants and bounds for the runtime execution flow.
Directories
Architecture & Design
- adr/ - Architecture Decision Records (ADRs). The canonical history of all ratified engineering choices.
- architecture/ - High-level architectural documents (e.g., pipelines, schemas).
- analysis/ - Deep dives and master plans for structural changes.
- specs/ - Detailed technical specifications and invariants.
Planning & Progress
- plans/ - Capability roadmaps and implementation plans.
- briefs/ - Project briefs and scoping documents for upcoming work.
- issues/ - Detailed issue analyses and technical reproductions (not standard trackers).
- audit/ - Audit reports and claims ledgers.
Operations & Usage
- examples/ - Usage examples and reference integrations.
- workbench/ - Documentation for the CORE workbench UI and related tooling.
- agents/ - Agent-specific operational guides.
Note regarding
agents/grok/: Operational guide for using Grok 4.3 + Grok Build with CORE. This is not architecture documentation.
Learning & Evaluation
- curriculum/ - Documentation on the teaching/learning order and knowledge progression.
- evals/ - Evaluation methodology and performance criteria documentation.
- benchmarks/ - Benchmark evidence and performance tracking logs.
Historical & Experimental
- sessions/ - Chronological session logs documenting the "decision trail" and intellectual history of major choices.
- handoffs/ - Legacy brief, audit, and investigation notes (historical; the formal HANDOFF mechanism is retired — see AGENTS.md for the current lightweight
session-break-summary-<DATETIME>.mdconvention). - research/ - Raw research notes and preliminary findings.
- lab/ - Experimental content (Warning: Not ratified; must not be referenced as authoritative in production PRs).