f79fec9e63
Production-line brief pack for the three independent Phase 3 wiring lanes, each grounded in fresh read-only research against the current worktree (not assumed from the plan text): - Lane A (discovery wiring): is_discovery_eligible + cross_band_discovery_gate -> DiscoveryCandidate via the contemplation runner's existing sink; live caller for propose_kappa_line_search so kappa_search_event fires. Flags a real open question (what feeds surprise_norm for a contemplation finding) rather than guessing. - Lane B (sensorium corridor eval): first live consumer of the I-04 feed — real Audio/Vision compilers -> cognitive_lifecycle -> readback -> GoldTether, shaped like the adr_0242_v2_energy_compare fixed-replay template. - Lane C (biography wiring): ADR-0240 harness PASS -> integrate_biography with I-01 closure asserts and provenance recording. Flags a genuine identity-substrate design question (mutation vs. proposal-only) for Shay rather than picking silently. Corrected dependency DAG: only Lane B actually depends on Phase 2's cognitive_lifecycle module landing. Lanes A and C touch zero Phase-2 code — every symbol they wire already exists on forgejo/main — so they can start immediately, in parallel with Phase 2's own review, rather than waiting. Also fixes a stale claim this research caught: the plan's substrate table (Sec 2) named packs/en/readback_rules.py as already-landed §2.3 readback rules. That file was deleted under audit ratchet W-006; the live substitute is generate/realizer.py:energy_modulated_surface. Corrected in place. Per standing production-line-pattern + no-self-dispatch doctrine: brief pack only, dispatch is Shay's call. [Verification]: docs-only change, no code touched; no test suite affected. |
||
|---|---|---|
| .. | ||
| adr | ||
| agents/grok | ||
| analysis | ||
| architecture | ||
| audit | ||
| benchmarks | ||
| briefs | ||
| curriculum | ||
| decisions | ||
| evals | ||
| examples | ||
| handoff | ||
| handoffs | ||
| implementation | ||
| issues | ||
| lab | ||
| outreach | ||
| 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).