core/docs
Claude a4f567f097
docs(plans,assessment): G-24 — the perception diagnosis, and the Perception Arc plan
Why capability has not moved despite everything being implemented, answered by
measurement rather than opinion, at 0e1be8be:

  F-A  The serving path is 100% symbolic. reader.py (490), proof_chain (3,916),
       both surface composers: zero geometric references. All served capability
       comes from a template parser feeding an ROBDD engine.
  F-B  The reader INVERTS its own ratified design. ADR-0252 §2 stage 1
       prescribes containment/transfer/accumulation/comparison and bans
       surface-slot regexes verbatim; the implementation is surface-slot
       regexes over categorical/member/ordering/propositional. Corpus agrees:
       1.28% read rate, possession/transfer/quantity absent, if/then (0.1% of
       sentences) holding 21% of the inventory.
  F-C  Template architecture cannot produce chunk lifts — each construction is
       one hand-fitted rule; generalization is zero by construction. This is
       why lifts have only ever arrived as overfit slivers.
  F-D  Geometry does exactly two cognitive jobs and both are stranded:
       salience->attention (bypassed by every licensed lane) and
       relation_compiler's Hamiltonian ground-state solver (off-serving,
       behind a 1.0% math reader). Real geometric computation exists — it
       "NEVER evaluates scale*input+offset in Python" — and nothing feeds it.
  F-E  The §5 NO-GO killed alignment-on-points-under-similarity. The
       composition branch — relations as OPERATORS, meaning as composition,
       the pattern relation_compiler already embodies — was never tested.

Plan: docs/plans/2026-07-28-perception-arc.md. Phase 0 pins the 1.28%/1.0%
read-rate floors as the metric the arc is accountable to. Phase 1 is a
§5-shaped pre-registered GO/NO-GO on hypothesis H2 (compositional
core-primitive reading over operator encodings; NO-GO branch declared: a
principled compositional grammar instead — either verdict exits the template
treadmill). Phase 2 builds ONE perception layer as combinator core + declared
construction lexicon, so coverage growth is table rows, not parsers. Phase 3
reconnects the Hamiltonian corridor to serving through the now-honest licence
machinery. Phase 4 deletes what earned it: G-3's template-widening program
superseded, curriculum-serve machinery parked. Phase 5 prepares the ADR-0252
amendment and the use_salience ruling for one-word decisions.

Explicitly untouched: core/physics, the algebra, the reliability gate, the
ledger discipline — correct and load-bearing. The enumerative reader stays
serving until its replacement proves out: supersession-in-place, per the ADR's
own preserved rule.

G-24 registered Tier A. G-3 as previously specified is superseded, recorded in
the execution plan's closing addendum rather than silently.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Wcw2pnMBwyvmNyQg4uPEt4
2026-07-28 17:02:53 +00:00
..
adr feat(ledger,tests,adr): PR-14 — the outcome-mix rule, and the four expected licences dissolve under it (R-8) 2026-07-28 07:59:01 +00:00
agents/grok
analysis feat(coherence): grounded-open hedge arm — serve pack surfaces honestly hedged instead of over-refusing (ADR-0254) 2026-07-23 01:27:17 -07:00
arc docs(arc): the commit index and rollback map for the assessment arc 2026-07-28 12:07:43 +00:00
architecture docs: apply the Wave 0 record amendments that need no ruling (N-1…N-7, H-12) 2026-07-27 17:38:12 -07:00
assessment docs(plans,assessment): G-24 — the perception diagnosis, and the Perception Arc plan 2026-07-28 17:02:53 +00:00
audit feat(wave-1): retire the dead instruments, delete the aliases nobody calls (PR-3, PR-3b, R-7) 2026-07-28 05:40:45 +00:00
benchmarks
briefs docs(governance): weekly-audit rulings T1/T7/T8/T9 — INV-32/33/34 registration, ADR-0243 fold, residual escalation, path sweep, prune ledger 2026-07-22 19:18:59 -07:00
curriculum
decisions
evals
examples
handoff docs(arc): reconcile the arc's records with what the units measured 2026-07-26 12:33:30 -07:00
handoffs
implementation
issues fix(tests): session-scoped engine-state isolation baseline — close module-scope escape to the live life-store 2026-07-22 20:32:06 -07:00
lab
outreach
paradigm-archive
plans docs(plans,assessment): G-24 — the perception diagnosis, and the Perception Arc plan 2026-07-28 17:02:53 +00:00
research feat(config,specs,tests): PR-5 — the flag register, profiles as units, and the daemon's missing fourth flag (R-3 + R-4) 2026-07-28 06:47:21 +00:00
sessions
specs docs(specs): the four posture statements — and R-11's measurement dissolves its own question 2026-07-28 08:26:48 +00:00
workbench docs(governance): weekly-audit rulings T1/T7/T8/T9 — INV-32/33/34 registration, ADR-0243 fold, residual escalation, path sweep, prune ledger 2026-07-22 19:18:59 -07:00
zig
3lang-depth-pr-plan.md
admissibility-exemplars.md
ci-optimization.md
conceptualizing_engineering_mastery.md docs(assessment): Phase 0 — ground truth, corpus triage, and the Phase 1 handoff 2026-07-27 15:19:54 -07:00
core-rd-base-prompts.md
ethics_packs.md
EVAL_AUDIT_2026-05-20.md
eval_methodology.md
frontier_baselines.md
gaps.md feat(wave-1): retire the dead instruments, delete the aliases nobody calls (PR-3, PR-3b, R-7) 2026-07-28 05:40:45 +00:00
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 chore: Refactor CLI and Governance Anchors (#926) 2026-07-03 12:34:56 -07:00
sponsors.md docs: remove unestablished NSF SBIR and DARPA claims from Path B 2026-06-25 14:36:12 -07:00
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

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>.md convention).
  • research/ - Raw research notes and preliminary findings.
  • lab/ - Experimental content (Warning: Not ratified; must not be referenced as authoritative in production PRs).

External

  • outreach/ - External communications and messaging.
  • zig/ - Scoped documentation for the Zig language components.