core/docs/analysis
Shay 7cb826a548 feat(determine): calibrated disclosed estimation — the engine earns the right to guess (Step E)
The final AGI-spine step (A INSTRUMENT → B WIRE → C DEEPEN → D CLOSE → E ESTIMATION).
The engine may now SERVE a DISCLOSED estimate for a query it would otherwise refuse —
but only for a predicate-class that has measured itself reliable, and never as fact.

This executes the ADR-0206 §5 cognition-path widening: the bridge's LICENSE node
(reliability_gate.license_for), previously "built — not yet called from serving", is now
called. govern_response returns APPROXIMATE iff a genuine licensed Action.SERVE
LicenseDecision is passed (STRICT for every other input — so every existing serving call
site is byte-identical); shape_surface DISCLOSES the estimate as "[approximate] …".

Mechanism:
- generate/determine/estimate.py — a BLIND converse-guesser: told p(a,b), asked p(b,a),
  it commits the converse. It never reads the pack's symmetry metadata; whether the guess
  is right is MEASURED, not assumed.
- evals/determination_estimation/ — the gold lane: run_practice (sealed, ADR-0199) folds
  the converse-guesser over symmetric (sibling_of) vs directed (parent_of) cases, scored
  against the pack's graph.edge.symmetric truth (gold independent of the solver). The gate
  DISCRIMINATES: sibling_of earns SERVE (660 correct → Wilson floor 0.990046 ≥ θ_SERVE),
  parent_of does not (660 wrong → 0.0). The license is earned by VOLUME — 657 perfect
  commits is the exact θ_SERVE=0.99 threshold (656 is below).
- generate/determine/data/estimation_ledger.json — the ratified committed ledger,
  hash-verified on load (a hand-edited ledger raises RatifiedLedgerError); it IS the
  deterministic sealed-practice output (a GSM8K-style --check test pins this).
- chat/runtime.py — when a converse query is refused and the class holds a SERVE license,
  the disclosed estimate is surfaced through the bridge (gated by config.estimation_enabled,
  default OFF; only meaningful with accrue_realized_knowledge).

Invariants:
- wrong=0 by construction — an estimate is ALWAYS disclosed ([approximate]), never a silent
  commit (UNVERIFIED_POSSIBLE is never in APPROXIMATE's admissible set), and only a genuine
  ratified license widens (a forged {"licensed":True} dict / a PROPOSE license / an
  unlicensed SERVE all stay STRICT). Defense-in-depth: type-gate ∧ admissible-set ∧
  hardcoded disclosed state.
- never self-authored — ceilings stay at safe defaults (θ_SERVE=0.99); the engine cannot
  raise its own bar. The ledger is sealed practice, hash-verified.
- session/serving only — no corpus/pack/identity/proposal/vault mutation; the HITL teaching
  path is untouched. Deterministic; no clock/random.
- byte-identical for every non-E turn (the 2643 govern_response call passes no license).

Out of scope (separate ADR-0206 §5 PRs): the math-serving seam (select_self_verified,
touches the sealed metric), SITUATE (stakes), and the live FEED-BACK loop.

Verified green: smoke (90), architectural invariants (56), response_governance (321,
incl. the new license-gated widening test), the determination-estimation lane (12), and
the B/D/determine regression net. Four-lens adversarial review (disclosure/wrong=0,
calibration integrity, byte-identity, boundary/determinism): all held. Design:
docs/analysis/E-estimation-design-2026-06-06.md.
2026-06-06 13:49:07 -07:00
..
AGI-candidacy-autonomous-improvement-roadmap-2026-06-05.md docs(design): L10/L11 lived-spine design records + AGI-candidacy roadmap 2026-06-05 15:11:08 -07:00
composition-capability-scope.md docs: mark ADR-0174 Phase 5a shipped in composition-capability-scope 2026-06-03 16:23:53 -07:00
composition-wall-execution-plan-2026-06-03.md feat(r4): flip cv-0005 to serving — train_sample 6/44/0 -> 7/43/0 (ADR-0207 §5 step 2) 2026-06-03 22:20:12 -07:00
comprehension-primitive-inventory.md
D-close-consolidation-design-2026-06-06.md feat(determine): idle deductive consolidation — the loop learns from determined facts (Step D) 2026-06-06 12:28:09 -07:00
deductive-logic-phase-2-benchmark-runway-2026-06-04.md docs: session record (2026-06-04) + mark runway PR-1/PR-2 shipped 2026-06-04 16:54:03 -07:00
E-estimation-design-2026-06-06.md feat(determine): calibrated disclosed estimation — the engine earns the right to guess (Step E) 2026-06-06 13:49:07 -07:00
extraction-richness-audit-2026-06-03.md docs: ratify ADR-0207 — GSM8K comprehension/composition substrate 2026-06-03 19:42:47 -07:00
field-reasoner-wedge-design-and-falsification-2026-06-04.md docs: field-reasoner wedge design + falsification dossier 2026-06-04 19:22:16 -07:00
field-wedge-ablation-result-2026-06-04.md feat(field-wedge): ablation verdict — field is decoration on additive (C3) (Phase W.2) 2026-06-04 19:44:22 -07:00
gsm8k-lift-program-strategy-2026-06-04.md fix(gsm8k): disable unsound serving bridges — restore sealed wrong=0 (0/5 -> 0/0) 2026-06-04 01:55:05 -07:00
L10-continuity-spike-design-2026-06-05.md docs(design): L10/L11 lived-spine design records + AGI-candidacy roadmap 2026-06-05 15:11:08 -07:00
L10-runtime-scoping-2026-06-05.md docs(design): L10/L11 lived-spine design records + AGI-candidacy roadmap 2026-06-05 15:11:08 -07:00
L10-shapeBplus-persistence-scope-2026-06-05.md docs(design): L10/L11 lived-spine design records + AGI-candidacy roadmap 2026-06-05 15:11:08 -07:00
oov-grounding-determinism-morphology-affinity-collapse.md fix: derive oov grounding from token content 2026-06-06 05:46:01 -07:00
phase2-general-comprehension-organ-scope-2026-06-05.md docs(analysis): Phase 2 spike — syntax pack is not a parser; structural-decode fork 2026-06-05 15:41:36 -07:00
pivot-to-deductive-logic-2026-06-04.md feat: ratify independent-gold invariant (INV-25) + SHA-pin deductive lane 2026-06-04 15:56:28 -07:00
question-layer-gap-survey.md
real-gsm8k-capability-measurement-2026-06-04.md docs: fourth lift attempt falsified (strict sum-reader 0/2) — exhaustive 2026-06-04 02:52:24 -07:00
REALIZE-R1-DETERMINE-scope-2026-06-06.md fix(realize): lookback hardening — defensive admissibility re-assertion + coverage 2026-06-06 06:31:54 -07:00
REALIZE-scope-2026-06-06.md docs(analysis): REALIZE phase scope (Step 3) — verified against the real substrate 2026-06-06 01:48:19 -07:00
relational-grounding-extension-2026-06-04.md feat(deductive): binary relations + multi-variable grounding (finite propositional) 2026-06-04 20:17:33 -07:00
solver-operation-coverage.md
universal-structure-and-field-symbol-coherence-gate-2026-06-04.md feat: Phase 2 — finite-entity grounding compiler + Phase 1.5 finding 2026-06-04 16:32:03 -07:00
wiring-promotion-gate-brief-2026-06-03.md docs: composition-wall execution scope (ADR-0207 §5 step 2) 2026-06-03 21:14:02 -07:00