feat(adr-0249): P5 arithmetic lift on real GSM8K + ADR-0249 (arc closure) #70

Merged
core-labs merged 2 commits from feat/adr-0249-p5-instrument into main 2026-07-18 20:15:44 +00:00
Owner

The closing phase of the reader→Hamiltonian compiler arc: it measures the corridor on real GSM8K and lands ADR-0249 (Proposed) with acceptance evidence. P1–P4 are merged (#66–#69); this is P5 + the ratification docs.

P5 — arithmetic-chain lift domain (real data)

evals/generalized_lift_instrument.py gains an arithmetic-chain domain: the corridor's turn-program executor vs a symbolic fold of the same compiled program, over the real GSM8K dev holdout (evals/gsm8k_math/dev, using each case's ground_truth_graph — never the templated cases).

Honest result on the sealed 50-case holdout:

Metric Value
Tier-1 affine ingestible 26 / 50 (52%)
Corridor correct on ingested 26 / 26 — wrong = 0
Corridor vs symbolic fold PARITY (delta = 0)
Refused (multi-entity) 24 / 50 — recorded Tier-2 frontier

This is the honest-NULL protocol working as intended: the corridor solves every real GSM8K problem it can ingest with zero wrong answers, matches the symbolic fold (the field doesn't beat arithmetic at arithmetic — PARITY is honest, not an inflated lift), and honestly refuses the multi-entity remainder. The deliverable is a decidable measurement + recorded real-data coverage. The stale "no reader-to-Hamiltonian compiler exists" scope note is corrected; wrong_zero_guard_held now binds both exact-regime domains (deductive flagship + arithmetic).

ADR-0249 (Proposed — no self-Accept)

docs/adr/ADR-0249-*.md documents the whole arc: the composition-as-certified-turn-sequences thesis, the five components, anti-hollow discipline, the Ring-2 non-mutating correction (the residual protocol is zero-bound, so the turn ledger reuses its chain-integrity pattern, not the admission protocol), the three-tier reproducibility bound, Tier-1 scope + recorded frontier, and the honest-measurement done-when. docs/handoff/ADR-0249-Acceptance-Evidence.md collects the phase SHAs, results, and in-tree verifications. §10 ruling record awaits your ratification.

Governance

Off-serving (A-04); no gate activated (ADR-0246 §3.7 stays uncalibrated); no manifold mutated (I-03); ratified contracts reused, not forked. Every phase smoke-gated green in-worktree.

Tests

tests/test_adr_0249_arithmetic_lift.py10/10 (5 new + 5 existing instrument tests still green). Real-GSM8K wrong=0, every-ingested-case-correct, PARITY-with-symbolic-fold, coverage recorded (26/24 tracked), domain joins the full report + scope corrected.

[Verification]: uv run python -m pytest tests/test_adr_0249_arithmetic_lift.py tests/test_generalized_lift_instrument.py -q → 10 passed; uv run core test --suite smoke -q → 176 passed.

The closing phase of the reader→Hamiltonian compiler arc: it measures the corridor on **real GSM8K** and lands ADR-0249 (Proposed) with acceptance evidence. P1–P4 are merged (#66–#69); this is P5 + the ratification docs. ## P5 — arithmetic-chain lift domain (real data) `evals/generalized_lift_instrument.py` gains an `arithmetic-chain` domain: the corridor's turn-program executor vs a symbolic fold of the **same** compiled program, over the **real GSM8K dev holdout** (`evals/gsm8k_math/dev`, using each case's `ground_truth_graph` — never the templated cases). **Honest result on the sealed 50-case holdout:** | Metric | Value | |---|---| | Tier-1 affine ingestible | 26 / 50 (52%) | | Corridor correct on ingested | 26 / 26 — **wrong = 0** | | Corridor vs symbolic fold | **PARITY** (delta = 0) | | Refused (multi-entity) | 24 / 50 — recorded Tier-2 frontier | This is the honest-NULL protocol working as intended: the corridor solves every real GSM8K problem it can ingest with zero wrong answers, matches the symbolic fold (the field doesn't beat arithmetic at arithmetic — PARITY is honest, not an inflated lift), and honestly refuses the multi-entity remainder. The deliverable is a *decidable measurement* + *recorded real-data coverage*. The stale "no reader-to-Hamiltonian compiler exists" scope note is corrected; `wrong_zero_guard_held` now binds both exact-regime domains (deductive flagship + arithmetic). ## ADR-0249 (Proposed — no self-Accept) `docs/adr/ADR-0249-*.md` documents the whole arc: the composition-as-certified-turn-sequences thesis, the five components, anti-hollow discipline, the **Ring-2 non-mutating correction** (the residual protocol is zero-bound, so the turn ledger reuses its chain-integrity *pattern*, not the admission protocol), the three-tier reproducibility bound, Tier-1 scope + recorded frontier, and the honest-measurement done-when. `docs/handoff/ADR-0249-Acceptance-Evidence.md` collects the phase SHAs, results, and in-tree verifications. §10 ruling record awaits your ratification. ## Governance Off-serving (A-04); no gate activated (ADR-0246 §3.7 stays uncalibrated); no manifold mutated (I-03); ratified contracts reused, not forked. Every phase smoke-gated green in-worktree. ## Tests `tests/test_adr_0249_arithmetic_lift.py` — **10/10** (5 new + 5 existing instrument tests still green). Real-GSM8K wrong=0, every-ingested-case-correct, PARITY-with-symbolic-fold, coverage recorded (26/24 tracked), domain joins the full report + scope corrected. [Verification]: `uv run python -m pytest tests/test_adr_0249_arithmetic_lift.py tests/test_generalized_lift_instrument.py -q` → 10 passed; `uv run core test --suite smoke -q` → 176 passed.
core-labs added 2 commits 2026-07-18 20:10:50 +00:00
Wires the turn-program executor into the generalized-lift instrument and
measures it against the REAL GSM8K dev holdout (evals/gsm8k_math/dev, never the
templated cases), using each problem's ground_truth_graph. Baseline is a
symbolic fold of the SAME compiled turn program: both paths consume identical
problems, the corridor relaxes each step, the baseline folds it numerically.

Honest result on the sealed 50-case dev holdout: 26 problems are Tier-1 affine
single-accumulator ingestible and solved wrong=0; the corridor matches the
symbolic fold on every one (PARITY, delta=0) — the field matches arithmetic, it
does not beat it, so this is real-holdout coverage, NOT a manufactured lift. The
24 refused (all not_single_accumulator / multi-entity) are the recorded Tier-2
frontier, never silently dropped.

Corrects the now-stale scope-limitation note ('no reader-to-Hamiltonian compiler
exists…') — the compiler exists as of this arc; the note now records real-data
Tier-1 coverage and the multi-entity frontier. wrong_zero_guard_held extended to
bind both exact-regime domains (deductive flagship + arithmetic).

10/10 pins (5 new + 5 existing instrument tests still green).

[Verification]: uv run python -m pytest tests/test_adr_0249_arithmetic_lift.py tests/test_generalized_lift_instrument.py -q
ADR-0249 documents the reader→Hamiltonian compiler (P1-P5): thesis (composition
= certified turn sequences), the five components, anti-hollow discipline, the
Ring-2 non-mutating correction, three-tier reproducibility, Tier-1 scope +
recorded frontier, and the honest-measurement done-when. Status Proposed — no
self-Accept; §10 ruling record awaits Shay.

Acceptance evidence: phases + merge SHAs, the real GSM8K dev-holdout result
(26/50 Tier-1 ingestible, wrong=0, PARITY vs symbolic fold, 24 multi-entity
refused = recorded frontier), in-tree algebra + CNF-soundness verification, the
design corrections applied, and the honest open register.
core-labs merged commit 220039f714 into main 2026-07-18 20:15:44 +00:00
core-labs deleted branch feat/adr-0249-p5-instrument 2026-07-18 20:15:47 +00:00
Sign in to join this conversation.
No reviewers
No labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: core-labs/core#70
No description provided.