core/evals/long_context_cost/baselines
Shay 283680f110 feat(adr-0044, adr-0045): domain ethics pack + long-context comparison
ADR-0044 — Medical / clinical ethics pack (worked-example domain pack).
Ships packs/ethics/medical_clinical_ethics_v1.json with six commitments
partitioned across all three remediation tiers:
  - refuse: no_dosing_recommendation, no_emergency_triage_authority
  - hedge:  defer_diagnosis_to_clinician, surface_evidence_grade
  - audit:  disclose_no_clinician_relationship, respect_patient_autonomy

Ratified end-to-end through scripts/ratify_ethics_pack.py (PACK_IDS
extended).  Production-mode load via load_ethics_pack succeeds.
ChatRuntime composition includes universal safety floor + every medical
commitment.  tests/test_medical_clinical_ethics_pack.py (8 tests) gates
file existence, sealed report, disjoint refusal/hedge lists, and
pack-swap visibility (default pack does NOT carry medical commitments).

ADR-0045 — Long-context recall: CORE vs transformer baselines.
Adds evals/long_context_cost/comparison_runner.py with a deterministic
needle-in-a-haystack measurement at N ∈ {100, 1_000, 10_000, 100_000}.
CORE recall = 100% at every tested N by exact cga_inner scan.

Paired with frozen citations of published transformer NIAH numbers in
evals/long_context_cost/baselines/transformer_long_context.json:
Claude 2.1 (200k, 50%), GPT-4 Turbo 128k (~71%), Gemini 1.5 Pro (99.7%),
NVIDIA RULER (varies).  Each citation carries source + url.

The two components measure different inputs (synthetic versors vs NL
needles) and are not directly comparable benchmark-for-benchmark.  The
comparison is at the architectural level — exact-scan recall vs
attention-based probabilistic recall.  Scope and limits documented in
the ADR.  tests/test_long_context_comparison.py (5 tests) gates schema,
CORE recall == 100%, and baseline citation presence.

CLI integration: two new demo targets with study-grade preambles.
  - core demo pack-measurements          (ADR-0043 — wired)
  - core demo long-context-comparison    (ADR-0045)
README + docs/PROGRESS.md cheatsheets updated.  docs/decisions/README.md
index extended with ADR-0044 + ADR-0045; pack-layer chain title now
"ADR-0027 through ADR-0045".

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-17 22:31:47 -07:00
..
transformer_long_context.json feat(adr-0044, adr-0045): domain ethics pack + long-context comparison 2026-05-17 22:31:47 -07:00
v1_structural_zero.json feat(phase4): long-context-cost lane + ADR-0019 Stage 1 vault recall vectorisation 2026-05-16 16:39:30 -07:00