696f62abdd
The word "expert" in the previous status name implied raw-capability parity
with frontier LLMs on the same benchmark — which the gate does NOT verify.
What the gate actually verifies is CORE *claim-shape compliance*:
* signed digest (replay-reproducible from on-disk lane results)
* replay determinism (same inputs → byte-equal trace_hash)
* typed refusal (fabrication refused, not paraphrased)
* exact recall (no ANN, no cosine, no attention bottleneck)
* grounding-source provenance
These are claim shapes a transformer LLM cannot structurally produce
regardless of raw accuracy. A frontier LLM might score higher on the
same benchmark but cannot pass this contract.
Rename scope (semantics only, per ADR-0113):
status string "expert-demo" → "audit-passed"
predicate key predicates.expert_demo → predicates.audit_passed
reason key expert_demo_reason → audit_passed_reason
YAML key expert_demo_claims → audit_passed_claims
CLI command core demo expert → core demo audit-passed
output dir evals/expert_demos/ → evals/audit_passed/
artifact filenames expert_demo.{json,html} → audit_passed.{json,html}
HTML title CORE Expert-Demo: X → CORE Audit-Passed: X
Internal Python identifiers (module/file/function/class names like
`expert_demo.py`, `evaluate_expert_demo`, `ExpertDemoClaim`,
`expert_demo_claim_for`) are deliberately kept to minimize churn. ADR
file titles (ADR-0106..0112) preserved as historical record.
`expert` namespace reserved for ADR-0114+: an actual capability tier
above `audit-passed` backed by a public benchmark with a stated
threshold. ADR-0114 proposes the first such target — GSM8K-math —
laying out a falsifiable 7-phase arc (parser → solver → verifier →
stepped-realizer → eval lane → first `expert` ledger tier promotion).
Tests: 184 directly-affected tests green (140 capability/expert-demo
suite + 34 demo/audit-tour + 10 correction-cue). Smoke suite 67/67.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
45 lines
1.7 KiB
YAML
45 lines
1.7 KiB
YAML
# Reviewer Registry v1 (ADR-0092).
|
|
#
|
|
# This file is parsed by core.capability.reviewers.load_reviewer_registry
|
|
# and consulted by the Domain Pack Contract v1 validator (ADR-0093) to
|
|
# enforce ADR-0091 predicate #8 (reviewer resolution).
|
|
#
|
|
# Adding reviewers is a reviewed proposal flow. Do not edit by hand
|
|
# outside that flow. The bootstrap entry below is self-sealed via its
|
|
# provenance field.
|
|
|
|
schema_version: 1
|
|
reviewers:
|
|
- reviewer_id: shay-j
|
|
display_name: "Joshua Shay"
|
|
role: primary
|
|
domains: ["*"]
|
|
review_scope: ["pack", "proposal", "chain", "eval"]
|
|
provenance: "adr-0092:bootstrap:2026-05-21"
|
|
|
|
# Reviewer-signed audit-passed promotion claims
|
|
# (ADR-0106 / ADR-0109 / renamed by ADR-0113).
|
|
# Each entry carries the canonical evidence-bundle SHA-256 hashed from
|
|
# the on-disk lane result files; re-derivation must reproduce
|
|
# claim_digest byte-for-byte (ADR-0106 §1.5). The audit-passed gate
|
|
# verifies CORE claim-shape compliance (signed digest, replay
|
|
# determinism, typed refusal, exact recall) — claim shapes a
|
|
# transformer LLM cannot structurally produce regardless of raw
|
|
# accuracy. This is NOT a raw-capability claim.
|
|
audit_passed_claims:
|
|
- domain_id: mathematics_logic
|
|
evidence_lanes:
|
|
- elementary_mathematics_ood
|
|
- inference_closure
|
|
- fabrication_control
|
|
evidence_revision: "adr-0110:reviewed:2026-05-22"
|
|
signed_by: shay-j
|
|
claim_digest: "94d74781e103854230c1a71590e4df2287f5d2e87832f1c29b8ec4618853c04b"
|
|
- domain_id: physics
|
|
evidence_lanes:
|
|
- foundational_physics_ood
|
|
- inference_closure
|
|
- fabrication_control
|
|
evidence_revision: "adr-0111:reviewed:2026-05-22"
|
|
signed_by: shay-j
|
|
claim_digest: "a104cad136f3219df05dc7ce6a78437c02f7b5827cd3cdce568db3acda6a43ed"
|