Repository navigation
Conversation
Freezes spec §2–§5, the analysis code (stats.rs), the analysis plan and prompt v1 under prereg_sha ef51087dc79b… before any measurement (S-1). New crate aprender-review-experiment (publish = false); harness CLI is an example, not a [[bin]]. Planted §3 edit turns prereg-check and FALSIFY-REX-PREREG-001 RED; restore → GREEN. Receipt: docs/audits/rex-001/rex-00-receipt.md. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…#4356 Phase 0: no declared label admits apr-serve review jobs on any host; cells stay NotRun{NoDeclaredExecutor} until infra#1088 lands. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ation check — Refs #4357 corpus_version review-corpus-v1@787d2026256cc08b. P 50 (cargo-mutants listing, markers stripped), R 50 (revert-the-fix, comment-only hunks dropped), G 50 (green, unreverted, pre-cutoff). 45 dev / 105 test; 70 test defect items. Diffs are outside git (items-v1.tar sha256 70dffe56…). Contracts review-corpus-v1 (FALSIFY-RCV-001..003) and review-corpus-contamination-v1 (FALSIFY-RCC-001..003); planted train leak RED (rc=101) -> GREEN. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…FY-RXR-001..003) — Refs #4358 Harness drives apr serve /v1/chat/completions at greedy/seed 4354/512 tokens, never truncates (context refusal -> NotRun{ContextOverflow}), seeded run order + 10% rerun. Scorer denominators are the EXPECTED item set; raw outputs are sha-checked and the verdict re-parsed. Receipts verify with minisign when --pubkey is given. Three falsifiers planted RED and restored GREEN (docs/audits/rex-001/rex-03-receipt.md). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…03) — 6/6 NotRun{NoDeclaredExecutor}, S-7 — Refs #4359
Every §2.1 cell has exactly one admission row; a silent cell rejects the file, Admitted
needs a parity receipt at or above a cited threshold, and no admitted cell raises S-7
(`rex admission-check` exits 10). With infra#1088 open, all six cells are NotRun, so S-7
fires and the experiment STOPs. The §7 premise "apr parity vs llama.cpp" is false at
v0.69.3 (GPU-vs-CPU only); the oracle is an explicit field. The S-6 operator ruling is
recorded in the receipt.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
`rex score --pilot --split dev` projects the test-split Wilson half-width on recall at the pilot estimate (design p = 0.5 when the pilot has no defect in its denominator) and grows the corpus above 0.12 or when the width cannot be computed. Runtime counts the 10 % re-run; no warm sample is None, not zero. The spec's ~0.117 is the Wald width; the frozen Wilson width is ~0.114. Contract rex-pilot-projection-v1 (FALSIFY-RXP-001..003), each planted RED at pilot_tests.rs:22/:29/:38 and green after restore. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The 4B shadow lane already runs inside the quorum rail (paiml-implement #420, advisory-lane.sh); `rex ledger` reads what it records in each quorum receipt and holds it to REX-07: every quorum carries a shadow row (no advisory_lane, or lane `off`, is missing), a lane that did not answer is Unknown{LaneUnavailable}, and the shadow is uncounted and leaves the width at the counted lanes. On the live PMAT-405 receipt it emits a correct row (gx10-cuda PASS, width 3) and exits 0. Contract review-ledger-v1, FALSIFY-RXL-001..003 each planted RED at ledger_tests.rs:49/:66/:85 and green after restore. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
) `rex ladder REPORT_JSON` reads only a locked, confirmatory rex-001-report-v1 and returns the 4B lane's rung: shadow by default, tripwire on H4 (explicit holds + CI lower bound ≥ 0), vote on H4 ∧ H5, capped by the §4.5 hardware ruling. H5 alone stays shadow (R-11). Contract rex-promotion-ladder-v1; FALSIFY-RXG-001..003 each planted RED at ladder_tests.rs:31/:55/:72 and green after restore. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…g is RED (Refs #4365) review-lane-perf-ratchet-v1 (§5.1). `rex ratchet record` turns a tag's warm, non-rerun receipts on the primary cell into per-item wall times; `rex ratchet check` arms after 3 tags and compares each later tag with the best earlier one by a paired bootstrap of the Harrell–Davis p95 ratio (ALPHA from the prereg). Exit 10 on RED. Finding (FALSIFY-RXR-002): the §4 unpaired CI-overlap rule, and a paired nearest-rank p95, both miss a planted +10% at n=130; the HD paired rule catches it 40/40 with 0/40 false alarms at 3% per-item run noise. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…#4366) - champion.rs: five fail-closed §5.4 gates, 20 evaluations per sealed test version (refusals spend nothing, R-6), pin-bump promotion with rollback sha, two-consecutive-gold-escape demotion. - fewshot.rs: B1b retrieval from non-test gold only (R-2), never the query; guard() scans each fenced block alone. Finding: a gold `- defect at` line after a fence joins the last hunk, so a whole-text scan missed a sealed test diff in a rendered prompt (RXF-003 pins it). - `rex challenge` (exit 0 promoted / 10 rejected / 11 refused); score_cmd uses verify_signed. - contracts/review-champion-challenger-v1.yaml (RXC-001..003, RXF-001..003). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…pt (Refs #4367) - b2.rs: one review-b2-loop-v1 row per B2 tier from the refusal ledger (refusal-receipt-v1): ready only on an acceptance receipt, verb_refused on a ledger row, unledgered otherwise — an absent refusal is not acceptance. teacher_receipt(): sha, count, k, m=1, 0 test hits over the non-test pool; fails closed on an empty sealed index. - `rex b2 status|teacher-receipt` (status exits 11 while any row is NotRun). - contracts/review-b2-loop-v1.yaml (FALSIFY-RXB-001..003). - At HEAD all four rows read unledgered: distill/finetune/merge/quantize have no measured qwen35 refusal row (EPIC #4002 owns the verbs). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…t dispatch time only (Refs #4354) Operator ruling 2026-09-25 (cop-inbox/handoff/ruling-r9-b.md, sha b6db6866c604). lambda-cuda may run the apr SHADOW lane only as rung 2: rung 1 (gx10-cuda) returned NotRun and the GPU lock is free at dispatch. No resident serve, no preloaded weights, no REX cells, no teacher/finetune jobs; other R-9 exclusions stand. A lock taken mid-round = NotRun{Busy}, ladder continues, no retry on the same cell. Fallback order gx10-cuda -> lambda-cuda -> intel-wgpu -> mini-metal -> intel-cpu -> NotRun{NoExecutor}. S-4, G7 and the lambda-minutes metric follow R-9. R-9 is §6, outside the §2-§5 prereg span: FALSIFY-REX-PREREG-001..003 pass, the lock is unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ha carried; holds() needs identity_gaps == 0 (Refs #4354) - Shadow is now Verdict{verdict,cell,backend} | NotRun(NoExecutor|Busy| Timeout|ContextOverflow|TrainActive) | Refused{cell,removed_by: ladder|gpu-proof|parse}, deny_unknown_fields. Unknown::LaneUnavailable {why: free text} is gone: one spelling with receipt-lint. - The receipt's advisory_lane.row carries it; a missing or unparsable row is a violation, never a silent Unknown. - weights_sha256 is read from the receipt, and Coverage::holds() requires identity_gaps == 0. - FALSIFY-RXL-004 (no weights sha => holds() false) and RXL-005 (free-text reason fails to parse), each killed by its mutant (holds() clause dropped; deny_unknown_fields dropped). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…a row (Refs #4354) Operator ruling PRM-001 v2 items 3, 4 and 6 (cop-inbox/handoff/ruling-prm-v2.md). v1 was locked with 0 data rows, so nothing becomes exploratory (R-1). Locked (§3-§4, stats.rs, analysis plan): - H1 = VERDICT identity across cells (verdict_divergence); bytes descriptive. - H4 = one rule: paired bootstrap of p4B - min(pHaiku, pAgy), min taken inside each resample (bootstrap_vs_min_voter); Holm-adjusted one-sided p decides, CI report-only. ladder.rs reads p_holm (report schema v2). - H5 decided on class-R recall only; per-class P/R recall + precision descriptive (paired_parsed_class; Scored carries its class). - §4.1 admission oracle = the cell's parity.oracle; llama.cpp@d1d3c3396 where declared (#4444), else apr-parity-gpu-cpu + H1 verdict check. - §4.6 train-active falls through the dispatch ladder, never blocks; lane rows use the #436 Verdict|NotRun|Refused spelling. - κ on per-item errors, apr vs each voter (error_kappa, kappa_andon). Unlocked: §0.4/R-11 zero-weight shadow; R-9/S-4/§9.1 lambda accounting (experiment cells, teacher, resident serve: 0 min; shadow rung 2 measured). Falsifiers: min-inside-resample differs from pick-once on tied voters; byte-only diff does not reject H1; RXG-004 CI is report-only; prereg 001-003. 90/90 lib tests; pv validate both contracts; clippy -D warnings clean. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ith the cop's pending-instrument ruling; §9 report IN_PROGRESS Spec copied from the cop handoff (sha e8764b72adbe) and amended with §1.1: T0 found none of the §1 verify commands exist; G1/G7/G10/G11/G13 are [U]-pending-instrument tied to T1/T10/T1/T6/T16; G2/G4 are #436 scope; G12's command replaced (apr has no --model-arch). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…, fails closed Five fleet hosts, 2026-09-25: cleanupPeriodDays 36500 on all five; files older than 30 d lambda-labs 3278, intel 290, gx10 1, mini 0, yoga 0 (matches infra#1135 T0). An unreachable host prints UNREACHABLE and exits 1. Case table: unset/numeric/no-settings key, planted old file. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Ruling agent-trace item 6. FALSIFY-TPA-001 (planted AWS key quarantined) and TPA-002 (planted test-split diff refused) fail 4/4 against admit() admitting everything. Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
…aled-test hit refuses Ruling agent-trace item 6. src/pool.rs: admit() gives each JSONL row one verdict. Admitted | Quarantined (secret hit, held byte-identical, never redacted) | Refused (sealed-test diff or sha, via contamination::Index, checked first) | Unchecked (empty sealed index admits nothing). The scanner has no regex dependency, scans JSON-unescaped strings, and uses whole-word prefixes. Contract training-pool-admission-v1 (TPA-001..004; pv validate: 0 errors). RED->GREEN: 4/4 fail on the stub at b177c3af8, 4/4 pass here; crate lib 87/87; clippy -D warnings clean. Mutants killed: no-unescape, no-refuse, no-quarantine, empty-index-admits, no-boundary. Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
… reports nothing PRA-001 T6. Secret scan = union of builtin detectors and the gitleaks v8.30.1 ruleset vendored verbatim as data (MIT, sha256-pinned), interpreted in-process in Rust. 20 run-time-built canaries, per-rule ablation, AWS doc key (gitleaks-allowlisted) caught by builtin only. Contract renamed from training-pool-admission-v1. This commit's scan() clears its hits: TAS-001/003/004 and both case tables are RED (5 failed, 91 passed). Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Refs #4354
scan() returns its hits. Mutation table (tests run: secret + pool): killed no-gitleaks, no-builtin, no-allowlists, no-entropy, no-unescape, no-translate, and-allows; survived no-keywords (equivalent: the keyword prefilter is a speed-up, every upstream regex already requires its keyword). Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Refs #4354
…ash-only index PRA-001 T7. FALSIFY-RCC-004 plants a sealed diff with whitespace, blank-line, partial-rename and re-base perturbation into a candidate pool. The exact checks (diff sha, hunk sha) miss it; the Index stores sketches but does not scan them yet, so RCC-004 is red (110/111). cluster.rs (MOSS-normalised 12-token shingles, bottom-64 MinHash, 0.7 containment), RCC-005/006 and the contract v1.1 land here with it. Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
…item is refused PRA-001 T7. Index::scan now checks each text's shingles against the sealed sketches: >= 0.7 of an item's bottom-64 sketch present is a `cluster` hit, so the perturbed sealed item is Refused at pool admission (111/111). False-positive probe, 391 real .rs commit diffs from origin/main, all 152,490 ordered pairs: 7 clustered at k=12 (0.005%), all one family of templated beat test files (copies with renamed identifiers); k=5 gave 469. Mutation table: whitespace skip, rename, header skip, marker, min-shingles, blank-line skip, threshold and scan removal are all killed. Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
…pend-only outcome joins; v1 rows still read (Refs #4354) v1 kept each counted lane's findings as a count, so every quorum lost its (input, output, findings) triple. v2 keeps the text verbatim and the lane's agent-trace-v1 input/output shas. Text that was never captured is None, a trace gap, never an empty list that would train as 'no issues'. - read_row dispatches on schema; both v1 shapes written under that name (402aff8 tagged shadow, 89d994b typed #436 shadow) still parse. - v1::Row::migrate keeps the count, leaves text/shas None, and refuses a legacy shadow (no cell/backend, so no typed #436 form). - OutcomeJoin: the latest join by at wins; the row is never rewritten. - contracts/review-ledger-v2.yaml carries FALSIFY-RXL-001..008; v1's stale Unknown{LaneUnavailable} equation now points at the typed form. Mutants killed (3/3): migrate invents Some(vec![]), trace_gap ignores missing text, an unknown schema read as v1. Crate lib 103/103, clippy -D warnings clean. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Top-k=20 teacher-logit blob per PRA-001 §2.7: u32 ids, T=1 log-softmax (f16), logsumexp_full (f32), retained mass M (f16) so 1−M is the true tail. Closed JSON header, zstd LE columns, one shared validator for encode and decode. Raw 130 B/token at k=20; encoded M6 needs real apr serve rows (top-k capture not yet in apr serve). FALSIFY-SPL-001..004 in contracts/sparse-logits-v1.yaml. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…te in a valid frame) (Refs #4354) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…independence-v1) New module kappa_probe.rs (stats.rs, spec §2–§5 and analysis-plan.md are untouched: prereg-locked). κ_err = the frozen stats::error_kappa on per-item error indicators vs GOLD, shadow lane vs every counted lane, over matured gold rows of one split. Unparsed verdicts, silver/pending/quarantined rows and pending/closed_unmerged outcomes are excluded, never counted as errors. A pair under min_n, or with κ undefined, is `insufficient` and prints no number. `rex lane-kappa` prints the scoreboard; with --candidate it gates: δ and min_n come only from the run manifest's lane_independence block, registered strictly before training started. Exit 12 = S-14 andon (κ rise > δ on any counted lane, a lane missing or insufficient on either side, an unusable manifest, or --candidate without --manifest). FALSIFY-LIND-001..004 were planted RED against a stub (4/4 failed), then GREEN. Four mutants each kill the falsifier they target: gate `>`→`>=` (003), no gold filter (001), registered_at `>=`→`>` (004), gate ignores the manifest's min_n (002; it first survived and got its own assertion). CLI smoke: exit 0 scoreboard, 12 on a voter-copying candidate, 12 with no manifest, 2 usage. `make lane-kappa ROWS=F [SPLIT=val] [MIN_N | MANIFEST CANDIDATE]` wraps it. Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
…g_sha f0b4e4ac) (Refs #4354) - docs/specifications/PRM-001-prometheus.md = handoff v3, sha256 c9b52d08d7eb. - rex-prereg-v2 now locks v3 §2–§5 + stats.rs + analysis plan v2 + prompt v1 in docs/audits/prm-001/prereg.lock. The 17:09Z draft lock (1f4acb3d) is void. - v1 lock docs/audits/rex-001/prereg.lock (ef51087d) restored byte-exact from 5f0ae10 and never edited again (operator). The v1 spec §2–§5 and v1 plan are restored byte-exact too; FALSIFY-REX-PREREG-004 keeps them verifying. - v1 spec gains a superseded banner above §0 (outside §2–§5). - stats.rs: H7 max-pair gate `h7_holds` (δ-free, undecided on any undefined κ); the v2 silver-step `kappa_andon` is removed (v3 has no silver pool). - A planted §3 edit on disk: `rex prereg-check` rc=1 (DRIFT spec_s2_s5). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
# Conflicts: # README.md # contracts/census.json
… own cluster (Refs #4354) FALSIFY-TDD-001..004 fail 4/4 against the one-cluster-per-item stub. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
… fingerprint, closed by union-find, named by earliest member (Refs #4354) Reuses cluster.rs (shingles, bottom-64 sketch, containment); no second MinHash. Candidates from an inverted index over sketch hashes; a pair matches when either sketch is >=0.7 contained in the other's shingles. Tiny diffs merge only on identical normalised tokens. Cluster id = min (at, id), order-independent, for the PRM-C9 split guard. FALSIFY-TDD-001..004 GREEN; TDD-003's chain asserts X!~Z as its premise. Mutants 8/9 killed; survivor >= -> > on the 0.7 threshold is boundary-equivalent on these fixtures. pv validate: 0 errors. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…et per index snapshot (Refs #4354) datacard::Snapshot reads index/agent-trace-v1/YYYY/MM/DD.jsonl in path order; a bad line or foreign schema is an error naming file:line, never a skipped row. The snapshot id is sha256(sha256sum manifest)[..16]. croissant() emits the Croissant 1.0 + RAI 1.0 JSON-LD card (aggregate counts only), datasheet() the seven-section Datasheet, write_snapshot() both plus the manifest under datacard/<snapshot>/: idempotent, and a hand-edited card is refused, not overwritten. validate() is a structural Croissant checker in Rust, since mlcroissant is Python (S-PY). Public-eligible = gold ∧ local ∧ secret-clean. FALSIFY-TDC-001..006 green; pv validate clean. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ide the datacard (Refs #4354) PRM-001 v2 folds PRA T14 into PRM-C14, which adds the weekly receipt. Per ISO week it records quorums/day, rows, index bytes and the CAS blobs the rows address: stored bytes, plus raw bytes read from the zstd frame header (RFC 8878). It checks them against the G15 [O] band (50-200 quorums/day, <= 0.45 TB/yr raw): within | outside | unmeasured. A missing blob or an undeclared raw size reads unmeasured, never within. weekly.json is written with the card under the same hand-edit rule. FALSIFY-TDC-007/008. These were written after the code, not RED-first; their RED proof is 10 hand mutants: 9 killed at first, and the survivor (the TB/yr cap had no case) is killed by the added 4.29 GB/day row. TDC-006 now also pins 'bad json'. For TDC-001..006, 10 of 12 mutants were killed; skip-bad and leak are equivalent (still refused / Snapshot keeps no row content). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
v3 renumbered the gates (G15 is now the branch row). The receipt's key, constants, contract text and test name follow. Refs #4354 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…figure research-design-pr-agent-qwen-3.5.md gains a SUPERSEDED banner pointing at PRM-001 v3; its body is unchanged. The figure is the operator's v3 export (PROMETHEUS-v3-dark-4k.png, sha256 078be9ce93b7…). The spec text is authoritative over the figure's known caption deltas. Refs #4354 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…l-excluding pool rebuild (Refs #4354, #4446) terms.rs validates provider, exact model_id (no family alias; local = weights sha256), access_channel consistent with provider, and terms_ref {https url, date, UTC fetched_at}. rebuild() takes first-class --exclude-provider / --exclude-channel args; a row with any gap is refused by every rebuild. public_release() keeps local rows only (§2.11). Not legal advice; S-6 governs. 7/7 terms tests, clippy -D warnings clean, pv validate ok; 10/10 planted mutants killed (sha length, https, month range, UTC Z, refused->kept, public-release google, alias rule, channel/provider check, channel exclusion, vertex mapping). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…st be refused; stub admits all FALSIFY-TAP-001..004 against a provenance() that returns Ok: 4 fail. Reuses PRM-C12 terms.rs (tags, Provider). label_source is a provisional gold marker pending PRM-C10. Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
…-gold rows before the secret scan
Verdict::Ineligible(Prov{Hosted,Untagged,NotGold}); provenance() runs after the
sealed check and before quarantine, so a hosted row is never quarantined (and
never released from it). Mutants killed: no-prov, no-hosted-first, any-label,
untagged-ok, notjson-ok, prov-after-secret.
Refs #4354
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
… lane, strata weights over distinct diffs Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
…p, one-rung steps (FALSIFY-RXG-005..008) 7 of 9 ladder tests fail on the stub. Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
…ability ≥ 0.95, speed), vote on 20 agreeing tie-breaks, lambda S-4 cap, one-rung steps rex ladder REPORT_JSON [--current RUNG]. 9/9 ladder tests, 159 lib tests, clippy -D warnings clean, 26/26 hand mutants killed. Refs #4354 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Refs #4354 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Refs #4354 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…1858) Caught by the PMAT-4354 degraded-quorum sonnet lane: six contracts added on rex/001 after the main merge were missing from census.json and README. Refs #4354 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
noahgift
enabled auto-merge
September 25, 2026 19:47
|
§13.11 rung 1 — quorum shadow verdict Shadow mode: this records a verdict and merges nothing. A refusal |
Member
Author
|
Superseded by #4459 (rex/001). The cop ruled at 07:12Z, and aprender-59's audit found prm-l to be an older subset of rex/001: |
auto-merge was automatically disabled
September 26, 2026 08:05
Pull request was closed
Member
Author
|
Correction to the ancestry line above. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PRM-L: land PRM-001 v3 (PROMETHEUS) and the rex/001 work on main
Refs #4354 · ticket PMAT-4354
What lands
docs/specifications/PRM-001-prometheus.md: spec v3, byte-exact with the operator handoff (sha256c9b52d08d7eb…).docs/audits/prm-001/prereg.lock(prereg_sha f0b4e4ac…). It covers PRM-001 §2–§5,stats.rs, the v2 analysis plan and prompt v1.docs/audits/rex-001/prereg.lock(ef51087d…) stays byte-frozen.falsify_rex_prereg_004proves it still verifies.stats::h7_holds: v3 H7 is δ-free. It holds when κ_err(qwen, each voter) ≤ max voter–voter κ_err, and it is undecided when any κ is undefined.review-experiment-protocol.md(above §0; §2–§5 are untouched, so the v1 lock verifies) and onresearch-design-pr-agent-qwen-3.5.md.h7_holds, plus G-PROV admissionrex ladder --current)contracts/census.jsonand the README counts are regenerated: 1858 contracts, 81 workspace crates.Figure
docs/specifications/figures/prometheus-flow.pngis the operator's v3 export (PROMETHEUS-v3-dark-4k.png, sha256078be9ce93b7…).The spec text is authoritative. The figure has three known text deltas against v3; the operator will re-export, and none of them blocks this PR:
Verification
cargo test -p aprender-review-experiment --lib: 155/155 pass. clippy-D warningsis clean, andcargo fmt --checkis clean.rex prereg-checkreturnsrex-prereg-v2 OK prereg_sha=f0b4e4ac…. A planted §3 edit gives DRIFT (rc=1).readme_contract: 16/16.check_readme_claims.shreturns rc=0.cargo deny check advisoriesis ok.fb367bf7fis 3/3 and not degraded: sonnet-5 APPROVE, agy gemini-3.1-pro-high PASS (run from a standalone full clone, away from shared-.git ref churn), haiku-4-5 APPROVE. The receipt is on the private fleet store (PMAT-4354 agy-r4).fb367bf7fand re-verified.No transcripts, trace blobs or secrets are in this diff: data files carry hashes and metadata only.
🤖 Generated with Claude Code