session 2026-08-08 (late): REVIEWED-102..112 placed; PENDING-119..128 filed; 82+118 closed; drift-check gains built-vs-ruled; verify-quotes promoted

claude/memory/knowledge-graph.jsonl

@@ -627,3 +627,11 @@
 {"subject": "the corpus-to-engine binding surface", "predicate": "has-enumeration-defect", "object": "FOUR SURFACES, NOT THREE. The governed record (graduation-spec.yaml engine_source_binding) names manifest.yaml sha256, sidecars source_sha256, coverage-ledger.json. The READING INDEX is a fourth consumed surface and NOTHING HASHES IT: measured 2026-08-08, content_sha256 occurs 0 times in the Alexander index's 689 lines, source_sha256 occurs 3 times and binds OUTWARD to the canonical text, and the manifest carries only a path plus a prose `reading_index_status`. Consequence: a three-sha checker would have read GREEN for all 56 days of the partial Alexander re-anchor (2026-06-12 to 2026-08-07, chamber 177e2b3). The binding runs index->text; nothing binds to the index.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-08-night-the-checks-were-the-weak-link.md", "extracted_at": "2026-08-08"}
 {"subject": "a differently-positioned reader", "predicate": "drift-pattern-good-direction", "object": "BROKE THE EXECUTOR'S SCOPE WHERE THE EXECUTOR'S OWN CHECKS COULD NOT. The steward supplied one datum the item had not cited (chamber 177e2b3) and required it resolved before ruling. Resolving it produced a THIRD answer neither of the steward's two branches predicted: the commit did not touch the binding surface (so the framing stood) but revealed the enumeration the proposal rested on was incomplete. Second same-day instance of the doctrine's positive case; recorded as evidence, proving nothing general.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 0.9, "source_file": "session-2026-08-08-night-the-checks-were-the-weak-link.md", "extracted_at": "2026-08-08"}
 {"subject": "governance-drift-check.py", "predicate": "has-blind-spot", "object": "DOES NOT READ ~/PENDING-archive.md, so its wake line 'deferred decisions: N tracked, none due' is a census of deferrals IN ONE FILE while reading as a census of deferrals. Every deferral inside a CLOSED item is invisible — and that is the normal case, because an item is typically closed BY a ruling that defers part of what it proposed. Surfaced only because a chamber YAML cited PENDING-53 and the citation failed to resolve live. Filed as PENDING-118 [HARDENING]; family with PENDING-108 and PENDING-110 — the register's own instruments not reaching parts of the register. Size unmeasured by design.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-08-night-the-checks-were-the-weak-link.md", "extracted_at": "2026-08-08"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "QUOTED THE ADVISORY AS THOUGH IT WERE THE PLACED RECORD — three instances in one thread, one cause. A relayed jurist message and the entry the steward places from it are DIFFERENT DOCUMENTS: placement can add, cut, or re-word. Quoting the advisory therefore systematically loses whatever the act of placing contributed. In one case it lost the closing sentence of REVIEWED-104 §1, which answered the package's own gate question Q2 without asking. Two instances were mine, one the jurist's own, which is why it is a property of the relay rather than of either party's care. Test: does this quotation come from a FILE or from a message?", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-08-late-the-charter-had-the-map.md", "extracted_at": "2026-08-08"}
+{"subject": "claude-code", "predicate": "drift-pattern", "object": "THE GROUNDING PASS FINDS MY ERRORS AND NEVER MY SUPPORT. Jurist-observed across THREE consecutive packages: every substantive omission cut AGAINST the executor's own argument. Not motivated reasoning — the opposite of advocacy — but a search shaped by 'what did I get wrong?' and never by 'what already backs this?'. Instances: dropped the REVIEWED-104 sentence that would have closed Q2; missed the ratified attested-absence sibling closest in content while hunting a doctrinal parent; and at session end offered as personal reading two things the charter states outright (silence as first-class; the violin named by name). Remedy: ground in TWO passes with both intents stated.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "feedback-grounding-pass-finds-errors-not-support.md", "extracted_at": "2026-08-08"}
+{"subject": "running the fix rather than reasoning about it", "predicate": "prevention", "object": "CAUGHT THE FIX REPRODUCING THE DEFECT IT WAS FIXING. The three-valued fleet verdict's first implementation treated per-check skips and suite-level cannot-assess alike, which made the summary line 'NOT A CLEAN PASS' PERMANENT — because one long-standing skip is vacuous-by-corpus-state. That is precisely the jurist's Q1 warning, that a check which always says the same thing stops being read, arriving inside the remedy written to honour it. Found by running it once and reading the output, not by review. Split into two strengths of weakening; the same lesson then transferred immediately to a quote-verifier (re-wrapped vs normalized).", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-08-late-the-charter-had-the-map.md", "extracted_at": "2026-08-08"}
+{"subject": "implementing an option in order to test it", "predicate": "prevention", "object": "REFUTED THE OPTION ITS OWN ITEM RECOMMENDED. PENDING-118 said 'widen the scan to PENDING-archive.md — the checker already parses that exact format.' Building it showed it does not: the marker is an HTML comment and there are ZERO in either register file; their deferrals are prose (53 and 26). Widening alone would have scanned two more files, found nothing, and reported CLEAN — a silent net built to close a blind spot, which is the failure class the item was filed to describe. The refutation was only available by building.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-08-late-the-charter-had-the-map.md", "extracted_at": "2026-08-08"}
+{"subject": "an instrument built the same session", "predicate": "drift-pattern-good-direction", "object": "CAUGHT ITS OWN AUTHOR WITHIN MINUTES. The built-vs-ruled check added to governance-drift-check.py flagged PENDING-118 as BUILT-with-no-ruling almost immediately after the executor marked it — the exact gap it was written to detect, on the executor's own work, before the steward could find it. Its real-artifact control (git HEAD:REVIEWED.md, which genuinely lacked REVIEWED-107/108/109) proves it discriminates on real states rather than only on fixtures.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-08-late-the-charter-had-the-map.md", "extracted_at": "2026-08-08"}
+{"subject": "the studium engine build order", "predicate": "has-charter-ruling", "object": "CHARTER §X FOUR LAYERS: L0 corpus (built) · L1 retrieval primitives (mostly built, the shared floor) · L2 aggregation & discovery — the pattern-finder, whole-corpus topical query its lighter sibling — NEXT · L3 orchestration — voices, CHAVRUTA, larger debate — THE FRONTIER. The chavruta is L3, not the near-term goal. L2 was built first DELIBERATELY ('the hardest mode... because proving it de-risks everything above it') and its interfaces are to emerge from lived use — 'the Making, then the violin', naming the steward's own treatise. §IV separately calls migration/genealogy the engine's SIGNATURE capability, not a late extra.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "docs/the-studium-engine-architectural-charter.md", "extracted_at": "2026-08-08"}
+{"subject": "corpus/index.db drawers table", "predicate": "has-unbuilt-consequence", "object": "CHARTER §IV states 'every drawer carries its source, location, date, and language as queryable axes... genealogy, migration-mapping and temporal evolution are first-class operations'. Measured 2026-08-08: drawers carries source_id, voice, lang, line_start/end — but PERIOD IS ABSENT, though every manifest entry declares it (catalog.period). The temporal axis the charter calls first-class is declared in the corpus and not carried into the store. One column, feedable from data already present.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-08-08-late-the-charter-had-the-map.md", "extracted_at": "2026-08-08"}
+{"subject": "the violin treatise corpus", "predicate": "has-sourcing-finding", "object": "LEOPOLD MOZART IS ALREADY IN THE LIBRARY AS AN EPUB — 'Treatise On The Fundamentals Of Violin Playing / Leopold Mozart (664)', the Knocker English translation of the 1756 Versuch. Born-digital, V-TEXT tier, no OCR and no Fraktur. The steward named it as a case with no digital edition they were aware of. So the violin problem is partly SOURCING rather than conversion. ⚠ But it is a TRANSLATION: a treatise citing it in English cites Knocker, not Mozart — a new instance of the unruled quotation-in x translation-of composition. Separately: V-SCAN ABSTAINS by design (no ground truth), so the real conversion question is what tier a scanned canonical can ever reach, not OCR quality.", "valid_from": "2026-08-08", "valid_to": null, "confidence": 0.9, "source_file": "session-2026-08-08-late-the-charter-had-the-map.md", "extracted_at": "2026-08-08"}