16 — CRITICAL-NOMINATE

Create the complete review inventory for values whose corruption could change legal meaning.

PARTIAL Partly built

Currently scoped to instrument dates only: 11 nominated on issue 4547.

Deterministic Instrument path 0 archived step 16 of 26

Where this output sits

Source evidence›Candidate evidence›Human decision›Audit acceptance›Release›Production

Source evidence, candidate evidence, human decision, audit acceptance, release and production are six separate things. This step produces the highlighted one and nothing further.

Scope

Nominates the values that matter — numbers, dates, identifiers, instrument numbers and spelling spans — binding each to token ids, the exact CAP value, a field type, geometry and a source crop hash, without normalising or extracting anything.

This role is allowed to

Maintain broad detection inventory
Select a smaller review queue with explicit rules

How it works

fed by 15 TAG

Inputs

instrument and instrument_candidate unitsExact CAP tokens and polygonsTABLE-ASSIGN where applicable

Deterministic Deterministic high-recall rules; optional pinned nomination classifier.

No internal sequence is documented for this step — only the contract above and below it. Nothing was invented to fill the gap.

Must pass

Every critical candidate is source-bound
Detected inventory and review queue reported separately

passes →

Outputs

Date, number, identifier, instrument-number and spelling-span candidatesExact CAP value, field type, token IDs, bbox/crop hash, reason and state

hands off to SPELL · REV · EXTRACT

fails →

HOLD

CRITICAL_MISSINGCRITICAL_UNKNOWNCRITICAL_UNBOUNDCRITICAL_INVENTORY_MISMATCH

Nothing continues on a failed gate. Uncertainty becomes an explicit HOLD, and no later step may read an unanswered item as an accepted one.

Non-scope — what this role does NOT own

Normalisation
Canonical extraction
Deciding a value is correct

Explicitly forbidden

Normalize or canonicalize values
Hide detected candidates
Equate no nominations with perfect accuracy

Dependencies and position

Starts: After TAG and complete unit ownership.
Previous step: 15 TAG
Next step: 17 SPELL
Hands off to: SPELL, REV, EXTRACT

Exact inputs

instrument and instrument_candidate units
Exact CAP tokens and polygons
TABLE-ASSIGN where applicable

Exact outputs

Date, number, identifier, instrument-number and spelling-span candidates
Exact CAP value, field type, token IDs, bbox/crop hash, reason and state

Performer and AI/ML boundary

Performer: Deterministic high-recall rules; optional pinned nomination classifier.
Class: Deterministic
AI boundary: Optional nomination only.

Training information

Not a trained component. No model, no weights, no training corpus. Behaviour is fixed by code and configuration, and identical inputs must produce identical outputs.

Deterministic validation and acceptance gates

Every critical candidate is source-bound
Detected inventory and review queue reported separately

HOLD and failure behaviour

Failure codes this step may emit:

CRITICAL_MISSING
CRITICAL_UNKNOWN
CRITICAL_UNBOUND
CRITICAL_INVENTORY_MISMATCH

Uncertainty becomes an explicit HOLD. Omission never converts uncertainty into acceptance, and no downstream step may treat an unanswered item as an accepted one.

Downstream handoff

SPELL, REV, EXTRACT

Active tool

Status: Partial
Run / inspect: nomination is performed inside BUILDER_STAGE_A.py (step 18); gates are recorded in READY.json
Input: linked units + TAG results
Output: critical candidate ledger with state

Dependencies

Step 15 TAG
Step 18 builder

Why this is the active version

Date nomination exists and is deliberately scoped: READY.json records date_scope_instrument_only true with instrument_date_count 11. That is real, bounded critical nomination. But the V8 contract also covers numbers, identifiers and instrument numbers with bbox/polygon and crop-hash binding, and the 100-percent-recall-or-HOLD gate is not evaluated anywhere. An earlier generation produced 1,915 unfiltered date detections which the trial itself marked INVALID_ALL_1915_DETECTIONS_WERE_NOT_REVIEW_ELIGIBLE.

Copied files — source receipt

File	Original SHA-256	Bytes	Copy
`SPELLING_AUDIT_LEDGER.json`	6822e1404be52d6b…	363,036	verified
`READY.json`	492579508714c8d7…	2,881	verified

2 file(s), all hash-verified against the original. Full detail in tool/SOURCE_RECEIPT.json. Copy-only: the historical source is never modified.

Archived versions

No superseded versions recorded for this role.

Known limitations

Currently scoped to instrument dates only: 11 nominated on issue 4547.
Numbers, identifiers and instrument numbers are not nominated by any implementation.
The 100-percent-recall-or-HOLD gate is not evaluated anywhere.
An earlier generation emitted 1,915 unfiltered date detections, which the trial itself recorded as not review-eligible. Quantity is not nomination.

Security and privacy

Operates on frozen local artifacts. No credentials required. No data leaves the machine.

Cost behaviour

No provider calls. No metered cost. Compute is local.

Copying a tool into this repository does not authorise running it, retraining it, calling a model, or processing a new issue. No paid call may be made without the owner's explicit authorisation and a hard cost cap.

Provenance

Registry: registry/roles.json (schema marsoom.e2t.roles.v1)
Derivation: 28 legacy roles - VER - HUMAN + REV = 27 active steps
Legacy role id: CRITICAL
Legacy source SHA-256: 6f5d5d7ed8869e45307424c2193f95ffab84abc44a6a188f5c7f98c2a48ec64d
Generated: 2026-09-04T22:13:12.433Z

Feedback and decisions

Feedback is recorded per source and never merged into an invented consensus. Where sources disagree, both positions stand and the owner decides.

Source	Events
Naser / owner Final authority. Overrides every other source.	none recorded
Codex / orchestrator Architecture and sequencing.	none recorded
Builder / designer Implementation reality and constraints.	none recorded
Independent reviewer Adversarial review of claims.	none recorded
Auditor Evidence verification against artifacts.	none recorded
Human REV reviewer Page-level truth from the review site.	none recorded

Recorded events

No feedback events recorded yet. The ledger exists and is append-only: feedback/FEEDBACK_LEDGER.jsonl.

Editing feedback is not possible: a change is a new event whose supersedes names the one it replaces, and the original stays exactly as written.

Generated from registry/roles.json by tools/build-reports.mjs. Do not hand-edit — edit the registry and rebuild.
Original page pixels are the visual authority. CAP owns the exact captured text.