08 — TITLE

Separate printed primary titles from subtitles, body, bylines, captions, and furniture.

ACTIVE Built and verified

1 tool file copied and hash-verified against the original.

ML proposal-only Page model 0 archived step 08 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

Separates printed primary titles from subtitles, body, bylines, captions and furniture, binding each to exact CAP line ids. A printed title and an AI-proposed label for a titleless unit are carried under different type markers and must never be confused.

This role is allowed to

Select exact CAP line IDs
Return no-title/HOLD

How it works

fed by 07 ROLE

Inputs

ROLE candidatesTypography evidenceOrdered CAP line aliases and unit boundaries

ML proposal-only Structured AI proposal with deterministic exact-CAP and ownership validation.

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

Must pass

Only PRIMARY_TITLE feeds TOC
Title lines belong to the same content unit exactly once
Derived label for a titleless unit is separately marked and never source text

passes →

Outputs

PRIMARY_TITLE, SUBTITLE, BODY, BYLINE, CAPTION, FURNITURE or HOLD links

hands off to ORDER · TAG · DGTL · ARCH

fails →

HOLD

TITLE_MISSINGTITLE_AMBIGUOUSTITLE_SUBTITLE_CONTAMINATIONTITLE_OWNERSHIP_CONFLICT

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

Inventing or rewriting a headline
Concatenating unrelated lines
Putting subtitle text into PRIMARY_TITLE

Explicitly forbidden

Invent or rewrite a headline
Concatenate unrelated lines
Place subtitle text in PRIMARY_TITLE

Dependencies and position

Starts: After ROLE evidence and ordered candidate units exist.
Previous step: 07 ROLE
Next step: 09 TYPE / TYPOGRAPHY
Hands off to: ORDER, TAG, DGTL, ARCH

Exact inputs

ROLE candidates
Typography evidence
Ordered CAP line aliases and unit boundaries

Exact outputs

PRIMARY_TITLE, SUBTITLE, BODY, BYLINE, CAPTION, FURNITURE or HOLD links

Performer and AI/ML boundary

Performer: Structured AI proposal with deterministic exact-CAP and ownership validation.
Class: ML proposal-only
AI boundary: May share the MAP-AI/ORDER/TAG request.

Training information

Not trained by this project. A pinned general model is prompted under a strict response schema. It proposes; deterministic validation accepts or HOLDs. It cannot create text or coordinates.

Deterministic validation and acceptance gates

Only PRIMARY_TITLE feeds TOC
Title lines belong to the same content unit exactly once
Derived label for a titleless unit is separately marked and never source text

HOLD and failure behaviour

Failure codes this step may emit:

TITLE_MISSING
TITLE_AMBIGUOUS
TITLE_SUBTITLE_CONTAMINATION
TITLE_OWNERSHIP_CONFLICT

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

ORDER, TAG, DGTL, ARCH

Active tool

Status: Active tool
Run / inspect: title binding is emitted by the MAP-AI detail call: field `t` with `k` = P (printed) or A (AI-proposed), and segment `m`
Input: ROLE candidates + ordered CAP line aliases
Output: detail-response field `t`

Dependencies

Step 03 MAP-AI
Exact CAP line IDs

Why this is the active version

The schema distinguishes a PRINTED title from an AI-PROPOSED one via the `k` discriminator. That distinction is exactly what the owner rule requires: only exact printed PRIMARY_TITLE text may enter the TOC as a source title. A derived label for a titleless unit is carried separately and must never be presented as source text.

Copied files — source receipt

File	Original SHA-256	Bytes	Copy
`schemas/detail-response.schema.json`	4b73e8c39581ca16…	2,721	verified

1 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

Only exact printed PRIMARY_TITLE text may enter the table of contents as a source title. A derived label is not source text and must be visibly marked as derived wherever it appears.
Subtitle contamination is a known, named failure mode with no independent detector.

Security and privacy

Page images and indexed references are sent to an external provider. Credentials live outside this repository. Model output is candidate evidence, never truth.

Cost behaviour

Metered per call by the provider. Token budget and tier are set per run and recorded in the run receipts.

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: TITLE
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.