Citation Diversifier (budget-as-constraints) [NO NEW FACTS]

Purpose: fix a common survey failure mode:

• - the draft reads under-cited (or reuses the same few citations everywhere)
• the pipeline fails the global unique-citation gate

This skill does not change prose by itself.
It produces a constraint sheet: output/CITATION_BUDGET_REPORT.md.

Inputs

• - INLINECODE1
• INLINECODE2 (H3 ids/titles; used to allocate budgets per subsection)
• INLINECODE3 (source of allowed_bibkeys_{selected,mapped,chapter,global} per H3)
• INLINECODE5

Output

• - INLINECODE6

Non-negotiables (NO NEW FACTS)

• - Only propose citation keys that exist in citations/ref.bib.
• Only propose keys that are in-scope for the target H3 (prefer subsection-first scope; use chapter/global only when truly cross-cutting).
• Do not propose “padding citations” that would require adding new claims or new numbers.

What a good budget report looks like (contract)

The report should feel like a constraint sheet, not a random list:

• - It states the blocking policy target and the gap-to-target (how many unique keys are missing; policy default is recommended).
• For each H3, it proposes a scope-safe budget sized to actually close the gap:

• - It gives placement guidance (where in the subsection those keys can be embedded without adding new facts).

Canonical (parseable) lines required (downstream validators depend on these):

• - The target is derived from queries.md:citation_target (recommended by default for A150++).
• INLINECODE11
• INLINECODE12 (gap-to-target; if 0, injection can be a no-op PASS)

Optional (always reported; may be blocking depending on citation_target):

• - INLINECODE15
• INLINECODE16

Recommended prioritization (scope-safe):

• - allowed_bibkeys_selected → allowed_bibkeys_mapped → INLINECODE19
• Use allowed_bibkeys_global only for:

How this connects to writing (LLM-first)

After you generate the budget report:

• - Apply it using citation-injector (LLM edits to output/DRAFT.md, NO NEW FACTS).
• Then run draft-polisher to remove any “budget dump voice” while keeping citation keys unchanged.

Important: citation-injector is LLM-first. Its script is validation-only.

Workflow

1) Diagnose the global situation

• - Read output/DRAFT.md and estimate the “unique-key gap” (or use pipeline-auditor’s FAIL reason).

2) Allocate budgets per H3 (scope-first)

• - Use outline/outline.yml to enumerate H3s in paper order.
• For each H3, read its allowed key sets from outline/writer_context_packs.jsonl.
• Pick a small set of unused keys that strengthen positioning without requiring new claims.

3) Write output/CITATION_BUDGET_REPORT.md
Required structure:

• - INLINECODE30
• INLINECODE31
• INLINECODE32
• INLINECODE33 (gap + strategy)
• INLINECODE34 (H3 id/title → suggested keys → placement hint)

Script (optional; deterministic report generator)

If you want a deterministic first-pass budget report, run the helper script. Treat it as a baseline and refine the plan as needed.

Quick Start

• - INLINECODE35
• INLINECODE36

All Options

• - INLINECODE37
• INLINECODE38 (optional)
• INLINECODE39 (rare override; prefer defaults)
• INLINECODE40 (rare override; default writes output/CITATION_BUDGET_REPORT.md)
• INLINECODE42 (optional)

Examples

• - Default IO:

Done criteria

• - output/CITATION_BUDGET_REPORT.md exists and has actionable, in-scope budgets.
• After applying the plan via citation-injector, pipeline-auditor no longer FAILs on global unique citations.