Paper Triage

Turn an ambiguous paper query into a ranked shortlist and clear next steps. Use this when the human starts with a fuzzy title fragment, overloaded term, or vague memory of a paper.

Arguments

• The positional argument is the paper query. Quote multi-word titles when running from a shell.
• --shortlist-size <n> controls the final shortlist size returned to the human.
• --relevance-limit <n> controls the first relevance-search pass.
• --bulk-candidate-limit <n> controls the wider recall pass.
• --snippet-candidate-limit <n> controls how many preliminary candidates get snippet search.
• --snippet-limit-per-paper <n> caps snippet evidence gathered for each snippet target.

Workflow

1. Run python scripts/run.py ....
2. Read result.possible_interpretations to see how the query was resolved.
3. Read result.shortlist for the ranked candidate papers.
4. Read to know which workflow to run next once the right paper is identified.