Paper_Reach

Run evidence-aware literature screening with Paper-Reach. Search candidate papers, screen abstracts conservatively, review full text when available, and emit structured JSON.

Apply a conservative screening rubric to rank papers and separate selected, ambiguous, and rejected items with reasons and evidence references. Use when a candidate set already exists and final ranking or grouping is needed.

Read abstracts and, when available, full text to extract structured evidence for literature screening. Use when a paper is ambiguous after abstract screening or the user needs method, dataset, supervision, or limitation details.

Retrieve candidate papers and perform conservative coarse screening using title and abstract evidence. Use when the user needs a candidate paper set, abstract-level screening, or a first-pass shortlist before full-text review.