--- name: literature-map-builder description: Cluster a set of papers into a topic map with methodology and findings per cluster, then surface the whitespace where nobody is working yet. title: Literature Map Builder category: research-analysis difficulty: intermediate author: admin icon: πŸ—ΊοΈ input: pdf output: markdown phase: enhance domain: research tags: literature-review,topic-clustering,research-mapping,embedding-based-analysis,gap-identification,hdbscan,pdf-processing,doi-ingestion,llm-synthesis,academic-research best_for: - systematic literature reviews - research proposal scoping - identifying unexplored research gaps - field landscape analysis --- ## Description Takes a folder of PDFs or a list of DOIs and produces a two-level topic map: top-level clusters by research question, leaves by methodology. Each cluster gets a one-paragraph synthesis plus a gap bullet β€” 'nobody has tried X on Y.' Output is a single markdown brief with inline citations. ## Why it works Researchers spend the first week of any project reading in a random order, which hides the shape of the field. Embedding-based clustering finds the *shape* before you commit to a reading order, so the gap you end up chasing is one of the field's actual gaps β€” not just a gap in your own reading. ## How it works 1. Embed each paper's abstract + methods section with a strong retrieval model. 2. HDBSCAN over the embeddings to find natural clusters (no k to pre-specify). 3. For each cluster, sample 3-5 papers into a context window and ask the LLM for a methodology+findings synthesis with a critical-gap bullet. 4. Second pass: compare the per-cluster gaps against all papers' conclusions to rule out gaps that are actually addressed elsewhere. 5. Emit a markdown report with per-cluster sections and a consolidated 'open questions' list at the bottom.