v1

V1 Find Citations About

Find papers in the citation graph of arxiv_id whose content matches query.

Combines the citation graph (paper_citations) with semantic search (Gemini RETRIEVAL_QUERY embedding vs. paper RETRIEVAL_DOCUMENT embeddings) to answer questions like "find papers citing X that talk about Y".

Algorithm:

  1. Resolve source paper UUID from arxiv_id.
  2. Embed query via Gemini (cached, 15-min TTL).
  3. Take the top 2000 citation neighbours by rank_score (impact-weighted).
  4. Re-rank that pool by cosine similarity to the query embedding.
  5. Return the top limit with similarity_score per paper.

Similarity is doc-doc cosine between RETRIEVAL_QUERY and RETRIEVAL_DOCUMENT spaces — relevant matches typically score ~0.55–0.75 (not 0.85+ like doc-doc). Results are returned ranked, with no hard threshold; callers can filter on similarity_score if they want a floor.

Rate limit: 20/minute per API key.

get/v1/papers/{arxiv_id}/citations/about

Request

  • Base URL: https://api.scholarfeed.org (the document declares no server; this is the origin it was published from)
  • URL: https://api.scholarfeed.org/v1/papers/{arxiv_id}/citations/about
  • Auth: HTTP bearer

Path parameters

arxiv_idstring required

Query parameters

querystring required

Natural-language topic query — finds citations whose content matches this query

directionstring

'citing' = papers this paper cites; 'cited_by' = papers that cite this paper

limitinteger
fieldsstring nullable

Comma-separated list of fields to return. If omitted, returns the lean 12-field default unless verbose=true.

verboseboolean

If true, returns the full 28-field paper shape. Default false returns the lean set.

exclude_idsstring nullable

Comma-separated arXiv IDs to exclude from results (max 100)

Response

Successful Response

object required

Changes

No recorded changes to this operation across all 1 revision of this API.