find_related
Find related PAPERS via three modes (papers, not claims — for claims related to a claim use find_related_claims): 'similarity' (default — vector similarity to a doc or text), 'byEntity' (papers mentioning a specific entity like "BERT"), 'byConcept' (papers sharing a key concept). Returns papers with abstract and metadata for quick understanding — no follow-up get_document needed.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | 'similarity' (default): vector similarity to documentId or text. 'byEntity': papers mentioning entity (e.g. 'BERT') — ranks by mention count, biases toward surveys that mention the entity many times rather than original papers introducing it; for canonical lookup use search_keyword or find_by_id. 'byConcept': papers sharing keyConcept. | similarity |
| text | No | For similarity mode (embeds text as query) | |
| limit | No | ||
| detail | No | 'minimal' = id+title+score. 'standard' = + abstract + metadata. 'full' = + author records + licenses | standard |
| entity | No | For byEntity mode: entity name like 'BERT' or 'ImageNet' (case-insensitive) | |
| run_id | No | Optional. The active methodist run_id (as returned by the methodist diagnose / get_current_dose door). Pass it whenever you call this tool while working inside a run, so the call is attributed to that run for the §8 usage crosscheck — attribution is run-anchored, so it stays correct even if your access token refreshes mid-run. Must be YOUR run: a run_id owned by a different principal, or a non-existent run_id, is rejected. | |
| concept | No | For byConcept mode: keyConcept string (case-insensitive, partial match) | |
| categories | No | Filter by arXiv categories | |
| documentId | No | For similarity mode (uses doc avg vector) | |
| vectorModel | No | Embedding model to use (similarity mode only) | gemini |