{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BSHFBIBL3SUZMYNIGNKOMEPT26","short_pith_number":"pith:BSHFBIBL","schema_version":"1.0","canonical_sha256":"0c8e50a02bdca99661a83354e611f3d7955dafeda4adc69e7436836948bca392","source":{"kind":"arxiv","id":"2605.22501","version":1},"attestation_state":"computed","paper":{"title":"BeLink: Biomedical Entity Linking Meets Generative Re-Ranking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Darya Shlyk, Lawrence Hunter, Stefano Montanelli","submitted_at":"2026-05-21T13:52:55Z","abstract_excerpt":"Despite recent progress, Biomedical Entity Linking (BEL) with large language models (LLMs) remains computationally inefficient and challenging to deploy in practical settings. In this work, we demonstrate that instruction-tuning of open-source generative models can offer an effective solution when applied at the re-ranking stage of the BEL pipeline. We propose a set-wise instruction-tuning formulation that enables fast and accurate candidate selection. Our method demonstrates strong performance on multiple BEL benchmarks, yielding significant improvements in linking accuracy (3%-24%) while red"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.22501","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T13:52:55Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"9746950f532a78cdc8256c42c848794827137c0d98cfbd762701b892373090f1","abstract_canon_sha256":"200840bb34a4e7e04bb249f3db370a8fe91d1692e429f430063b414036bdd525"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:47.848837Z","signature_b64":"fZ8dV1fzRED7NJ8bM/ZDqrAeuQM4tYphrdTGlxbPtSQaSQMFl338wvzzM9IsC1K/4kIp7sJxztdfBukMy8yzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c8e50a02bdca99661a83354e611f3d7955dafeda4adc69e7436836948bca392","last_reissued_at":"2026-05-22T01:04:47.846801Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:47.846801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BeLink: Biomedical Entity Linking Meets Generative Re-Ranking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Darya Shlyk, Lawrence Hunter, Stefano Montanelli","submitted_at":"2026-05-21T13:52:55Z","abstract_excerpt":"Despite recent progress, Biomedical Entity Linking (BEL) with large language models (LLMs) remains computationally inefficient and challenging to deploy in practical settings. In this work, we demonstrate that instruction-tuning of open-source generative models can offer an effective solution when applied at the re-ranking stage of the BEL pipeline. We propose a set-wise instruction-tuning formulation that enables fast and accurate candidate selection. Our method demonstrates strong performance on multiple BEL benchmarks, yielding significant improvements in linking accuracy (3%-24%) while red"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22501","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.22501/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.22501","created_at":"2026-05-22T01:04:47.847951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22501v1","created_at":"2026-05-22T01:04:47.847951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22501","created_at":"2026-05-22T01:04:47.847951+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSHFBIBL3SUZ","created_at":"2026-05-22T01:04:47.847951+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSHFBIBL3SUZMYNI","created_at":"2026-05-22T01:04:47.847951+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSHFBIBL","created_at":"2026-05-22T01:04:47.847951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26","json":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26.json","graph_json":"https://pith.science/api/pith-number/BSHFBIBL3SUZMYNIGNKOMEPT26/graph.json","events_json":"https://pith.science/api/pith-number/BSHFBIBL3SUZMYNIGNKOMEPT26/events.json","paper":"https://pith.science/paper/BSHFBIBL"},"agent_actions":{"view_html":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26","download_json":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26.json","view_paper":"https://pith.science/paper/BSHFBIBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22501&json=true","fetch_graph":"https://pith.science/api/pith-number/BSHFBIBL3SUZMYNIGNKOMEPT26/graph.json","fetch_events":"https://pith.science/api/pith-number/BSHFBIBL3SUZMYNIGNKOMEPT26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26/action/storage_attestation","attest_author":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26/action/author_attestation","sign_citation":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26/action/citation_signature","submit_replication":"https://pith.science/pith/BSHFBIBL3SUZMYNIGNKOMEPT26/action/replication_record"}},"created_at":"2026-05-22T01:04:47.847951+00:00","updated_at":"2026-05-22T01:04:47.847951+00:00"}