{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2HMSE7KXIKBAXSSDT6UAQQB4EZ","short_pith_number":"pith:2HMSE7KX","schema_version":"1.0","canonical_sha256":"d1d9227d5742820bca439fa808403c266343c5744b6176908579f1609a30cc2f","source":{"kind":"arxiv","id":"2601.19667","version":2},"attestation_state":"computed","paper":{"title":"SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"SynCABEL generates synthetic training examples with large language models to overcome data scarcity in biomedical entity linking and reaches new state-of-the-art results on three multilingual benchmarks with up to 60 percent less human-anno","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Remaki, Christel G\\'erardin, Eul\\`alia Farr\\'e-Maduell, Martin Krallinger, Xavier Tannier","submitted_at":"2026-01-27T14:47:17Z","abstract_excerpt":"We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in supervised biomedical entity linking (BEL): the scarcity of expert-annotated training data. SynCABEL leverages large language models to generate context-rich synthetic training examples for all candidate concepts in a target knowledge base, providing broad supervision without manual annotation. We demonstrate that SynCABEL, when combined with decoder-only models and guided inference, establishes new state-of-the-art results across three widely used multi"},"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":"2601.19667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-27T14:47:17Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"14d5b3f61f35d292638e87b1c4ce8066733d21fb1ea186fae240d1bd6f2ebd37","abstract_canon_sha256":"4307d55b4a2750067ba882e7ba207ed054dd71bffb1b002bec46141bf31fef43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:31.837468Z","signature_b64":"9xWhjF39UBY69AwiAbN5QXuo8y78ro37dnzHGOWZSNMkzQbcqQGogiuLywdsgOtY9VJh84eUOWDtoTiBI7r+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1d9227d5742820bca439fa808403c266343c5744b6176908579f1609a30cc2f","last_reissued_at":"2026-05-18T02:44:31.836974Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:31.836974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"SynCABEL generates synthetic training examples with large language models to overcome data scarcity in biomedical entity linking and reaches new state-of-the-art results on three multilingual benchmarks with up to 60 percent less human-anno","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Remaki, Christel G\\'erardin, Eul\\`alia Farr\\'e-Maduell, Martin Krallinger, Xavier Tannier","submitted_at":"2026-01-27T14:47:17Z","abstract_excerpt":"We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in supervised biomedical entity linking (BEL): the scarcity of expert-annotated training data. SynCABEL leverages large language models to generate context-rich synthetic training examples for all candidate concepts in a target knowledge base, providing broad supervision without manual annotation. We demonstrate that SynCABEL, when combined with decoder-only models and guided inference, establishes new state-of-the-art results across three widely used multi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SynCABEL, when combined with decoder-only models and guided inference, establishes new state-of-the-art results across three widely used multilingual benchmarks: MedMentions for English, QUAERO for French, and SPACCC for Spanish.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that LLM-generated synthetic examples are sufficiently representative of real biomedical text distributions and do not introduce systematic biases or hallucinations that would degrade downstream linking performance.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SynCABEL generates LLM-based synthetic data for all candidate concepts in biomedical entity linking, reaching new SOTA results on MedMentions, QUAERO, and SPACCC with up to 60% less human-annotated data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SynCABEL generates synthetic training examples with large language models to overcome data scarcity in biomedical entity linking and reaches new state-of-the-art results on three multilingual benchmarks with up to 60 percent less human-anno","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9bf3a9d6244abd4915dcd9ed74c436faae953d4f4e26ba3c7f58cbd88a2571ae"},"source":{"id":"2601.19667","kind":"arxiv","version":2},"verdict":{"id":"76bc4c1f-786b-4a46-86e5-a03019a397a1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T10:56:45.841996Z","strongest_claim":"SynCABEL, when combined with decoder-only models and guided inference, establishes new state-of-the-art results across three widely used multilingual benchmarks: MedMentions for English, QUAERO for French, and SPACCC for Spanish.","one_line_summary":"SynCABEL generates LLM-based synthetic data for all candidate concepts in biomedical entity linking, reaching new SOTA results on MedMentions, QUAERO, and SPACCC with up to 60% less human-annotated data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that LLM-generated synthetic examples are sufficiently representative of real biomedical text distributions and do not introduce systematic biases or hallucinations that would degrade downstream linking performance.","pith_extraction_headline":"SynCABEL generates synthetic training examples with large language models to overcome data scarcity in biomedical entity linking and reaches new state-of-the-art results on three multilingual benchmarks with up to 60 percent less human-anno"},"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":"2601.19667","created_at":"2026-05-18T02:44:31.837045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.19667v2","created_at":"2026-05-18T02:44:31.837045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.19667","created_at":"2026-05-18T02:44:31.837045+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HMSE7KXIKBA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HMSE7KXIKBAXSSD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HMSE7KX","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13451","citing_title":"LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ","json":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ.json","graph_json":"https://pith.science/api/pith-number/2HMSE7KXIKBAXSSDT6UAQQB4EZ/graph.json","events_json":"https://pith.science/api/pith-number/2HMSE7KXIKBAXSSDT6UAQQB4EZ/events.json","paper":"https://pith.science/paper/2HMSE7KX"},"agent_actions":{"view_html":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ","download_json":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ.json","view_paper":"https://pith.science/paper/2HMSE7KX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.19667&json=true","fetch_graph":"https://pith.science/api/pith-number/2HMSE7KXIKBAXSSDT6UAQQB4EZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2HMSE7KXIKBAXSSDT6UAQQB4EZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/action/storage_attestation","attest_author":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/action/author_attestation","sign_citation":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/action/citation_signature","submit_replication":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/action/replication_record"}},"created_at":"2026-05-18T02:44:31.837045+00:00","updated_at":"2026-05-18T02:44:31.837045+00:00"}