{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2HMSE7KXIKBAXSSDT6UAQQB4EZ","short_pith_number":"pith:2HMSE7KX","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"},"canonical_sha256":"d1d9227d5742820bca439fa808403c266343c5744b6176908579f1609a30cc2f","source":{"kind":"arxiv","id":"2601.19667","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.19667","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2601.19667v2","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.19667","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"2HMSE7KXIKBA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2HMSE7KXIKBAXSSD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2HMSE7KX","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2HMSE7KXIKBAXSSDT6UAQQB4EZ","target":"record","payload":{"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"},"canonical_sha256":"d1d9227d5742820bca439fa808403c266343c5744b6176908579f1609a30cc2f","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"},"source_kind":"arxiv","source_id":"2601.19667","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yEfCoNgIKLSbh6udJUojMzrY2gf4XHMttO/lJ41524zFWnsjL3auHAJzgRTOQIutbzkWdP7Ljnp1WpYn9hf2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:07:30.751148Z"},"content_sha256":"fe210b83869da4c3d7972aca24be386d5fe2197d3d49214e96f75f0d87c73e43","schema_version":"1.0","event_id":"sha256:fe210b83869da4c3d7972aca24be386d5fe2197d3d49214e96f75f0d87c73e43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2HMSE7KXIKBAXSSDT6UAQQB4EZ","target":"graph","payload":{"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"},"verdict_id":"76bc4c1f-786b-4a46-86e5-a03019a397a1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tTSJzEykLCN8zHZX19nlqOoHZYlxJKO3qtvMK7RX2lXVrCOkWTsLA8hJHVCRrF7UkK0J78m8Au6G4AuThW1HAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:07:30.751629Z"},"content_sha256":"55d43d90019efa938bcc4abcc2979760ae91f2b27297c06635723764c6f9323d","schema_version":"1.0","event_id":"sha256:55d43d90019efa938bcc4abcc2979760ae91f2b27297c06635723764c6f9323d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/bundle.json","state_url":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T16:07:30Z","links":{"resolver":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ","bundle":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/bundle.json","state":"https://pith.science/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2HMSE7KXIKBAXSSDT6UAQQB4EZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2HMSE7KXIKBAXSSDT6UAQQB4EZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4307d55b4a2750067ba882e7ba207ed054dd71bffb1b002bec46141bf31fef43","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-27T14:47:17Z","title_canon_sha256":"14d5b3f61f35d292638e87b1c4ce8066733d21fb1ea186fae240d1bd6f2ebd37"},"schema_version":"1.0","source":{"id":"2601.19667","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.19667","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2601.19667v2","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.19667","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"2HMSE7KXIKBA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2HMSE7KXIKBAXSSD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2HMSE7KX","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:55d43d90019efa938bcc4abcc2979760ae91f2b27297c06635723764c6f9323d","target":"graph","created_at":"2026-05-18T02:44:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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"}],"snapshot_sha256":"9bf3a9d6244abd4915dcd9ed74c436faae953d4f4e26ba3c7f58cbd88a2571ae"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Adam Remaki, Christel G\\'erardin, Eul\\`alia Farr\\'e-Maduell, Martin Krallinger, Xavier Tannier","cross_cats":["cs.AI","cs.IR","cs.LG"],"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","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-27T14:47:17Z","title":"SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.19667","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T10:56:45.841996Z","id":"76bc4c1f-786b-4a46-86e5-a03019a397a1","model_set":{"reader":"grok-4.3"},"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","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","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.","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."}},"verdict_id":"76bc4c1f-786b-4a46-86e5-a03019a397a1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fe210b83869da4c3d7972aca24be386d5fe2197d3d49214e96f75f0d87c73e43","target":"record","created_at":"2026-05-18T02:44:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4307d55b4a2750067ba882e7ba207ed054dd71bffb1b002bec46141bf31fef43","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-27T14:47:17Z","title_canon_sha256":"14d5b3f61f35d292638e87b1c4ce8066733d21fb1ea186fae240d1bd6f2ebd37"},"schema_version":"1.0","source":{"id":"2601.19667","kind":"arxiv","version":2}},"canonical_sha256":"d1d9227d5742820bca439fa808403c266343c5744b6176908579f1609a30cc2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1d9227d5742820bca439fa808403c266343c5744b6176908579f1609a30cc2f","first_computed_at":"2026-05-18T02:44:31.836974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:31.836974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9xWhjF39UBY69AwiAbN5QXuo8y78ro37dnzHGOWZSNMkzQbcqQGogiuLywdsgOtY9VJh84eUOWDtoTiBI7r+Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:31.837468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.19667","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe210b83869da4c3d7972aca24be386d5fe2197d3d49214e96f75f0d87c73e43","sha256:55d43d90019efa938bcc4abcc2979760ae91f2b27297c06635723764c6f9323d"],"state_sha256":"6aae31b571ea5c4bdafaccf3a65bde29ec4e87e59f6efd67a61d0459a0e263b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mJaHGBRQHUoIervEaYYrHhVzK0yY5IA8pUW+JkLUQ3SuvZQyKiBibYq2NmkWY8QeQ/6OICNNFe2b7anrkA82DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T16:07:30.755042Z","bundle_sha256":"3a8290015f5e421ac32ab9d8465aa7808a0d3d123ad115dfb9203d63345a5271"}}