{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SAMYO6C5OAHCL2CEDG6IOXSC4D","short_pith_number":"pith:SAMYO6C5","schema_version":"1.0","canonical_sha256":"901987785d700e25e84419bc875e42e0f63f0d5c07d8cfe6fb05a563d5a7aded","source":{"kind":"arxiv","id":"2509.07588","version":1},"attestation_state":"computed","paper":{"title":"BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrey Sakhovskiy, Elena Tutubalina","submitted_at":"2025-09-09T10:59:47Z","abstract_excerpt":"In recent years, there has been substantial progress in using pretrained Language Models (LMs) on a range of tasks aimed at improving the understanding of biomedical texts. Nonetheless, existing biomedical LLMs show limited comprehension of complex, domain-specific concept structures and the factual information encoded in biomedical Knowledge Graphs (KGs). In this work, we propose BALI (Biomedical Knowledge Graph and Language Model Alignment), a novel joint LM and KG pre-training method that augments an LM with external knowledge by the simultaneous learning of a dedicated KG encoder and align"},"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":"2509.07588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T10:59:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a18f891dd75ce5c11f232348bd4f5abf2b03413b9af7c0e46c4eb5e17d2a2f53","abstract_canon_sha256":"85aae649bc72ef092f908eedad82a77dcd622cf30ecae1468a087a561112e9f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:24.256520Z","signature_b64":"+P3I0BcEsGWxwYucuOYGbPKNzshyRbSgjJY4APewKZLGlLrU2e7on7MZH5frF5upyPpxBXo653CSXAHTbSKoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"901987785d700e25e84419bc875e42e0f63f0d5c07d8cfe6fb05a563d5a7aded","last_reissued_at":"2026-07-05T12:07:24.256074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:24.256074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrey Sakhovskiy, Elena Tutubalina","submitted_at":"2025-09-09T10:59:47Z","abstract_excerpt":"In recent years, there has been substantial progress in using pretrained Language Models (LMs) on a range of tasks aimed at improving the understanding of biomedical texts. Nonetheless, existing biomedical LLMs show limited comprehension of complex, domain-specific concept structures and the factual information encoded in biomedical Knowledge Graphs (KGs). In this work, we propose BALI (Biomedical Knowledge Graph and Language Model Alignment), a novel joint LM and KG pre-training method that augments an LM with external knowledge by the simultaneous learning of a dedicated KG encoder and align"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07588","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/2509.07588/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":"2509.07588","created_at":"2026-07-05T12:07:24.256125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07588v1","created_at":"2026-07-05T12:07:24.256125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07588","created_at":"2026-07-05T12:07:24.256125+00:00"},{"alias_kind":"pith_short_12","alias_value":"SAMYO6C5OAHC","created_at":"2026-07-05T12:07:24.256125+00:00"},{"alias_kind":"pith_short_16","alias_value":"SAMYO6C5OAHCL2CE","created_at":"2026-07-05T12:07:24.256125+00:00"},{"alias_kind":"pith_short_8","alias_value":"SAMYO6C5","created_at":"2026-07-05T12:07:24.256125+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/SAMYO6C5OAHCL2CEDG6IOXSC4D","json":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D.json","graph_json":"https://pith.science/api/pith-number/SAMYO6C5OAHCL2CEDG6IOXSC4D/graph.json","events_json":"https://pith.science/api/pith-number/SAMYO6C5OAHCL2CEDG6IOXSC4D/events.json","paper":"https://pith.science/paper/SAMYO6C5"},"agent_actions":{"view_html":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D","download_json":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D.json","view_paper":"https://pith.science/paper/SAMYO6C5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07588&json=true","fetch_graph":"https://pith.science/api/pith-number/SAMYO6C5OAHCL2CEDG6IOXSC4D/graph.json","fetch_events":"https://pith.science/api/pith-number/SAMYO6C5OAHCL2CEDG6IOXSC4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/action/storage_attestation","attest_author":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/action/author_attestation","sign_citation":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/action/citation_signature","submit_replication":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/action/replication_record"}},"created_at":"2026-07-05T12:07:24.256125+00:00","updated_at":"2026-07-05T12:07:24.256125+00:00"}