{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SAMYO6C5OAHCL2CEDG6IOXSC4D","short_pith_number":"pith:SAMYO6C5","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"},"canonical_sha256":"901987785d700e25e84419bc875e42e0f63f0d5c07d8cfe6fb05a563d5a7aded","source":{"kind":"arxiv","id":"2509.07588","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07588","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07588v1","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07588","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"SAMYO6C5OAHC","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"SAMYO6C5OAHCL2CE","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"SAMYO6C5","created_at":"2026-07-05T12:07:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SAMYO6C5OAHCL2CEDG6IOXSC4D","target":"record","payload":{"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"},"canonical_sha256":"901987785d700e25e84419bc875e42e0f63f0d5c07d8cfe6fb05a563d5a7aded","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"},"source_kind":"arxiv","source_id":"2509.07588","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9rnSPjbtSPI+3KEO20NJRlLdm23ktW8FYtlajd9JozkDdGnKAKQmeQiBp/X+WI9lxF/Y+pJDgpnDtheDmVpyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:07:18.687953Z"},"content_sha256":"23860e61bc6067ef2b70bde7b34fa5b5007202764426d3506e459e1fd01998ae","schema_version":"1.0","event_id":"sha256:23860e61bc6067ef2b70bde7b34fa5b5007202764426d3506e459e1fd01998ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SAMYO6C5OAHCL2CEDG6IOXSC4D","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"22wtGGzHwtDkNx+00FrH4FITmaPvjUDPLaXS9WfvP+Pvl7cnkHJgDP8ZVlIYsZdGB0NOatsxUIduKqT162naDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:07:18.688620Z"},"content_sha256":"4c0e187cbb74729d3fbe690e6c0ea3870b1cc3c64d3e3e217f5bab9a6a3d61aa","schema_version":"1.0","event_id":"sha256:4c0e187cbb74729d3fbe690e6c0ea3870b1cc3c64d3e3e217f5bab9a6a3d61aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/bundle.json","state_url":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/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":"2026-08-05T10:07:18Z","links":{"resolver":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D","bundle":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/bundle.json","state":"https://pith.science/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SAMYO6C5OAHCL2CEDG6IOXSC4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SAMYO6C5OAHCL2CEDG6IOXSC4D","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":"85aae649bc72ef092f908eedad82a77dcd622cf30ecae1468a087a561112e9f9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T10:59:47Z","title_canon_sha256":"a18f891dd75ce5c11f232348bd4f5abf2b03413b9af7c0e46c4eb5e17d2a2f53"},"schema_version":"1.0","source":{"id":"2509.07588","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07588","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07588v1","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07588","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"SAMYO6C5OAHC","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"SAMYO6C5OAHCL2CE","created_at":"2026-07-05T12:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"SAMYO6C5","created_at":"2026-07-05T12:07:24Z"}],"graph_snapshots":[{"event_id":"sha256:4c0e187cbb74729d3fbe690e6c0ea3870b1cc3c64d3e3e217f5bab9a6a3d61aa","target":"graph","created_at":"2026-07-05T12:07:24Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.07588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrey Sakhovskiy, Elena Tutubalina","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T10:59:47Z","title":"BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07588","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:23860e61bc6067ef2b70bde7b34fa5b5007202764426d3506e459e1fd01998ae","target":"record","created_at":"2026-07-05T12:07:24Z","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":"85aae649bc72ef092f908eedad82a77dcd622cf30ecae1468a087a561112e9f9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T10:59:47Z","title_canon_sha256":"a18f891dd75ce5c11f232348bd4f5abf2b03413b9af7c0e46c4eb5e17d2a2f53"},"schema_version":"1.0","source":{"id":"2509.07588","kind":"arxiv","version":1}},"canonical_sha256":"901987785d700e25e84419bc875e42e0f63f0d5c07d8cfe6fb05a563d5a7aded","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"901987785d700e25e84419bc875e42e0f63f0d5c07d8cfe6fb05a563d5a7aded","first_computed_at":"2026-07-05T12:07:24.256074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:24.256074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+P3I0BcEsGWxwYucuOYGbPKNzshyRbSgjJY4APewKZLGlLrU2e7on7MZH5frF5upyPpxBXo653CSXAHTbSKoCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:24.256520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.07588","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23860e61bc6067ef2b70bde7b34fa5b5007202764426d3506e459e1fd01998ae","sha256:4c0e187cbb74729d3fbe690e6c0ea3870b1cc3c64d3e3e217f5bab9a6a3d61aa"],"state_sha256":"714183b9a995bca44ce27a68f9bbc3220a1caaa0ef6a1d82d938c08dd2a2bc48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jVWyAE7a29uR8a3C9nrKTsf0OmlbUi6hOIyZREUuazV/bqUKJtT2OslvW+5+wKaI4VUWoswvJ94/EZUnSbQjDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:07:18.694190Z","bundle_sha256":"08b83981d1b19e276e14f47a39a6d5ee4fe2f77d6050b375908fafa8e8eca37a"}}