{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:22TZSFFSV2ZMM4QVKN3463D4UE","short_pith_number":"pith:22TZSFFS","schema_version":"1.0","canonical_sha256":"d6a79914b2aeb2c672155377cf6c7ca12e7ec19aae91a8d13f88a1fca5fa9d7a","source":{"kind":"arxiv","id":"2310.03320","version":4},"attestation_state":"computed","paper":{"title":"BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balasubramaniam Srinivasan, Huzefa Rangwala, Rishita Anubhai, Vassilis N. Ioannidis, Zichen Wang, Zifeng Wang","submitted_at":"2023-10-05T05:30:42Z","abstract_excerpt":"Foundation models (FMs) are able to leverage large volumes of unlabeled data to demonstrate superior performance across a wide range of tasks. However, FMs developed for biomedical domains have largely remained unimodal, i.e., independently trained and used for tasks on protein sequences alone, small molecule structures alone, or clinical data alone. To overcome this limitation of biomedical FMs, we present BioBridge, a novel parameter-efficient learning framework, to bridge independently trained unimodal FMs to establish multimodal behavior. BioBridge achieves it by utilizing Knowledge Graphs"},"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":"2310.03320","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T05:30:42Z","cross_cats_sorted":[],"title_canon_sha256":"88a2ed4441d916bfdf73f141f2578cdebed3901dfdd90c1ec391d85342fc6a5d","abstract_canon_sha256":"d19682b1e69e12768c90e96e0429a1411f4823296fd3ee79e26b96fe5d81d21a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:21.590747Z","signature_b64":"NX/iUHCYoSX+UKl8oUr+d6vXcojG4FzoaeZgpmJ0+aQ1yaU/MXUDqZzb8fQlCiwHEj/FtBrokClTY+6y8z5YCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6a79914b2aeb2c672155377cf6c7ca12e7ec19aae91a8d13f88a1fca5fa9d7a","last_reissued_at":"2026-07-05T07:35:21.590344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:21.590344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balasubramaniam Srinivasan, Huzefa Rangwala, Rishita Anubhai, Vassilis N. Ioannidis, Zichen Wang, Zifeng Wang","submitted_at":"2023-10-05T05:30:42Z","abstract_excerpt":"Foundation models (FMs) are able to leverage large volumes of unlabeled data to demonstrate superior performance across a wide range of tasks. However, FMs developed for biomedical domains have largely remained unimodal, i.e., independently trained and used for tasks on protein sequences alone, small molecule structures alone, or clinical data alone. To overcome this limitation of biomedical FMs, we present BioBridge, a novel parameter-efficient learning framework, to bridge independently trained unimodal FMs to establish multimodal behavior. BioBridge achieves it by utilizing Knowledge Graphs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03320","kind":"arxiv","version":4},"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/2310.03320/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":"2310.03320","created_at":"2026-07-05T07:35:21.590398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03320v4","created_at":"2026-07-05T07:35:21.590398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03320","created_at":"2026-07-05T07:35:21.590398+00:00"},{"alias_kind":"pith_short_12","alias_value":"22TZSFFSV2ZM","created_at":"2026-07-05T07:35:21.590398+00:00"},{"alias_kind":"pith_short_16","alias_value":"22TZSFFSV2ZMM4QV","created_at":"2026-07-05T07:35:21.590398+00:00"},{"alias_kind":"pith_short_8","alias_value":"22TZSFFS","created_at":"2026-07-05T07:35:21.590398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15016","citing_title":"COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18703","citing_title":"Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE","json":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE.json","graph_json":"https://pith.science/api/pith-number/22TZSFFSV2ZMM4QVKN3463D4UE/graph.json","events_json":"https://pith.science/api/pith-number/22TZSFFSV2ZMM4QVKN3463D4UE/events.json","paper":"https://pith.science/paper/22TZSFFS"},"agent_actions":{"view_html":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE","download_json":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE.json","view_paper":"https://pith.science/paper/22TZSFFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03320&json=true","fetch_graph":"https://pith.science/api/pith-number/22TZSFFSV2ZMM4QVKN3463D4UE/graph.json","fetch_events":"https://pith.science/api/pith-number/22TZSFFSV2ZMM4QVKN3463D4UE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE/action/storage_attestation","attest_author":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE/action/author_attestation","sign_citation":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE/action/citation_signature","submit_replication":"https://pith.science/pith/22TZSFFSV2ZMM4QVKN3463D4UE/action/replication_record"}},"created_at":"2026-07-05T07:35:21.590398+00:00","updated_at":"2026-07-05T07:35:21.590398+00:00"}