{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7S6MMYEYJCU43SB5YBTYVGZB6L","short_pith_number":"pith:7S6MMYEY","schema_version":"1.0","canonical_sha256":"fcbcc6609848a9cdc83dc0678a9b21f2ce284e5d442c39f213d5cb0a3092bfa2","source":{"kind":"arxiv","id":"2503.22727","version":2},"attestation_state":"computed","paper":{"title":"A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alejandro Lozano, Alfred Seunghoon Song, Anita Rau, Austin Wolfgang Katzer, Chiang Chia-Chun, Christopher Polzak, Collin Chiu, Ivan Lopez, James Burgess, Jeffrey Gu, Jeffrey J. Nirschl, Josiah Aklilu, Liangyu Chen, Min Woo Sun, Orr Zohar, Robert Tibshirani, Serena Yeung-Levy, Xiaohan Wang, Yuhui Zhang","submitted_at":"2025-03-26T05:56:46Z","abstract_excerpt":"Despite the excitement behind biomedical artificial intelligence (AI), access to high-quality, diverse, and large-scale data - the foundation for modern AI systems - is still a bottleneck to unlocking its full potential. To address this gap, we introduce Biomedica, an open-source dataset derived from the PubMed Central Open Access subset, containing over 6 million scientific articles and 24 million image-text pairs, along with 27 metadata fields (including expert human annotations). To overcome the challenges of accessing our large-scale dataset, we provide scalable streaming and search APIs t"},"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":"2503.22727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T05:56:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c88dcfc021e7c09f88b7f4cd0581b759742974a5d98b8820d47668392d2d4c5a","abstract_canon_sha256":"22574e9b8f2642ba9bdce9160d2ada847615928bea9d053a9441de9213f29443"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:06.880225Z","signature_b64":"8SO8YoyPyCRXp1QwMnP5z3UJhR22q0fQdJiNQi90ypYq1xxL82hVDE2dqRw5GpBifEefE2ZdPQTBxzBXUb9DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcbcc6609848a9cdc83dc0678a9b21f2ce284e5d442c39f213d5cb0a3092bfa2","last_reissued_at":"2026-07-05T10:43:06.879618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:06.879618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alejandro Lozano, Alfred Seunghoon Song, Anita Rau, Austin Wolfgang Katzer, Chiang Chia-Chun, Christopher Polzak, Collin Chiu, Ivan Lopez, James Burgess, Jeffrey Gu, Jeffrey J. Nirschl, Josiah Aklilu, Liangyu Chen, Min Woo Sun, Orr Zohar, Robert Tibshirani, Serena Yeung-Levy, Xiaohan Wang, Yuhui Zhang","submitted_at":"2025-03-26T05:56:46Z","abstract_excerpt":"Despite the excitement behind biomedical artificial intelligence (AI), access to high-quality, diverse, and large-scale data - the foundation for modern AI systems - is still a bottleneck to unlocking its full potential. To address this gap, we introduce Biomedica, an open-source dataset derived from the PubMed Central Open Access subset, containing over 6 million scientific articles and 24 million image-text pairs, along with 27 metadata fields (including expert human annotations). To overcome the challenges of accessing our large-scale dataset, we provide scalable streaming and search APIs t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22727","kind":"arxiv","version":2},"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/2503.22727/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":"2503.22727","created_at":"2026-07-05T10:43:06.879685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22727v2","created_at":"2026-07-05T10:43:06.879685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22727","created_at":"2026-07-05T10:43:06.879685+00:00"},{"alias_kind":"pith_short_12","alias_value":"7S6MMYEYJCU4","created_at":"2026-07-05T10:43:06.879685+00:00"},{"alias_kind":"pith_short_16","alias_value":"7S6MMYEYJCU43SB5","created_at":"2026-07-05T10:43:06.879685+00:00"},{"alias_kind":"pith_short_8","alias_value":"7S6MMYEY","created_at":"2026-07-05T10:43:06.879685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.05299","citing_title":"SmolVLM: Redefining small and efficient multimodal models","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L","json":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L.json","graph_json":"https://pith.science/api/pith-number/7S6MMYEYJCU43SB5YBTYVGZB6L/graph.json","events_json":"https://pith.science/api/pith-number/7S6MMYEYJCU43SB5YBTYVGZB6L/events.json","paper":"https://pith.science/paper/7S6MMYEY"},"agent_actions":{"view_html":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L","download_json":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L.json","view_paper":"https://pith.science/paper/7S6MMYEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22727&json=true","fetch_graph":"https://pith.science/api/pith-number/7S6MMYEYJCU43SB5YBTYVGZB6L/graph.json","fetch_events":"https://pith.science/api/pith-number/7S6MMYEYJCU43SB5YBTYVGZB6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/action/storage_attestation","attest_author":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/action/author_attestation","sign_citation":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/action/citation_signature","submit_replication":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/action/replication_record"}},"created_at":"2026-07-05T10:43:06.879685+00:00","updated_at":"2026-07-05T10:43:06.879685+00:00"}