{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EGQNXQP3G3C7LQK6UHIO2QWLY2","short_pith_number":"pith:EGQNXQP3","schema_version":"1.0","canonical_sha256":"21a0dbc1fb36c5f5c15ea1d0ed42cbc692af01baf0f114981b77768344f48673","source":{"kind":"arxiv","id":"2607.07673","version":1},"attestation_state":"computed","paper":{"title":"MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dain Kim, Gui Yang, Hoifung Poon, Hua Xu, Hyunjae Kim, Jaewoo Kang, Jonathan Marquez, Kevin W. Jin, Mengmeng Du, Pan Xiao, Qingyu Chen, Roy Jiang, Rui Shi, Serina S. Applebaum, Sheng Zhang, Tuo Guo, Xuguang Ai, Yan Hu, Yawen Wei, Yiming Kong, Younjoon Chung, Yuelei Fu, Yuexi Du, Yuntian Liu, Yuxuan Tian, Yu Yin, Zhen Chen, Zhiyuan Cao","submitted_at":"2026-07-08T17:26:49Z","abstract_excerpt":"Medicine is inherently multimodal, requiring clinicians to synthesize information across diverse data streams. Yet the development of multimodal foundation models is constrained by limited access to large-scale, high-quality clinical data. Although PubMed Central (PMC) offers a complementary source of expert-authored image-text data, existing PMC-derived resources remain limited in fidelity, reproducibility, and clinical validation. We introduce MedPMC, an automated, continuously updatable framework that transforms permissively licensed literature into high-fidelity infrastructure for medical "},"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":"2607.07673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-08T17:26:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f96c5e61fbac6b0a3d7c09fea2e5ba22c2bd586b530ef5e37ef9a1b82261cb7c","abstract_canon_sha256":"8b3c7b4dac69c7cfd5c8d6dfb55eb33c8fd3d3d3f3e9f6cb955c4928b41de484"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:38.697478Z","signature_b64":"ivjrM/L308/8qBinl88Y76RNgBlmpBnVcC4v8ahd3wvRo4boc1evzsj+YoSg+AYBZUD530kWZAyDrdnEACXpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21a0dbc1fb36c5f5c15ea1d0ed42cbc692af01baf0f114981b77768344f48673","last_reissued_at":"2026-07-09T01:20:38.697024Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:38.697024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dain Kim, Gui Yang, Hoifung Poon, Hua Xu, Hyunjae Kim, Jaewoo Kang, Jonathan Marquez, Kevin W. Jin, Mengmeng Du, Pan Xiao, Qingyu Chen, Roy Jiang, Rui Shi, Serina S. Applebaum, Sheng Zhang, Tuo Guo, Xuguang Ai, Yan Hu, Yawen Wei, Yiming Kong, Younjoon Chung, Yuelei Fu, Yuexi Du, Yuntian Liu, Yuxuan Tian, Yu Yin, Zhen Chen, Zhiyuan Cao","submitted_at":"2026-07-08T17:26:49Z","abstract_excerpt":"Medicine is inherently multimodal, requiring clinicians to synthesize information across diverse data streams. Yet the development of multimodal foundation models is constrained by limited access to large-scale, high-quality clinical data. Although PubMed Central (PMC) offers a complementary source of expert-authored image-text data, existing PMC-derived resources remain limited in fidelity, reproducibility, and clinical validation. We introduce MedPMC, an automated, continuously updatable framework that transforms permissively licensed literature into high-fidelity infrastructure for medical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07673","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/2607.07673/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":"2607.07673","created_at":"2026-07-09T01:20:38.697086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07673v1","created_at":"2026-07-09T01:20:38.697086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07673","created_at":"2026-07-09T01:20:38.697086+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGQNXQP3G3C7","created_at":"2026-07-09T01:20:38.697086+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGQNXQP3G3C7LQK6","created_at":"2026-07-09T01:20:38.697086+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGQNXQP3","created_at":"2026-07-09T01:20:38.697086+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/EGQNXQP3G3C7LQK6UHIO2QWLY2","json":"https://pith.science/pith/EGQNXQP3G3C7LQK6UHIO2QWLY2.json","graph_json":"https://pith.science/api/pith-number/EGQNXQP3G3C7LQK6UHIO2QWLY2/graph.json","events_json":"https://pith.science/api/pith-number/EGQNXQP3G3C7LQK6UHIO2QWLY2/events.json","paper":"https://pith.science/paper/EGQNXQP3"},"agent_actions":{"view_html":"https://pith.science/pith/EGQNXQP3G3C7LQK6UHIO2QWLY2","download_json":"https://pith.science/pith/EGQNXQP3G3C7LQK6UHIO2QWLY2.json","view_paper":"https://pith.science/paper/EGQNXQP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07673&json=true","fetch_graph":"https://pith.science/api/pith-number/EGQNXQP3G3C7LQK6UHIO2QWLY2/graph.json","fetch_events":"https://pith.science/api/pith-number/EGQNXQP3G3C7LQK6UHIO2QWLY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGQNXQP3G3C7LQK6UHIO2QWLY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGQNXQP3G3C7LQK6UHIO2QWLY2/action/storage_attestation","attest_author":"https://pith.science/pith/EGQNXQP3G3C7LQK6UHIO2QWLY2/action/author_attestation","sign_citation":"https://pith.science/pith/EGQNXQP3G3C7LQK6UHIO2QWLY2/action/citation_signature","submit_replication":"https://pith.science/pith/EGQNXQP3G3C7LQK6UHIO2QWLY2/action/replication_record"}},"created_at":"2026-07-09T01:20:38.697086+00:00","updated_at":"2026-07-09T01:20:38.697086+00:00"}