{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OPSP2HJSKX2H2MCVGEVBXQME4S","short_pith_number":"pith:OPSP2HJS","schema_version":"1.0","canonical_sha256":"73e4fd1d3255f47d3055312a1bc184e489853cddf43a31e33da55329d546f4f8","source":{"kind":"arxiv","id":"2405.07988","version":2},"attestation_state":"computed","paper":{"title":"MedVersa: A Generalist Foundation Model for Medical Image Interpretation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric J. Topol, Hong-Yu Zhou, Juli\\'an Nicol\\'as Acosta, Pranav Rajpurkar, Subathra Adithan, Suvrankar Datta","submitted_at":"2024-05-13T17:58:51Z","abstract_excerpt":"Current medical AI systems are often limited to narrow applications, hindering widespread adoption. We present MedVersa, a generalist foundation model trained on tens of millions of compiled medical instances. MedVersa unlocks generalist learning from multimodal inputs and outputs, representing the first example of a generalist model reaching competitive performance with leading specialized solutions across a variety of medical imaging scenarios. MedVersa achieves state-of-the-art performance in nine tasks, sometimes outperforming counterparts by over 10%. Radiologist evaluation shows MedVersa"},"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":"2405.07988","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-13T17:58:51Z","cross_cats_sorted":[],"title_canon_sha256":"ec4f23b20ffe6301ba22d74f3ef7bba6b05cb5eaae2f86dd35a42375c471be0d","abstract_canon_sha256":"b1aaf02ca0a73de1a828ab81b10cca0c143674f2a4eb55d525cb5ba2ce827c24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:38.768873Z","signature_b64":"W9zM8bbmHgbFonSHy+QXdmY6sqifXIeUE93zKRmGO5PcdxKUg3p3/9vQITEIR99+IToICmBUsHbRxrz6VXwNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73e4fd1d3255f47d3055312a1bc184e489853cddf43a31e33da55329d546f4f8","last_reissued_at":"2026-07-05T11:18:38.768431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:38.768431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedVersa: A Generalist Foundation Model for Medical Image Interpretation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric J. Topol, Hong-Yu Zhou, Juli\\'an Nicol\\'as Acosta, Pranav Rajpurkar, Subathra Adithan, Suvrankar Datta","submitted_at":"2024-05-13T17:58:51Z","abstract_excerpt":"Current medical AI systems are often limited to narrow applications, hindering widespread adoption. We present MedVersa, a generalist foundation model trained on tens of millions of compiled medical instances. MedVersa unlocks generalist learning from multimodal inputs and outputs, representing the first example of a generalist model reaching competitive performance with leading specialized solutions across a variety of medical imaging scenarios. MedVersa achieves state-of-the-art performance in nine tasks, sometimes outperforming counterparts by over 10%. Radiologist evaluation shows MedVersa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07988","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/2405.07988/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":"2405.07988","created_at":"2026-07-05T11:18:38.768487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.07988v2","created_at":"2026-07-05T11:18:38.768487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07988","created_at":"2026-07-05T11:18:38.768487+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPSP2HJSKX2H","created_at":"2026-07-05T11:18:38.768487+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPSP2HJSKX2H2MCV","created_at":"2026-07-05T11:18:38.768487+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPSP2HJS","created_at":"2026-07-05T11:18:38.768487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11702","citing_title":"MedCTA: A Benchmark for Clinical Tool Agents","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03417","citing_title":"A unified multi-task framework enables interpretable chest radiograph analysis","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08819","citing_title":"From pre-training to downstream performance: Does domain-specific pre-training make sense?","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13598","citing_title":"Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S","json":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S.json","graph_json":"https://pith.science/api/pith-number/OPSP2HJSKX2H2MCVGEVBXQME4S/graph.json","events_json":"https://pith.science/api/pith-number/OPSP2HJSKX2H2MCVGEVBXQME4S/events.json","paper":"https://pith.science/paper/OPSP2HJS"},"agent_actions":{"view_html":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S","download_json":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S.json","view_paper":"https://pith.science/paper/OPSP2HJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.07988&json=true","fetch_graph":"https://pith.science/api/pith-number/OPSP2HJSKX2H2MCVGEVBXQME4S/graph.json","fetch_events":"https://pith.science/api/pith-number/OPSP2HJSKX2H2MCVGEVBXQME4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S/action/storage_attestation","attest_author":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S/action/author_attestation","sign_citation":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S/action/citation_signature","submit_replication":"https://pith.science/pith/OPSP2HJSKX2H2MCVGEVBXQME4S/action/replication_record"}},"created_at":"2026-07-05T11:18:38.768487+00:00","updated_at":"2026-07-05T11:18:38.768487+00:00"}