{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TCV6A32VXCBP2ZTRUW7OMN6TKX","short_pith_number":"pith:TCV6A32V","schema_version":"1.0","canonical_sha256":"98abe06f55b882fd6671a5bee637d355caabd3d9f5d4db84a3a86ab14c6c47fe","source":{"kind":"arxiv","id":"2506.12186","version":2},"attestation_state":"computed","paper":{"title":"MRI-CORE: A Foundation Model for Magnetic Resonance Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Hanxue Gu, Haoyu Dong, Maciej A. Mazurowski, Nicholas Konz, Qihang Li, Yaqian Chen, Yuwen Chen","submitted_at":"2025-06-13T19:26:56Z","abstract_excerpt":"The widespread use of Magnetic Resonance Imaging (MRI) in combination with deep learning shows promise for many high-impact automated diagnostic and prognostic tools. However, training new models requires large amounts of labeled data, a challenge due to high cost of precise annotations and data privacy. To address this issue, we introduce the MRI-CORE, a vision foundation model trained using more than 6 million slices from over 110 thousand MRI volumes across 18 body locations. Our experiments show notable improvements in performance over state-of-the-art methods in 13 data-restricted segment"},"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":"2506.12186","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2025-06-13T19:26:56Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"247c20937a727edafc58c19c2f37e923d258d3860d171a2dab07eeda53337819","abstract_canon_sha256":"da47663f8d7aaac11eb4a65dd0e0b342d696a37f1ff12fc4d623d6aaaf4d0bf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:43.221340Z","signature_b64":"RjPQwrqja1O+ygRk6Dzr0ad0poMMPv5VjeU4fe42fs0+evUU36wMhLfEKYOCVSwluq90r8zqMHFHcABSbW4iCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98abe06f55b882fd6671a5bee637d355caabd3d9f5d4db84a3a86ab14c6c47fe","last_reissued_at":"2026-07-05T11:41:43.220829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:43.220829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MRI-CORE: A Foundation Model for Magnetic Resonance Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Hanxue Gu, Haoyu Dong, Maciej A. Mazurowski, Nicholas Konz, Qihang Li, Yaqian Chen, Yuwen Chen","submitted_at":"2025-06-13T19:26:56Z","abstract_excerpt":"The widespread use of Magnetic Resonance Imaging (MRI) in combination with deep learning shows promise for many high-impact automated diagnostic and prognostic tools. However, training new models requires large amounts of labeled data, a challenge due to high cost of precise annotations and data privacy. To address this issue, we introduce the MRI-CORE, a vision foundation model trained using more than 6 million slices from over 110 thousand MRI volumes across 18 body locations. Our experiments show notable improvements in performance over state-of-the-art methods in 13 data-restricted segment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12186","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/2506.12186/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":"2506.12186","created_at":"2026-07-05T11:41:43.220891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12186v2","created_at":"2026-07-05T11:41:43.220891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12186","created_at":"2026-07-05T11:41:43.220891+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCV6A32VXCBP","created_at":"2026-07-05T11:41:43.220891+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCV6A32VXCBP2ZTR","created_at":"2026-07-05T11:41:43.220891+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCV6A32V","created_at":"2026-07-05T11:41:43.220891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23172","citing_title":"A Benchmark of (MRI-) Foundation Models to Predict IDH Mutational Status in Glioma","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08164","citing_title":"How Much MRI Preprocessing Is Enough? A Cost-Utility Study for Brain MRI Foundation Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30829","citing_title":"LegSegNet: A Public Deep Learning System for Lower Extremity CT Tissue Segmentation and Quantification","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23172","citing_title":"A Benchmark of (MRI-) Foundation Models to Predict IDH Mutational Status in Glioma","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX","json":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX.json","graph_json":"https://pith.science/api/pith-number/TCV6A32VXCBP2ZTRUW7OMN6TKX/graph.json","events_json":"https://pith.science/api/pith-number/TCV6A32VXCBP2ZTRUW7OMN6TKX/events.json","paper":"https://pith.science/paper/TCV6A32V"},"agent_actions":{"view_html":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX","download_json":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX.json","view_paper":"https://pith.science/paper/TCV6A32V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12186&json=true","fetch_graph":"https://pith.science/api/pith-number/TCV6A32VXCBP2ZTRUW7OMN6TKX/graph.json","fetch_events":"https://pith.science/api/pith-number/TCV6A32VXCBP2ZTRUW7OMN6TKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX/action/storage_attestation","attest_author":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX/action/author_attestation","sign_citation":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX/action/citation_signature","submit_replication":"https://pith.science/pith/TCV6A32VXCBP2ZTRUW7OMN6TKX/action/replication_record"}},"created_at":"2026-07-05T11:41:43.220891+00:00","updated_at":"2026-07-05T11:41:43.220891+00:00"}