{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MPUQWOLUVVBHQJ3IULMLZKC2HV","short_pith_number":"pith:MPUQWOLU","schema_version":"1.0","canonical_sha256":"63e90b3974ad42782768a2d8bca85a3d717e7dc95a0c42009a55d2862f71973a","source":{"kind":"arxiv","id":"2508.01889","version":1},"attestation_state":"computed","paper":{"title":"Medical Image De-Identification Resources: Synthetic DICOM Data and Tools for Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Kopchick, David Clunie, Fred Prior, Granger Sutton, Keyvan Farahani, Kirk Smith, Laura Opsahl-Ong, Linmin Pei, Michael W. Rutherford, Phillip Farmer, Qinyan Pan, Tracy Nolan, Ulrike Wagner","submitted_at":"2025-08-03T18:48:28Z","abstract_excerpt":"Medical imaging research increasingly depends on large-scale data sharing to promote reproducibility and train Artificial Intelligence (AI) models. Ensuring patient privacy remains a significant challenge for open-access data sharing. Digital Imaging and Communications in Medicine (DICOM), the global standard data format for medical imaging, encodes both essential clinical metadata and extensive protected health information (PHI) and personally identifiable information (PII). Effective de-identification must remove identifiers, preserve scientific utility, and maintain DICOM validity. Tools ex"},"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":"2508.01889","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-03T18:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"76046d5074122a82f1c214092a2215bbcb2bf7fa1a86f164f1e4a76808a19aca","abstract_canon_sha256":"53bd64e082203a25ae40d86849f75d03de489f7875672a4850292f5c44bc8b0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:47.040622Z","signature_b64":"r8RkTfzVjIQ7qe5idfcjDnRQu4Wkx6iifFGKnaiDX2+PGDpogtOfnmj8U8jDUBcbEiN++9hFccH6/GcWkaXwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63e90b3974ad42782768a2d8bca85a3d717e7dc95a0c42009a55d2862f71973a","last_reissued_at":"2026-07-05T11:47:47.040149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:47.040149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Medical Image De-Identification Resources: Synthetic DICOM Data and Tools for Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Kopchick, David Clunie, Fred Prior, Granger Sutton, Keyvan Farahani, Kirk Smith, Laura Opsahl-Ong, Linmin Pei, Michael W. Rutherford, Phillip Farmer, Qinyan Pan, Tracy Nolan, Ulrike Wagner","submitted_at":"2025-08-03T18:48:28Z","abstract_excerpt":"Medical imaging research increasingly depends on large-scale data sharing to promote reproducibility and train Artificial Intelligence (AI) models. Ensuring patient privacy remains a significant challenge for open-access data sharing. Digital Imaging and Communications in Medicine (DICOM), the global standard data format for medical imaging, encodes both essential clinical metadata and extensive protected health information (PHI) and personally identifiable information (PII). Effective de-identification must remove identifiers, preserve scientific utility, and maintain DICOM validity. Tools ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01889","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/2508.01889/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":"2508.01889","created_at":"2026-07-05T11:47:47.040210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01889v1","created_at":"2026-07-05T11:47:47.040210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01889","created_at":"2026-07-05T11:47:47.040210+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPUQWOLUVVBH","created_at":"2026-07-05T11:47:47.040210+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPUQWOLUVVBHQJ3I","created_at":"2026-07-05T11:47:47.040210+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPUQWOLU","created_at":"2026-07-05T11:47:47.040210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.02014","citing_title":"Towards Selection of Large Multimodal Models as Engines for Burned-in Protected Health Information Detection in Medical Images","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV","json":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV.json","graph_json":"https://pith.science/api/pith-number/MPUQWOLUVVBHQJ3IULMLZKC2HV/graph.json","events_json":"https://pith.science/api/pith-number/MPUQWOLUVVBHQJ3IULMLZKC2HV/events.json","paper":"https://pith.science/paper/MPUQWOLU"},"agent_actions":{"view_html":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV","download_json":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV.json","view_paper":"https://pith.science/paper/MPUQWOLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01889&json=true","fetch_graph":"https://pith.science/api/pith-number/MPUQWOLUVVBHQJ3IULMLZKC2HV/graph.json","fetch_events":"https://pith.science/api/pith-number/MPUQWOLUVVBHQJ3IULMLZKC2HV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV/action/storage_attestation","attest_author":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV/action/author_attestation","sign_citation":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV/action/citation_signature","submit_replication":"https://pith.science/pith/MPUQWOLUVVBHQJ3IULMLZKC2HV/action/replication_record"}},"created_at":"2026-07-05T11:47:47.040210+00:00","updated_at":"2026-07-05T11:47:47.040210+00:00"}