{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5DHG4ANST3WUX6YFXMZU4FJQPH","short_pith_number":"pith:5DHG4ANS","schema_version":"1.0","canonical_sha256":"e8ce6e01b29eed4bfb05bb334e153079ccd0a109b121d332fb15c5384e5883a7","source":{"kind":"arxiv","id":"2509.00437","version":1},"attestation_state":"computed","paper":{"title":"A Hybrid AI-based and Rule-based Approach to DICOM De-identification: A Solution for the MIDI-B Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Hamideh Haghiri, Klaus H. Maier-Hein, Marco Nolden, Rajesh Baidya, Stefan Dvoretskii","submitted_at":"2025-08-30T09:52:15Z","abstract_excerpt":"Ensuring the de-identification of medical imaging data is a critical step in enabling safe data sharing. This paper presents a hybrid de-identification framework designed to process Digital Imaging and Communications in Medicine (DICOM) files. Our framework adopts a modified, pre-built rule-based component, updated with The Cancer Imaging Archive (TCIA)'s best practices guidelines, as outlined in DICOM PS 3.15, for improved performance. It incorporates PaddleOCR, a robust Optical Character Recognition (OCR) system for extracting text from images, and RoBERTa, a fine-tuned transformer-based mod"},"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":"2509.00437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-30T09:52:15Z","cross_cats_sorted":[],"title_canon_sha256":"136b78f2e32f7cf3889ce02e1b02b928e0d4e966bd3a4f0cfd50c78583899b18","abstract_canon_sha256":"952a142f75fba142359ec4fae454531da959a6134199f8e80aa509750bc547a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:16.351250Z","signature_b64":"lMiyxOAIh48Ys9U5INVj07woixhAuKeCyuA1gRjm7A6tS6dERsEH9JPa/B4yEK1DbBud/V5Ir85MjyDYON/nBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8ce6e01b29eed4bfb05bb334e153079ccd0a109b121d332fb15c5384e5883a7","last_reissued_at":"2026-07-05T12:02:16.350822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:16.350822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hybrid AI-based and Rule-based Approach to DICOM De-identification: A Solution for the MIDI-B Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Hamideh Haghiri, Klaus H. Maier-Hein, Marco Nolden, Rajesh Baidya, Stefan Dvoretskii","submitted_at":"2025-08-30T09:52:15Z","abstract_excerpt":"Ensuring the de-identification of medical imaging data is a critical step in enabling safe data sharing. This paper presents a hybrid de-identification framework designed to process Digital Imaging and Communications in Medicine (DICOM) files. Our framework adopts a modified, pre-built rule-based component, updated with The Cancer Imaging Archive (TCIA)'s best practices guidelines, as outlined in DICOM PS 3.15, for improved performance. It incorporates PaddleOCR, a robust Optical Character Recognition (OCR) system for extracting text from images, and RoBERTa, a fine-tuned transformer-based mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00437","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/2509.00437/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":"2509.00437","created_at":"2026-07-05T12:02:16.350883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00437v1","created_at":"2026-07-05T12:02:16.350883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00437","created_at":"2026-07-05T12:02:16.350883+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DHG4ANST3WU","created_at":"2026-07-05T12:02:16.350883+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DHG4ANST3WUX6YF","created_at":"2026-07-05T12:02:16.350883+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DHG4ANS","created_at":"2026-07-05T12:02:16.350883+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/5DHG4ANST3WUX6YFXMZU4FJQPH","json":"https://pith.science/pith/5DHG4ANST3WUX6YFXMZU4FJQPH.json","graph_json":"https://pith.science/api/pith-number/5DHG4ANST3WUX6YFXMZU4FJQPH/graph.json","events_json":"https://pith.science/api/pith-number/5DHG4ANST3WUX6YFXMZU4FJQPH/events.json","paper":"https://pith.science/paper/5DHG4ANS"},"agent_actions":{"view_html":"https://pith.science/pith/5DHG4ANST3WUX6YFXMZU4FJQPH","download_json":"https://pith.science/pith/5DHG4ANST3WUX6YFXMZU4FJQPH.json","view_paper":"https://pith.science/paper/5DHG4ANS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00437&json=true","fetch_graph":"https://pith.science/api/pith-number/5DHG4ANST3WUX6YFXMZU4FJQPH/graph.json","fetch_events":"https://pith.science/api/pith-number/5DHG4ANST3WUX6YFXMZU4FJQPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DHG4ANST3WUX6YFXMZU4FJQPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DHG4ANST3WUX6YFXMZU4FJQPH/action/storage_attestation","attest_author":"https://pith.science/pith/5DHG4ANST3WUX6YFXMZU4FJQPH/action/author_attestation","sign_citation":"https://pith.science/pith/5DHG4ANST3WUX6YFXMZU4FJQPH/action/citation_signature","submit_replication":"https://pith.science/pith/5DHG4ANST3WUX6YFXMZU4FJQPH/action/replication_record"}},"created_at":"2026-07-05T12:02:16.350883+00:00","updated_at":"2026-07-05T12:02:16.350883+00:00"}