{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3GZLBNSYJR7YXUXFDHQ76DBGDZ","short_pith_number":"pith:3GZLBNSY","schema_version":"1.0","canonical_sha256":"d9b2b0b6584c7f8bd2e519e1ff0c261e5a259a23c748b13ff02544ea29abbc9c","source":{"kind":"arxiv","id":"2603.18577","version":2},"attestation_state":"computed","paper":{"title":"MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Pu, Jian Zhang, Kai He, Mengling Feng, Qingyuan Lei, Yuling Xu, Zhihui Chen","submitted_at":"2026-03-19T07:38:11Z","abstract_excerpt":"Text-guided image editors can now manipulate authentic medical scans with high fidelity, enabling lesion implantation/removal that threatens clinical trust and safety. Existing defenses are inadequate for healthcare. Medical detectors are largely black-box, while MLLM-based explainers are typically post-hoc, lack medical expertise, and may hallucinate evidence on ambiguous cases. We present MedForge, a data-and-method solution for pre-hoc, evidence-grounded medical forgery detection. We introduce MedForge-90K, a large-scale benchmark of realistic lesion edits across 19 pathologies with expert-"},"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":"2603.18577","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-19T07:38:11Z","cross_cats_sorted":[],"title_canon_sha256":"2632f1a47e9a654f6393a588f8d4b95b95f955ffb020a417096b0b2c4827294c","abstract_canon_sha256":"8976ccaf7adb70f83007337bc30101f1120b9bc2e32942ccf9ea5eaedb2ffa85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:48.591091Z","signature_b64":"IFKH3se446h4ZujiuqWFs8fMB0UShmBdxQI/EyUBkAu/QMdaCO33H1kZcaG3JVLkQM8mmVjTirRIaSehXoUHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9b2b0b6584c7f8bd2e519e1ff0c261e5a259a23c748b13ff02544ea29abbc9c","last_reissued_at":"2026-06-04T01:08:48.590379Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:48.590379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Pu, Jian Zhang, Kai He, Mengling Feng, Qingyuan Lei, Yuling Xu, Zhihui Chen","submitted_at":"2026-03-19T07:38:11Z","abstract_excerpt":"Text-guided image editors can now manipulate authentic medical scans with high fidelity, enabling lesion implantation/removal that threatens clinical trust and safety. Existing defenses are inadequate for healthcare. Medical detectors are largely black-box, while MLLM-based explainers are typically post-hoc, lack medical expertise, and may hallucinate evidence on ambiguous cases. We present MedForge, a data-and-method solution for pre-hoc, evidence-grounded medical forgery detection. We introduce MedForge-90K, a large-scale benchmark of realistic lesion edits across 19 pathologies with expert-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.18577","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/2603.18577/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":"2603.18577","created_at":"2026-06-04T01:08:48.590478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.18577v2","created_at":"2026-06-04T01:08:48.590478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.18577","created_at":"2026-06-04T01:08:48.590478+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GZLBNSYJR7Y","created_at":"2026-06-04T01:08:48.590478+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GZLBNSYJR7YXUXF","created_at":"2026-06-04T01:08:48.590478+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GZLBNSY","created_at":"2026-06-04T01:08:48.590478+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/3GZLBNSYJR7YXUXFDHQ76DBGDZ","json":"https://pith.science/pith/3GZLBNSYJR7YXUXFDHQ76DBGDZ.json","graph_json":"https://pith.science/api/pith-number/3GZLBNSYJR7YXUXFDHQ76DBGDZ/graph.json","events_json":"https://pith.science/api/pith-number/3GZLBNSYJR7YXUXFDHQ76DBGDZ/events.json","paper":"https://pith.science/paper/3GZLBNSY"},"agent_actions":{"view_html":"https://pith.science/pith/3GZLBNSYJR7YXUXFDHQ76DBGDZ","download_json":"https://pith.science/pith/3GZLBNSYJR7YXUXFDHQ76DBGDZ.json","view_paper":"https://pith.science/paper/3GZLBNSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.18577&json=true","fetch_graph":"https://pith.science/api/pith-number/3GZLBNSYJR7YXUXFDHQ76DBGDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3GZLBNSYJR7YXUXFDHQ76DBGDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GZLBNSYJR7YXUXFDHQ76DBGDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GZLBNSYJR7YXUXFDHQ76DBGDZ/action/storage_attestation","attest_author":"https://pith.science/pith/3GZLBNSYJR7YXUXFDHQ76DBGDZ/action/author_attestation","sign_citation":"https://pith.science/pith/3GZLBNSYJR7YXUXFDHQ76DBGDZ/action/citation_signature","submit_replication":"https://pith.science/pith/3GZLBNSYJR7YXUXFDHQ76DBGDZ/action/replication_record"}},"created_at":"2026-06-04T01:08:48.590478+00:00","updated_at":"2026-06-04T01:08:48.590478+00:00"}