{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QGS5K4T2TDYYUUWS74OCADBTW7","short_pith_number":"pith:QGS5K4T2","schema_version":"1.0","canonical_sha256":"81a5d5727a98f18a52d2ff1c200c33b7e55c7247dec91262d295c1a5e0249da9","source":{"kind":"arxiv","id":"2501.02816","version":1},"attestation_state":"computed","paper":{"title":"InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiwei Zhang, Kai Wang, Qixian Hao, Shaozhang Niu","submitted_at":"2025-01-06T07:32:12Z","abstract_excerpt":"As artificial intelligence advances rapidly, particularly with the advent of GANs and diffusion models, the accuracy of Image Inpainting Localization (IIL) has become increasingly challenging. Current IIL methods face two main challenges: a tendency towards overconfidence, leading to incorrect predictions; and difficulty in detecting subtle tampering boundaries in inpainted images. In response, we propose a new paradigm that treats IIL as a conditional mask generation task utilizing diffusion models. Our method, InpDiffusion, utilizes the denoising process enhanced by the integration of image "},"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":"2501.02816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T07:32:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14c0128fbc076fbdf5a307ed49d69ce559b6d22f62e52a86b6143b11b5813397","abstract_canon_sha256":"86aa8f6d670837035dc116be533a9583de9c60f0c4d14af416ed1482beda37eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:12.799251Z","signature_b64":"Syc4nD96rE38t11IumQVmvzvyh0CoY49z91cVTobpOj6v/tVnX2/xIgGZVqZwMbDESS77bVrBKiL5Py3TtEABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81a5d5727a98f18a52d2ff1c200c33b7e55c7247dec91262d295c1a5e0249da9","last_reissued_at":"2026-07-05T09:57:12.798786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:12.798786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiwei Zhang, Kai Wang, Qixian Hao, Shaozhang Niu","submitted_at":"2025-01-06T07:32:12Z","abstract_excerpt":"As artificial intelligence advances rapidly, particularly with the advent of GANs and diffusion models, the accuracy of Image Inpainting Localization (IIL) has become increasingly challenging. Current IIL methods face two main challenges: a tendency towards overconfidence, leading to incorrect predictions; and difficulty in detecting subtle tampering boundaries in inpainted images. In response, we propose a new paradigm that treats IIL as a conditional mask generation task utilizing diffusion models. Our method, InpDiffusion, utilizes the denoising process enhanced by the integration of image "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02816","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/2501.02816/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":"2501.02816","created_at":"2026-07-05T09:57:12.798848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02816v1","created_at":"2026-07-05T09:57:12.798848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02816","created_at":"2026-07-05T09:57:12.798848+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGS5K4T2TDYY","created_at":"2026-07-05T09:57:12.798848+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGS5K4T2TDYYUUWS","created_at":"2026-07-05T09:57:12.798848+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGS5K4T2","created_at":"2026-07-05T09:57:12.798848+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/QGS5K4T2TDYYUUWS74OCADBTW7","json":"https://pith.science/pith/QGS5K4T2TDYYUUWS74OCADBTW7.json","graph_json":"https://pith.science/api/pith-number/QGS5K4T2TDYYUUWS74OCADBTW7/graph.json","events_json":"https://pith.science/api/pith-number/QGS5K4T2TDYYUUWS74OCADBTW7/events.json","paper":"https://pith.science/paper/QGS5K4T2"},"agent_actions":{"view_html":"https://pith.science/pith/QGS5K4T2TDYYUUWS74OCADBTW7","download_json":"https://pith.science/pith/QGS5K4T2TDYYUUWS74OCADBTW7.json","view_paper":"https://pith.science/paper/QGS5K4T2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02816&json=true","fetch_graph":"https://pith.science/api/pith-number/QGS5K4T2TDYYUUWS74OCADBTW7/graph.json","fetch_events":"https://pith.science/api/pith-number/QGS5K4T2TDYYUUWS74OCADBTW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGS5K4T2TDYYUUWS74OCADBTW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGS5K4T2TDYYUUWS74OCADBTW7/action/storage_attestation","attest_author":"https://pith.science/pith/QGS5K4T2TDYYUUWS74OCADBTW7/action/author_attestation","sign_citation":"https://pith.science/pith/QGS5K4T2TDYYUUWS74OCADBTW7/action/citation_signature","submit_replication":"https://pith.science/pith/QGS5K4T2TDYYUUWS74OCADBTW7/action/replication_record"}},"created_at":"2026-07-05T09:57:12.798848+00:00","updated_at":"2026-07-05T09:57:12.798848+00:00"}