{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IMKZWY4QVJJSR65CBMXSGZWNHU","short_pith_number":"pith:IMKZWY4Q","schema_version":"1.0","canonical_sha256":"43159b6390aa5328fba20b2f2366cd3d268e6d460b6fdb16006e874dd3ff5319","source":{"kind":"arxiv","id":"2411.14823","version":2},"attestation_state":"computed","paper":{"title":"Omni-IML: Towards Unified Image Manipulation Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenfan Qu, Fengjun Guo, Lianwen Jin, Yiwu Zhong","submitted_at":"2024-11-22T09:44:13Z","abstract_excerpt":"Existing Image Manipulation Localization (IML) methods mostly rely heavily on task-specific designs, making them perform well only on the target IML task, while joint training on multiple IML tasks causes significant performance degradation, hindering real applications.\n  To this end, we propose Omni-IML, the first generalist model designed to unify IML across diverse tasks.\n  Specifically, Omni-IML achieves generalization through three key components: (1) a Modal Gate Encoder, which adaptively selects the optimal encoding modality per sample, (2) a Dynamic Weight Decoder, which dynamically ad"},"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":"2411.14823","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:44:13Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"a16c15c4dbbc7d54771d67dda72325f7264383cb6e5c97133d73cdb5bf51de95","abstract_canon_sha256":"5faabaeaa5a852e6a502f51be05be9ef8f3dc54426d83fe7424eb38349aa0d71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:26.299712Z","signature_b64":"dimOFWMv0bxAbuppmbrnPqPtZh8htdB7ZTmNACPF7YE4pnhXHMh5JN07mpWKQPdD1Nb6TyF3IBDpetqVE/tAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43159b6390aa5328fba20b2f2366cd3d268e6d460b6fdb16006e874dd3ff5319","last_reissued_at":"2026-07-05T10:55:26.299127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:26.299127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omni-IML: Towards Unified Image Manipulation Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenfan Qu, Fengjun Guo, Lianwen Jin, Yiwu Zhong","submitted_at":"2024-11-22T09:44:13Z","abstract_excerpt":"Existing Image Manipulation Localization (IML) methods mostly rely heavily on task-specific designs, making them perform well only on the target IML task, while joint training on multiple IML tasks causes significant performance degradation, hindering real applications.\n  To this end, we propose Omni-IML, the first generalist model designed to unify IML across diverse tasks.\n  Specifically, Omni-IML achieves generalization through three key components: (1) a Modal Gate Encoder, which adaptively selects the optimal encoding modality per sample, (2) a Dynamic Weight Decoder, which dynamically ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14823","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/2411.14823/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":"2411.14823","created_at":"2026-07-05T10:55:26.299207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14823v2","created_at":"2026-07-05T10:55:26.299207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14823","created_at":"2026-07-05T10:55:26.299207+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMKZWY4QVJJS","created_at":"2026-07-05T10:55:26.299207+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMKZWY4QVJJSR65C","created_at":"2026-07-05T10:55:26.299207+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMKZWY4Q","created_at":"2026-07-05T10:55:26.299207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22285","citing_title":"Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT-Quantization Embedding","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU","json":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU.json","graph_json":"https://pith.science/api/pith-number/IMKZWY4QVJJSR65CBMXSGZWNHU/graph.json","events_json":"https://pith.science/api/pith-number/IMKZWY4QVJJSR65CBMXSGZWNHU/events.json","paper":"https://pith.science/paper/IMKZWY4Q"},"agent_actions":{"view_html":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU","download_json":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU.json","view_paper":"https://pith.science/paper/IMKZWY4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14823&json=true","fetch_graph":"https://pith.science/api/pith-number/IMKZWY4QVJJSR65CBMXSGZWNHU/graph.json","fetch_events":"https://pith.science/api/pith-number/IMKZWY4QVJJSR65CBMXSGZWNHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU/action/storage_attestation","attest_author":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU/action/author_attestation","sign_citation":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU/action/citation_signature","submit_replication":"https://pith.science/pith/IMKZWY4QVJJSR65CBMXSGZWNHU/action/replication_record"}},"created_at":"2026-07-05T10:55:26.299207+00:00","updated_at":"2026-07-05T10:55:26.299207+00:00"}