{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IQUOJVRDDXINXQVA35WDGTNAYW","short_pith_number":"pith:IQUOJVRD","schema_version":"1.0","canonical_sha256":"4428e4d6231dd0dbc2a0df6c334da0c58c5ba6a9f05750658916873fb6ccb1ba","source":{"kind":"arxiv","id":"2605.14091","version":1},"attestation_state":"computed","paper":{"title":"Venus-DeFakerOne: Unified Fake Image Detection & Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DeFakerOne integrates InternVL2 and SAM2 into one model that detects and localizes image forgeries across many generation types at once.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"GuangJian Team","submitted_at":"2026-05-13T20:20:33Z","abstract_excerpt":"In recent years, the rapid evolution of generative AI has fundamentally reshaped the paradigm of image forgery, breaking the traditional boundaries between document editing, natural image manipulation, DeepFake generation, and full-image AIGC synthesis. Despite this shift toward unified forgery generation, existing research in Fake Image Detection and Localization (FIDL) remains fragmented. This creates a mismatch between increasingly unified forgery generation mechanisms and the domain-specific detection paradigm. Bridging this mismatch poses two key challenges for FIDL: understanding cross-d"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T20:20:33Z","cross_cats_sorted":[],"title_canon_sha256":"526ac25e496562b5d0b373f5d0d12e857027f8b2d4d4e1c2a0c895e9706f4d4d","abstract_canon_sha256":"1adb4fcd9e84da8667fe0d5f77a829cb4da772bd2be76eb965b901e490e441fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:12.211429Z","signature_b64":"4ePp1XSU6JyrQIEyGEqr8U0+nsmhLrObvCvs7WS+WXgeiQjilhYPkkjsk6joEFZYzIbP764/PI4hfFL1/a0GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4428e4d6231dd0dbc2a0df6c334da0c58c5ba6a9f05750658916873fb6ccb1ba","last_reissued_at":"2026-05-17T23:39:12.210632Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:12.210632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Venus-DeFakerOne: Unified Fake Image Detection & Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DeFakerOne integrates InternVL2 and SAM2 into one model that detects and localizes image forgeries across many generation types at once.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"GuangJian Team","submitted_at":"2026-05-13T20:20:33Z","abstract_excerpt":"In recent years, the rapid evolution of generative AI has fundamentally reshaped the paradigm of image forgery, breaking the traditional boundaries between document editing, natural image manipulation, DeepFake generation, and full-image AIGC synthesis. Despite this shift toward unified forgery generation, existing research in Fake Image Detection and Localization (FIDL) remains fragmented. This creates a mismatch between increasingly unified forgery generation mechanisms and the domain-specific detection paradigm. Bridging this mismatch poses two key challenges for FIDL: understanding cross-d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"DeFakerOne achieves state-of-the-art performance, outperforming baselines on 39 forgery detection benchmarks and 9 localization benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That integrating InternVL2 and SAM2 with fine-grained supervision sufficiently captures cross-domain artifact transfer and interference without domain-specific adaptations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DeFakerOne integrates InternVL2 and SAM2 into a single model that achieves state-of-the-art results on 39 detection and 9 localization benchmarks for unified fake image detection and localization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DeFakerOne integrates InternVL2 and SAM2 into one model that detects and localizes image forgeries across many generation types at once.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ed973a2587b9722d376254be1c3e5915b5bd0b7e736be819e5f6222315ae2f62"},"source":{"id":"2605.14091","kind":"arxiv","version":1},"verdict":{"id":"8e319d0d-7138-4122-9a47-557cd0be4388","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:25:41.568710Z","strongest_claim":"DeFakerOne achieves state-of-the-art performance, outperforming baselines on 39 forgery detection benchmarks and 9 localization benchmarks.","one_line_summary":"DeFakerOne integrates InternVL2 and SAM2 into a single model that achieves state-of-the-art results on 39 detection and 9 localization benchmarks for unified fake image detection and localization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That integrating InternVL2 and SAM2 with fine-grained supervision sufficiently captures cross-domain artifact transfer and interference without domain-specific adaptations.","pith_extraction_headline":"DeFakerOne integrates InternVL2 and SAM2 into one model that detects and localizes image forgeries across many generation types at once."},"references":{"count":240,"sample":[{"doi":"","year":2025,"title":"Findings of the Association for Computational Linguistics: EMNLP 2025 , pages=","work_id":"6bb81f2e-0894-4d04-ac96-0b406a06140a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection","work_id":"f28a8b39-972c-46e1-85e2-94c11302493e","ref_index":2,"cited_arxiv_id":"2506.00979","is_internal_anchor":true},{"doi":"","year":null,"title":"Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detection , year=","work_id":"b3c836c1-b202-4f85-ad2b-0fe08c4b4978","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Fourteenth International Conference on Learning Representations , year=","work_id":"e8971a5c-107c-48b8-908f-1ad1f40e577d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Effort: Efficient Orthogonal Modeling for Generalizable AI-Generated Image Detection , author=. ICML , year=","work_id":"7f1d763b-c6a7-4280-b3ac-0c5964af5e86","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":240,"snapshot_sha256":"3c6447ba8f4a3dec70ab7a9b6df50a21d826b3fd666c20097b76af70c58198ba","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"36ca793253c2e3d07f53b691468c3fb3817fd8be953a450785426c16a88d27b7"},"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":"2605.14091","created_at":"2026-05-17T23:39:12.210764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14091v1","created_at":"2026-05-17T23:39:12.210764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14091","created_at":"2026-05-17T23:39:12.210764+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQUOJVRDDXIN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQUOJVRDDXINXQVA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQUOJVRD","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW","json":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW.json","graph_json":"https://pith.science/api/pith-number/IQUOJVRDDXINXQVA35WDGTNAYW/graph.json","events_json":"https://pith.science/api/pith-number/IQUOJVRDDXINXQVA35WDGTNAYW/events.json","paper":"https://pith.science/paper/IQUOJVRD"},"agent_actions":{"view_html":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW","download_json":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW.json","view_paper":"https://pith.science/paper/IQUOJVRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14091&json=true","fetch_graph":"https://pith.science/api/pith-number/IQUOJVRDDXINXQVA35WDGTNAYW/graph.json","fetch_events":"https://pith.science/api/pith-number/IQUOJVRDDXINXQVA35WDGTNAYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW/action/storage_attestation","attest_author":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW/action/author_attestation","sign_citation":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW/action/citation_signature","submit_replication":"https://pith.science/pith/IQUOJVRDDXINXQVA35WDGTNAYW/action/replication_record"}},"created_at":"2026-05-17T23:39:12.210764+00:00","updated_at":"2026-05-17T23:39:12.210764+00:00"}