{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NW4ODDMS6J5QQIDT7DWXA2YOLS","short_pith_number":"pith:NW4ODDMS","schema_version":"1.0","canonical_sha256":"6db8e18d92f27b082073f8ed706b0e5ca2156f7870e547b705e1d0174cb43689","source":{"kind":"arxiv","id":"2507.16596","version":2},"attestation_state":"computed","paper":{"title":"A Multimodal Deviation Perceiving Framework for Weakly-Supervised Temporal Forgery Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junyan Wu, Qian Wang, Wei Lu, Wenbo Xu, Xiangyang Luo","submitted_at":"2025-07-22T13:55:16Z","abstract_excerpt":"Current researches on Deepfake forensics often treat detection as a classification task or temporal forgery localization problem, which are usually restrictive, time-consuming, and challenging to scale for large datasets. To resolve these issues, we present a multimodal deviation perceiving framework for weakly-supervised temporal forgery localization (MDP), which aims to identify temporal partial forged segments using only video-level annotations. The MDP proposes a novel multimodal interaction mechanism (MI) and an extensible deviation perceiving loss to perceive multimodal deviation, which "},"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":"2507.16596","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T13:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"b01d044bb59c15b03d63bef481e65647b3501a51012e7b9389b1c7114b9d046b","abstract_canon_sha256":"f26526816cff1d6b522b3416aa233c31f8d6e3972921d35c45092ce7eb5ca505"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:05.910942Z","signature_b64":"ol42yA4GzgUZdmuttKfsASLc/D1zUQhkmosS9OohqfDYQrwQwVDLQb+/Y2p1RamuUn5AhqSGEzrjdrPA5acWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6db8e18d92f27b082073f8ed706b0e5ca2156f7870e547b705e1d0174cb43689","last_reissued_at":"2026-07-05T11:48:05.910410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:05.910410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multimodal Deviation Perceiving Framework for Weakly-Supervised Temporal Forgery Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junyan Wu, Qian Wang, Wei Lu, Wenbo Xu, Xiangyang Luo","submitted_at":"2025-07-22T13:55:16Z","abstract_excerpt":"Current researches on Deepfake forensics often treat detection as a classification task or temporal forgery localization problem, which are usually restrictive, time-consuming, and challenging to scale for large datasets. To resolve these issues, we present a multimodal deviation perceiving framework for weakly-supervised temporal forgery localization (MDP), which aims to identify temporal partial forged segments using only video-level annotations. The MDP proposes a novel multimodal interaction mechanism (MI) and an extensible deviation perceiving loss to perceive multimodal deviation, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16596","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/2507.16596/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":"2507.16596","created_at":"2026-07-05T11:48:05.910481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16596v2","created_at":"2026-07-05T11:48:05.910481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16596","created_at":"2026-07-05T11:48:05.910481+00:00"},{"alias_kind":"pith_short_12","alias_value":"NW4ODDMS6J5Q","created_at":"2026-07-05T11:48:05.910481+00:00"},{"alias_kind":"pith_short_16","alias_value":"NW4ODDMS6J5QQIDT","created_at":"2026-07-05T11:48:05.910481+00:00"},{"alias_kind":"pith_short_8","alias_value":"NW4ODDMS","created_at":"2026-07-05T11:48:05.910481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02187","citing_title":"Registering the 4D Millimeter Wave Radar Point Clouds Via Generalized Method of Moments","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS","json":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS.json","graph_json":"https://pith.science/api/pith-number/NW4ODDMS6J5QQIDT7DWXA2YOLS/graph.json","events_json":"https://pith.science/api/pith-number/NW4ODDMS6J5QQIDT7DWXA2YOLS/events.json","paper":"https://pith.science/paper/NW4ODDMS"},"agent_actions":{"view_html":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS","download_json":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS.json","view_paper":"https://pith.science/paper/NW4ODDMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16596&json=true","fetch_graph":"https://pith.science/api/pith-number/NW4ODDMS6J5QQIDT7DWXA2YOLS/graph.json","fetch_events":"https://pith.science/api/pith-number/NW4ODDMS6J5QQIDT7DWXA2YOLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS/action/storage_attestation","attest_author":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS/action/author_attestation","sign_citation":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS/action/citation_signature","submit_replication":"https://pith.science/pith/NW4ODDMS6J5QQIDT7DWXA2YOLS/action/replication_record"}},"created_at":"2026-07-05T11:48:05.910481+00:00","updated_at":"2026-07-05T11:48:05.910481+00:00"}