{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5ASV4ROU5IMPL35WK3K76RXCKB","short_pith_number":"pith:5ASV4ROU","schema_version":"1.0","canonical_sha256":"e8255e45d4ea18f5efb656d5ff46e25051d19534c9107c59643043f7c8dd8f70","source":{"kind":"arxiv","id":"2607.04472","version":1},"attestation_state":"computed","paper":{"title":"EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Jiang, Ke Zhang, Quan Zhang, Shen Shen","submitted_at":"2026-07-05T19:33:21Z","abstract_excerpt":"The rapid proliferation of artificial intelligence-generated content necessitates reliable multimodal forensics. Beyond video-level binary classification, precisely localizing sparsely distributed forged segments in long-form videos remains a critical challenge. This task is particularly difficult when manipulations are subtly embedded and cross-modal signals are weak and temporally diffuse. To address these challenges, we propose EVAS, an end-to-end multimodal framework for temporal forgery localization. At its core, a Multi-Stage Audio-Visual Synergy mechanism facilitates progressive cross-m"},"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":"2607.04472","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T19:33:21Z","cross_cats_sorted":[],"title_canon_sha256":"b9bfd9e3a62aeb33246139fb3a41ca6cef9c191f909039b3955170674ee8ef76","abstract_canon_sha256":"df0138b790dcc03a11a9e39067809612f3dbefce85ca5a8b86f1316479bb2cb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:20.836660Z","signature_b64":"uzqIOjMtZO6AQCNaXz0UZuQ6x59ebeoqc8bt7a0z9OgyyhLTG59xabYHShF7xR+6PZ7qUuIYhYNkUXrYBlOpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8255e45d4ea18f5efb656d5ff46e25051d19534c9107c59643043f7c8dd8f70","last_reissued_at":"2026-07-07T02:19:20.836082Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:20.836082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Jiang, Ke Zhang, Quan Zhang, Shen Shen","submitted_at":"2026-07-05T19:33:21Z","abstract_excerpt":"The rapid proliferation of artificial intelligence-generated content necessitates reliable multimodal forensics. Beyond video-level binary classification, precisely localizing sparsely distributed forged segments in long-form videos remains a critical challenge. This task is particularly difficult when manipulations are subtly embedded and cross-modal signals are weak and temporally diffuse. To address these challenges, we propose EVAS, an end-to-end multimodal framework for temporal forgery localization. At its core, a Multi-Stage Audio-Visual Synergy mechanism facilitates progressive cross-m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04472","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/2607.04472/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":"2607.04472","created_at":"2026-07-07T02:19:20.836168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04472v1","created_at":"2026-07-07T02:19:20.836168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04472","created_at":"2026-07-07T02:19:20.836168+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ASV4ROU5IMP","created_at":"2026-07-07T02:19:20.836168+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ASV4ROU5IMPL35W","created_at":"2026-07-07T02:19:20.836168+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ASV4ROU","created_at":"2026-07-07T02:19:20.836168+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/5ASV4ROU5IMPL35WK3K76RXCKB","json":"https://pith.science/pith/5ASV4ROU5IMPL35WK3K76RXCKB.json","graph_json":"https://pith.science/api/pith-number/5ASV4ROU5IMPL35WK3K76RXCKB/graph.json","events_json":"https://pith.science/api/pith-number/5ASV4ROU5IMPL35WK3K76RXCKB/events.json","paper":"https://pith.science/paper/5ASV4ROU"},"agent_actions":{"view_html":"https://pith.science/pith/5ASV4ROU5IMPL35WK3K76RXCKB","download_json":"https://pith.science/pith/5ASV4ROU5IMPL35WK3K76RXCKB.json","view_paper":"https://pith.science/paper/5ASV4ROU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04472&json=true","fetch_graph":"https://pith.science/api/pith-number/5ASV4ROU5IMPL35WK3K76RXCKB/graph.json","fetch_events":"https://pith.science/api/pith-number/5ASV4ROU5IMPL35WK3K76RXCKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ASV4ROU5IMPL35WK3K76RXCKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ASV4ROU5IMPL35WK3K76RXCKB/action/storage_attestation","attest_author":"https://pith.science/pith/5ASV4ROU5IMPL35WK3K76RXCKB/action/author_attestation","sign_citation":"https://pith.science/pith/5ASV4ROU5IMPL35WK3K76RXCKB/action/citation_signature","submit_replication":"https://pith.science/pith/5ASV4ROU5IMPL35WK3K76RXCKB/action/replication_record"}},"created_at":"2026-07-07T02:19:20.836168+00:00","updated_at":"2026-07-07T02:19:20.836168+00:00"}