{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PB6T43WH5F3SX72C5ZYCRPPEHG","short_pith_number":"pith:PB6T43WH","schema_version":"1.0","canonical_sha256":"787d3e6ec7e9772bff42ee7028bde4399390569af730a96fc47649858abe6bb2","source":{"kind":"arxiv","id":"2508.02000","version":1},"attestation_state":"computed","paper":{"title":"Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","eess.AS","eess.IV"],"primary_cat":"cs.SD","authors_text":"Chung-Che Wang, Haibin Wu, Hung-yi Lee, Jiawei Du, Jyh-Shing Roger Jang, Lin Zhang, Shih-Peng Cheng, Xiaoxiao Miao, Xuanjun Chen","submitted_at":"2025-08-04T02:41:09Z","abstract_excerpt":"Audio-visual temporal deepfake localization under the content-driven partial manipulation remains a highly challenging task. In this scenario, the deepfake regions are usually only spanning a few frames, with the majority of the rest remaining identical to the original. To tackle this, we propose a Hierarchical Boundary Modeling Network (HBMNet), which includes three modules: an Audio-Visual Feature Encoder that extracts discriminative frame-level representations, a Coarse Proposal Generator that predicts candidate boundary regions, and a Fine-grained Probabilities Generator that refines these"},"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":"2508.02000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-04T02:41:09Z","cross_cats_sorted":["cs.CV","eess.AS","eess.IV"],"title_canon_sha256":"2ac13397eb3f5932214053c70c5811c1201379541a75c302fdaae04420a9315a","abstract_canon_sha256":"87b97a22d96bf341a5a112aa2e9f29fb6bab2e06aa9205db2e25d17ae6906f93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:49.349469Z","signature_b64":"kBo0YAVlxh6PD3a/u5Q5/iPCCkYEYLZkUd78fP1lO0B58nw702bO3SBPFHqJf5NakCL5mB9jJDtUM6FIVKqWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"787d3e6ec7e9772bff42ee7028bde4399390569af730a96fc47649858abe6bb2","last_reissued_at":"2026-07-05T11:47:49.348973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:49.348973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","eess.AS","eess.IV"],"primary_cat":"cs.SD","authors_text":"Chung-Che Wang, Haibin Wu, Hung-yi Lee, Jiawei Du, Jyh-Shing Roger Jang, Lin Zhang, Shih-Peng Cheng, Xiaoxiao Miao, Xuanjun Chen","submitted_at":"2025-08-04T02:41:09Z","abstract_excerpt":"Audio-visual temporal deepfake localization under the content-driven partial manipulation remains a highly challenging task. In this scenario, the deepfake regions are usually only spanning a few frames, with the majority of the rest remaining identical to the original. To tackle this, we propose a Hierarchical Boundary Modeling Network (HBMNet), which includes three modules: an Audio-Visual Feature Encoder that extracts discriminative frame-level representations, a Coarse Proposal Generator that predicts candidate boundary regions, and a Fine-grained Probabilities Generator that refines these"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02000","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/2508.02000/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":"2508.02000","created_at":"2026-07-05T11:47:49.349025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02000v1","created_at":"2026-07-05T11:47:49.349025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02000","created_at":"2026-07-05T11:47:49.349025+00:00"},{"alias_kind":"pith_short_12","alias_value":"PB6T43WH5F3S","created_at":"2026-07-05T11:47:49.349025+00:00"},{"alias_kind":"pith_short_16","alias_value":"PB6T43WH5F3SX72C","created_at":"2026-07-05T11:47:49.349025+00:00"},{"alias_kind":"pith_short_8","alias_value":"PB6T43WH","created_at":"2026-07-05T11:47:49.349025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04841","citing_title":"Joint Fullband-Subband Modeling for High-Resolution SingFake Detection","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG","json":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG.json","graph_json":"https://pith.science/api/pith-number/PB6T43WH5F3SX72C5ZYCRPPEHG/graph.json","events_json":"https://pith.science/api/pith-number/PB6T43WH5F3SX72C5ZYCRPPEHG/events.json","paper":"https://pith.science/paper/PB6T43WH"},"agent_actions":{"view_html":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG","download_json":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG.json","view_paper":"https://pith.science/paper/PB6T43WH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02000&json=true","fetch_graph":"https://pith.science/api/pith-number/PB6T43WH5F3SX72C5ZYCRPPEHG/graph.json","fetch_events":"https://pith.science/api/pith-number/PB6T43WH5F3SX72C5ZYCRPPEHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG/action/storage_attestation","attest_author":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG/action/author_attestation","sign_citation":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG/action/citation_signature","submit_replication":"https://pith.science/pith/PB6T43WH5F3SX72C5ZYCRPPEHG/action/replication_record"}},"created_at":"2026-07-05T11:47:49.349025+00:00","updated_at":"2026-07-05T11:47:49.349025+00:00"}