{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WDDIOEN52QETRVOLWJZC3RWNDW","short_pith_number":"pith:WDDIOEN5","schema_version":"1.0","canonical_sha256":"b0c68711bdd40938d5cbb2722dc6cd1d93babe5fb4037d712eb42df5f3fa2285","source":{"kind":"arxiv","id":"2507.22781","version":1},"attestation_state":"computed","paper":{"title":"HOLA: Enhancing Audio-visual Deepfake Detection via Hierarchical Contextual Aggregations and Efficient Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danlei Huang, Fei Wang, Hao Wang, Heli Sun, Jia Zhang, Junxiao Xue, Liang He, Peihao Guo, Suyu Xing, Xinyi Yin, Xuecheng Wu, Yifan Wang","submitted_at":"2025-07-30T15:47:12Z","abstract_excerpt":"Advances in Generative AI have made video-level deepfake detection increasingly challenging, exposing the limitations of current detection techniques. In this paper, we present HOLA, our solution to the Video-Level Deepfake Detection track of 2025 1M-Deepfakes Detection Challenge. Inspired by the success of large-scale pre-training in the general domain, we first scale audio-visual self-supervised pre-training in the multimodal video-level deepfake detection, which leverages our self-built dataset of 1.81M samples, thereby leading to a unified two-stage framework. To be specific, HOLA features"},"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":"2507.22781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T15:47:12Z","cross_cats_sorted":[],"title_canon_sha256":"40e8ac457e5a576caf1b03d945dd76d0dcf5b459649b62d9715001c645c2a4bd","abstract_canon_sha256":"1527f57bc4389bd3e819caa394cfbdb4105df91a5b4a19d88978b0dfe336ccb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:49.106209Z","signature_b64":"32462LWZGj+pZeMJKdVlvIO3VOJyc5mv+ajIU1vWaGfoQ1JbnJwFrobcuLmyGuOxNPbu/g0QlUONoTj3BqKwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c68711bdd40938d5cbb2722dc6cd1d93babe5fb4037d712eb42df5f3fa2285","last_reissued_at":"2026-07-05T11:45:49.105715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:49.105715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOLA: Enhancing Audio-visual Deepfake Detection via Hierarchical Contextual Aggregations and Efficient Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danlei Huang, Fei Wang, Hao Wang, Heli Sun, Jia Zhang, Junxiao Xue, Liang He, Peihao Guo, Suyu Xing, Xinyi Yin, Xuecheng Wu, Yifan Wang","submitted_at":"2025-07-30T15:47:12Z","abstract_excerpt":"Advances in Generative AI have made video-level deepfake detection increasingly challenging, exposing the limitations of current detection techniques. In this paper, we present HOLA, our solution to the Video-Level Deepfake Detection track of 2025 1M-Deepfakes Detection Challenge. Inspired by the success of large-scale pre-training in the general domain, we first scale audio-visual self-supervised pre-training in the multimodal video-level deepfake detection, which leverages our self-built dataset of 1.81M samples, thereby leading to a unified two-stage framework. To be specific, HOLA features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22781","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/2507.22781/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":"2507.22781","created_at":"2026-07-05T11:45:49.105778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22781v1","created_at":"2026-07-05T11:45:49.105778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22781","created_at":"2026-07-05T11:45:49.105778+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDDIOEN52QET","created_at":"2026-07-05T11:45:49.105778+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDDIOEN52QETRVOL","created_at":"2026-07-05T11:45:49.105778+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDDIOEN5","created_at":"2026-07-05T11:45:49.105778+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/WDDIOEN52QETRVOLWJZC3RWNDW","json":"https://pith.science/pith/WDDIOEN52QETRVOLWJZC3RWNDW.json","graph_json":"https://pith.science/api/pith-number/WDDIOEN52QETRVOLWJZC3RWNDW/graph.json","events_json":"https://pith.science/api/pith-number/WDDIOEN52QETRVOLWJZC3RWNDW/events.json","paper":"https://pith.science/paper/WDDIOEN5"},"agent_actions":{"view_html":"https://pith.science/pith/WDDIOEN52QETRVOLWJZC3RWNDW","download_json":"https://pith.science/pith/WDDIOEN52QETRVOLWJZC3RWNDW.json","view_paper":"https://pith.science/paper/WDDIOEN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22781&json=true","fetch_graph":"https://pith.science/api/pith-number/WDDIOEN52QETRVOLWJZC3RWNDW/graph.json","fetch_events":"https://pith.science/api/pith-number/WDDIOEN52QETRVOLWJZC3RWNDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDDIOEN52QETRVOLWJZC3RWNDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDDIOEN52QETRVOLWJZC3RWNDW/action/storage_attestation","attest_author":"https://pith.science/pith/WDDIOEN52QETRVOLWJZC3RWNDW/action/author_attestation","sign_citation":"https://pith.science/pith/WDDIOEN52QETRVOLWJZC3RWNDW/action/citation_signature","submit_replication":"https://pith.science/pith/WDDIOEN52QETRVOLWJZC3RWNDW/action/replication_record"}},"created_at":"2026-07-05T11:45:49.105778+00:00","updated_at":"2026-07-05T11:45:49.105778+00:00"}