{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MBCLR3RFO4HOOG6CARTMBAP4EZ","short_pith_number":"pith:MBCLR3RF","schema_version":"1.0","canonical_sha256":"6044b8ee25770ee71bc20466c081fc267450ea6cd27fd58b546668779b808557","source":{"kind":"arxiv","id":"2401.16423","version":1},"attestation_state":"computed","paper":{"title":"Synchformer: Efficient Synchronization from Sparse Cues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Esa Rahtu, Vladimir Iashin, Weidi Xie","submitted_at":"2024-01-29T18:59:55Z","abstract_excerpt":"Our objective is audio-visual synchronization with a focus on 'in-the-wild' videos, such as those on YouTube, where synchronization cues can be sparse. Our contributions include a novel audio-visual synchronization model, and training that decouples feature extraction from synchronization modelling through multi-modal segment-level contrastive pre-training. This approach achieves state-of-the-art performance in both dense and sparse settings. We also extend synchronization model training to AudioSet a million-scale 'in-the-wild' dataset, investigate evidence attribution techniques for interpre"},"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":"2401.16423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T18:59:55Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"00e89b7793bd657840020aef35e690c62f0f98a70bb2764f465d3ebc15e6a7f1","abstract_canon_sha256":"100b67408497c7b4fb790c1993f1d0872bea736c08f56e05e503e23db276d91f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:48.894122Z","signature_b64":"bYdo4ZNKDs++p8I41j36tCDGUwNVZBoI6G/h6yYmyqaaXt9535wNM+PUKCb86QnCpVECp6Wb9xCsA5z5lu6vDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6044b8ee25770ee71bc20466c081fc267450ea6cd27fd58b546668779b808557","last_reissued_at":"2026-07-05T07:38:48.893697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:48.893697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synchformer: Efficient Synchronization from Sparse Cues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Esa Rahtu, Vladimir Iashin, Weidi Xie","submitted_at":"2024-01-29T18:59:55Z","abstract_excerpt":"Our objective is audio-visual synchronization with a focus on 'in-the-wild' videos, such as those on YouTube, where synchronization cues can be sparse. Our contributions include a novel audio-visual synchronization model, and training that decouples feature extraction from synchronization modelling through multi-modal segment-level contrastive pre-training. This approach achieves state-of-the-art performance in both dense and sparse settings. We also extend synchronization model training to AudioSet a million-scale 'in-the-wild' dataset, investigate evidence attribution techniques for interpre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16423","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/2401.16423/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":"2401.16423","created_at":"2026-07-05T07:38:48.893757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16423v1","created_at":"2026-07-05T07:38:48.893757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16423","created_at":"2026-07-05T07:38:48.893757+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBCLR3RFO4HO","created_at":"2026-07-05T07:38:48.893757+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBCLR3RFO4HOOG6C","created_at":"2026-07-05T07:38:48.893757+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBCLR3RF","created_at":"2026-07-05T07:38:48.893757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.01929","citing_title":"Woosh: A Sound Effects Foundation Model","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ","json":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ.json","graph_json":"https://pith.science/api/pith-number/MBCLR3RFO4HOOG6CARTMBAP4EZ/graph.json","events_json":"https://pith.science/api/pith-number/MBCLR3RFO4HOOG6CARTMBAP4EZ/events.json","paper":"https://pith.science/paper/MBCLR3RF"},"agent_actions":{"view_html":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ","download_json":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ.json","view_paper":"https://pith.science/paper/MBCLR3RF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16423&json=true","fetch_graph":"https://pith.science/api/pith-number/MBCLR3RFO4HOOG6CARTMBAP4EZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MBCLR3RFO4HOOG6CARTMBAP4EZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ/action/storage_attestation","attest_author":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ/action/author_attestation","sign_citation":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ/action/citation_signature","submit_replication":"https://pith.science/pith/MBCLR3RFO4HOOG6CARTMBAP4EZ/action/replication_record"}},"created_at":"2026-07-05T07:38:48.893757+00:00","updated_at":"2026-07-05T07:38:48.893757+00:00"}