{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5ZGFS6OPONAAUPVX5CIKXNQJX5","short_pith_number":"pith:5ZGFS6OP","schema_version":"1.0","canonical_sha256":"ee4c5979cf73400a3eb7e890abb609bf5978912d8ac7abd80bbcabfa90178cc9","source":{"kind":"arxiv","id":"2608.01310","version":1},"attestation_state":"computed","paper":{"title":"FATE: Frame-Level Audio-Visual Temporal Embedding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Bingzi Zhang, Kaisi Guan, Ruihua Song, Xihua Wang, Xin Cheng, Yijing Chen, Ying Ba","submitted_at":"2026-08-02T15:26:21Z","abstract_excerpt":"When a dog opens its mouth and barks, humans naturally recognize what the sound is and when it occurs. Building audio-visual models with this same ability requires representations that capture both semantic and temporal alignment. Current approaches fall short on one side or the other: embedding models match semantic but lose temporal information; synchronization models capture temporal offsets but lack semantic understanding. To bridge this gap, we propose FATE, Frame-level Audio-visual Temporal Embedding. Unlike prior embedding models that pool each modality into a single embedding and disca"},"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":"2608.01310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-02T15:26:21Z","cross_cats_sorted":[],"title_canon_sha256":"fec8be547fe71276830d62227f285cc3c6ce17ad007a8d2244743a9d7d30dbbc","abstract_canon_sha256":"c138f7336cb2cf93ec87e65b3fb1ca60a2f7e63024fbfb8a12d0efe3273f7dbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:03:44.555114Z","signature_b64":"0JsukufNRdLn89dgslsQm6C1ZkiLz8Sgw6CkaTPlioywGIDjWP3qQ8BUBRysNCyt+xn/Ws+P5QUXNz836yfVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee4c5979cf73400a3eb7e890abb609bf5978912d8ac7abd80bbcabfa90178cc9","last_reissued_at":"2026-08-04T02:03:44.553277Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:03:44.553277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FATE: Frame-Level Audio-Visual Temporal Embedding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Bingzi Zhang, Kaisi Guan, Ruihua Song, Xihua Wang, Xin Cheng, Yijing Chen, Ying Ba","submitted_at":"2026-08-02T15:26:21Z","abstract_excerpt":"When a dog opens its mouth and barks, humans naturally recognize what the sound is and when it occurs. Building audio-visual models with this same ability requires representations that capture both semantic and temporal alignment. Current approaches fall short on one side or the other: embedding models match semantic but lose temporal information; synchronization models capture temporal offsets but lack semantic understanding. To bridge this gap, we propose FATE, Frame-level Audio-visual Temporal Embedding. Unlike prior embedding models that pool each modality into a single embedding and disca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01310","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/2608.01310/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":"2608.01310","created_at":"2026-08-04T02:03:44.554725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01310v1","created_at":"2026-08-04T02:03:44.554725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01310","created_at":"2026-08-04T02:03:44.554725+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZGFS6OPONAA","created_at":"2026-08-04T02:03:44.554725+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZGFS6OPONAAUPVX","created_at":"2026-08-04T02:03:44.554725+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZGFS6OP","created_at":"2026-08-04T02:03:44.554725+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/5ZGFS6OPONAAUPVX5CIKXNQJX5","json":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5.json","graph_json":"https://pith.science/api/pith-number/5ZGFS6OPONAAUPVX5CIKXNQJX5/graph.json","events_json":"https://pith.science/api/pith-number/5ZGFS6OPONAAUPVX5CIKXNQJX5/events.json","paper":"https://pith.science/paper/5ZGFS6OP"},"agent_actions":{"view_html":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5","download_json":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5.json","view_paper":"https://pith.science/paper/5ZGFS6OP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01310&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZGFS6OPONAAUPVX5CIKXNQJX5/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZGFS6OPONAAUPVX5CIKXNQJX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/action/storage_attestation","attest_author":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/action/author_attestation","sign_citation":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/action/citation_signature","submit_replication":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/action/replication_record"}},"created_at":"2026-08-04T02:03:44.554725+00:00","updated_at":"2026-08-04T02:03:44.554725+00:00"}