{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P2KDEXLJJF3JA5JGDZV444VZJJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"78922933d62818e516117d735052783dbadd167e9ed209dc012d2428aa1eaee5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-13T07:41:15Z","title_canon_sha256":"e58a7655474c24351b9e634eafa07961699c5a77d69b5fa973d341d28aca2ebb"},"schema_version":"1.0","source":{"id":"2106.06939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06939","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06939v1","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06939","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"P2KDEXLJJF3J","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_16","alias_value":"P2KDEXLJJF3JA5JG","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_8","alias_value":"P2KDEXLJ","created_at":"2026-07-05T02:48:42Z"}],"graph_snapshots":[{"event_id":"sha256:41043378e6228d57e22247e6f0de8e3cc51f1a2ef0d0d61060cf847eb0a2fc4f","target":"graph","created_at":"2026-07-05T02:48:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.06939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal correlation provides an inherent supervision for video unsupervised representation learning. Existing methods focus on distinguishing different video clips by visual and audio representations. We human visual perception could attend to regions where sounds are made, and our auditory perception could also ground their frequencies of sounding objects, which we call bidirectional local correspondence. Such supervision is intuitive but not well explored in the contrastive learning framework. This paper introduces a pretext task, Cross-Modal Attention Consistency (CMAC), for exploring t","authors_text":"Chuang Gan, Hongtao Xie, Jingdong Wang, Qi Dai, Shaobo Min, Yongdong Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-13T07:41:15Z","title":"Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06939","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b101d191f6028685483cbe6c3ffc436ac8bacf2ef9644a5fffb57b453e671c04","target":"record","created_at":"2026-07-05T02:48:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"78922933d62818e516117d735052783dbadd167e9ed209dc012d2428aa1eaee5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-13T07:41:15Z","title_canon_sha256":"e58a7655474c24351b9e634eafa07961699c5a77d69b5fa973d341d28aca2ebb"},"schema_version":"1.0","source":{"id":"2106.06939","kind":"arxiv","version":1}},"canonical_sha256":"7e94325d6949769075261e6bce72b94a522c8b87b028fb50afaaecbfa2878d70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e94325d6949769075261e6bce72b94a522c8b87b028fb50afaaecbfa2878d70","first_computed_at":"2026-07-05T02:48:42.745361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:42.745361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P9XA0nmhOcomJXhKu68Sd9iSz8z4dVJYUaLmz1Wprc83xuiADuly6voOjOr5FgJ16WIq7ptTQpQM7d9wF2BwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:42.745744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b101d191f6028685483cbe6c3ffc436ac8bacf2ef9644a5fffb57b453e671c04","sha256:41043378e6228d57e22247e6f0de8e3cc51f1a2ef0d0d61060cf847eb0a2fc4f"],"state_sha256":"050010588f60947809f4b58e67bbb6aa683093fc44e2c7faa0f2aff451d4f9e4"}