{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2YTEMFTT56KY5WH7JJ2RXKIFPN","short_pith_number":"pith:2YTEMFTT","canonical_record":{"source":{"id":"2008.05789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2020-08-13T10:08:12Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"c81f674f56bcf105f0d62ab49b78178c039fda7b15ac4453729306940138561a","abstract_canon_sha256":"50cd1e2babcb3b0143507cf845aea217c58cdee0f6f3d1933c73470cb45638ce"},"schema_version":"1.0"},"canonical_sha256":"d626461673ef958ed8ff4a751ba9057b62cd6f958cdf74a612a6ce8614bb3a90","source":{"kind":"arxiv","id":"2008.05789","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.05789","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"arxiv_version","alias_value":"2008.05789v1","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05789","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"pith_short_12","alias_value":"2YTEMFTT56KY","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"pith_short_16","alias_value":"2YTEMFTT56KY5WH7","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"pith_short_8","alias_value":"2YTEMFTT","created_at":"2026-07-05T01:27:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2YTEMFTT56KY5WH7JJ2RXKIFPN","target":"record","payload":{"canonical_record":{"source":{"id":"2008.05789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2020-08-13T10:08:12Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"c81f674f56bcf105f0d62ab49b78178c039fda7b15ac4453729306940138561a","abstract_canon_sha256":"50cd1e2babcb3b0143507cf845aea217c58cdee0f6f3d1933c73470cb45638ce"},"schema_version":"1.0"},"canonical_sha256":"d626461673ef958ed8ff4a751ba9057b62cd6f958cdf74a612a6ce8614bb3a90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:49.249391Z","signature_b64":"xcEO86JVYmfvurB0Ik0LOoCeAQ8nazTPCrlQSZi0vi0o+TAJCpWoDo5KSdB8TZLo1S9MJUhVgK2lBGRxJ40IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d626461673ef958ed8ff4a751ba9057b62cd6f958cdf74a612a6ce8614bb3a90","last_reissued_at":"2026-07-05T01:27:49.248999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:49.248999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.05789","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:27:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmpKi7rWgM5vqpi5YtDUUmJWjRpXi8NqlKEDXVxAK4afg1vEfab9I8p92TwINLQnzMYxhWhCADhdstpoTlaGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:17:23.341097Z"},"content_sha256":"473d83310668856f991708f780320c9bd19495a572aec46eb831587020f6f52c","schema_version":"1.0","event_id":"sha256:473d83310668856f991708f780320c9bd19495a572aec46eb831587020f6f52c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2YTEMFTT56KY5WH7JJ2RXKIFPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.MM","authors_text":"Rui Feng, Ruize Wang, Ying Cheng, Yuejie Zhang, Zhihao Pan","submitted_at":"2020-08-13T10:08:12Z","abstract_excerpt":"When watching videos, the occurrence of a visual event is often accompanied by an audio event, e.g., the voice of lip motion, the music of playing instruments. There is an underlying correlation between audio and visual events, which can be utilized as free supervised information to train a neural network by solving the pretext task of audio-visual synchronization. In this paper, we propose a novel self-supervised framework with co-attention mechanism to learn generic cross-modal representations from unlabelled videos in the wild, and further benefit downstream tasks. Specifically, we explore "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05789","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/2008.05789/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:27:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cC3Mu57tzDeobIP+YVFo+Eu4GUhv8BIJbGZeiHyBYxH3bgwEfMPvkA6T2bl/JXRHP6NmD/bAaPKQPPb1ZNRCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:17:23.341492Z"},"content_sha256":"db93528b4215d529be593e438cabceac3e2f8bcf14f0f067157f0b3f001de233","schema_version":"1.0","event_id":"sha256:db93528b4215d529be593e438cabceac3e2f8bcf14f0f067157f0b3f001de233"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YTEMFTT56KY5WH7JJ2RXKIFPN/bundle.json","state_url":"https://pith.science/pith/2YTEMFTT56KY5WH7JJ2RXKIFPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YTEMFTT56KY5WH7JJ2RXKIFPN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T01:17:23Z","links":{"resolver":"https://pith.science/pith/2YTEMFTT56KY5WH7JJ2RXKIFPN","bundle":"https://pith.science/pith/2YTEMFTT56KY5WH7JJ2RXKIFPN/bundle.json","state":"https://pith.science/pith/2YTEMFTT56KY5WH7JJ2RXKIFPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YTEMFTT56KY5WH7JJ2RXKIFPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2YTEMFTT56KY5WH7JJ2RXKIFPN","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":"50cd1e2babcb3b0143507cf845aea217c58cdee0f6f3d1933c73470cb45638ce","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2020-08-13T10:08:12Z","title_canon_sha256":"c81f674f56bcf105f0d62ab49b78178c039fda7b15ac4453729306940138561a"},"schema_version":"1.0","source":{"id":"2008.05789","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.05789","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"arxiv_version","alias_value":"2008.05789v1","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05789","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"pith_short_12","alias_value":"2YTEMFTT56KY","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"pith_short_16","alias_value":"2YTEMFTT56KY5WH7","created_at":"2026-07-05T01:27:49Z"},{"alias_kind":"pith_short_8","alias_value":"2YTEMFTT","created_at":"2026-07-05T01:27:49Z"}],"graph_snapshots":[{"event_id":"sha256:db93528b4215d529be593e438cabceac3e2f8bcf14f0f067157f0b3f001de233","target":"graph","created_at":"2026-07-05T01:27:49Z","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/2008.05789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When watching videos, the occurrence of a visual event is often accompanied by an audio event, e.g., the voice of lip motion, the music of playing instruments. There is an underlying correlation between audio and visual events, which can be utilized as free supervised information to train a neural network by solving the pretext task of audio-visual synchronization. In this paper, we propose a novel self-supervised framework with co-attention mechanism to learn generic cross-modal representations from unlabelled videos in the wild, and further benefit downstream tasks. Specifically, we explore ","authors_text":"Rui Feng, Ruize Wang, Ying Cheng, Yuejie Zhang, Zhihao Pan","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2020-08-13T10:08:12Z","title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05789","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":"sha256:473d83310668856f991708f780320c9bd19495a572aec46eb831587020f6f52c","target":"record","created_at":"2026-07-05T01:27:49Z","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":"50cd1e2babcb3b0143507cf845aea217c58cdee0f6f3d1933c73470cb45638ce","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2020-08-13T10:08:12Z","title_canon_sha256":"c81f674f56bcf105f0d62ab49b78178c039fda7b15ac4453729306940138561a"},"schema_version":"1.0","source":{"id":"2008.05789","kind":"arxiv","version":1}},"canonical_sha256":"d626461673ef958ed8ff4a751ba9057b62cd6f958cdf74a612a6ce8614bb3a90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d626461673ef958ed8ff4a751ba9057b62cd6f958cdf74a612a6ce8614bb3a90","first_computed_at":"2026-07-05T01:27:49.248999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:49.248999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xcEO86JVYmfvurB0Ik0LOoCeAQ8nazTPCrlQSZi0vi0o+TAJCpWoDo5KSdB8TZLo1S9MJUhVgK2lBGRxJ40IBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:49.249391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.05789","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:473d83310668856f991708f780320c9bd19495a572aec46eb831587020f6f52c","sha256:db93528b4215d529be593e438cabceac3e2f8bcf14f0f067157f0b3f001de233"],"state_sha256":"44abc70e493fa1dcd92f7c38a1c73ed6ef866ff6d392197f85d21ee74d4ca0d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o9jiu8PDbd883jtuCZqzOixPkSZ+5oq1rSYIq76JfHGFGIQrK4+5sKiZz2gsOYWqjhqHevn31e6fcKTqoy7SCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T01:17:23.343696Z","bundle_sha256":"a8e1cd77bdb10a3c3f4162ac590a90d8a51efc7214e77edbc66c5d7bff7c4a3f"}}