{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5ZGFS6OPONAAUPVX5CIKXNQJX5","short_pith_number":"pith:5ZGFS6OP","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"},"canonical_sha256":"ee4c5979cf73400a3eb7e890abb609bf5978912d8ac7abd80bbcabfa90178cc9","source":{"kind":"arxiv","id":"2608.01310","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01310","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01310v1","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01310","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"5ZGFS6OPONAA","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"5ZGFS6OPONAAUPVX","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"5ZGFS6OP","created_at":"2026-08-04T02:03:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5ZGFS6OPONAAUPVX5CIKXNQJX5","target":"record","payload":{"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"},"canonical_sha256":"ee4c5979cf73400a3eb7e890abb609bf5978912d8ac7abd80bbcabfa90178cc9","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"},"source_kind":"arxiv","source_id":"2608.01310","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":"2026-08-04T02:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3BPdksDI++2J4oltapYybGVGft0TPC+fUlMnHDSH4nJ5lSMSYjijrxUIwuOd7wvHwXAKuEfHRKbOfgD1UM8bAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:08:15.020667Z"},"content_sha256":"72f9b7951515577f956676cc88ca998a17eb8d4354f121479ba30a00428d876e","schema_version":"1.0","event_id":"sha256:72f9b7951515577f956676cc88ca998a17eb8d4354f121479ba30a00428d876e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5ZGFS6OPONAAUPVX5CIKXNQJX5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T02:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5xgex/TgFy8PWRlnEcE3pRoQbFwfB+iD56PkOGbt53K0qT31KOoFst/JGjWJGg3U/B4iA1yPryytWBZHv3AyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:08:15.021504Z"},"content_sha256":"9fea528b99d090f2837bb286e87f734f6cbbc38f52e645370c41cf510c7784ad","schema_version":"1.0","event_id":"sha256:9fea528b99d090f2837bb286e87f734f6cbbc38f52e645370c41cf510c7784ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/bundle.json","state_url":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/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":"2026-08-19T10:08:15Z","links":{"resolver":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5","bundle":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/bundle.json","state":"https://pith.science/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ZGFS6OPONAAUPVX5CIKXNQJX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5ZGFS6OPONAAUPVX5CIKXNQJX5","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":"c138f7336cb2cf93ec87e65b3fb1ca60a2f7e63024fbfb8a12d0efe3273f7dbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-02T15:26:21Z","title_canon_sha256":"fec8be547fe71276830d62227f285cc3c6ce17ad007a8d2244743a9d7d30dbbc"},"schema_version":"1.0","source":{"id":"2608.01310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01310","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01310v1","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01310","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"5ZGFS6OPONAA","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"5ZGFS6OPONAAUPVX","created_at":"2026-08-04T02:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"5ZGFS6OP","created_at":"2026-08-04T02:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:9fea528b99d090f2837bb286e87f734f6cbbc38f52e645370c41cf510c7784ad","target":"graph","created_at":"2026-08-04T02:03:44Z","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/2608.01310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bingzi Zhang, Kaisi Guan, Ruihua Song, Xihua Wang, Xin Cheng, Yijing Chen, Ying Ba","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-02T15:26:21Z","title":"FATE: Frame-Level Audio-Visual Temporal Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01310","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":"sha256:72f9b7951515577f956676cc88ca998a17eb8d4354f121479ba30a00428d876e","target":"record","created_at":"2026-08-04T02:03:44Z","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":"c138f7336cb2cf93ec87e65b3fb1ca60a2f7e63024fbfb8a12d0efe3273f7dbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-02T15:26:21Z","title_canon_sha256":"fec8be547fe71276830d62227f285cc3c6ce17ad007a8d2244743a9d7d30dbbc"},"schema_version":"1.0","source":{"id":"2608.01310","kind":"arxiv","version":1}},"canonical_sha256":"ee4c5979cf73400a3eb7e890abb609bf5978912d8ac7abd80bbcabfa90178cc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee4c5979cf73400a3eb7e890abb609bf5978912d8ac7abd80bbcabfa90178cc9","first_computed_at":"2026-08-04T02:03:44.553277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:03:44.553277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JsukufNRdLn89dgslsQm6C1ZkiLz8Sgw6CkaTPlioywGIDjWP3qQ8BUBRysNCyt+xn/Ws+P5QUXNz836yfVAA==","signature_status":"signed_v1","signed_at":"2026-08-04T02:03:44.555114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72f9b7951515577f956676cc88ca998a17eb8d4354f121479ba30a00428d876e","sha256:9fea528b99d090f2837bb286e87f734f6cbbc38f52e645370c41cf510c7784ad"],"state_sha256":"9510d2f8bb9340b46cc8b0f3b2dbe811606734f3f8d293909171d32b8e3012a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wAFojGeJ2EvoKNa5USjk8WzOsOGsXqtg/eYA6CQ58eNOwOxgMwsxnPTC9G4TtP6j6yba6JpKJBoni2o3LfnGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:08:15.026943Z","bundle_sha256":"41145708e8ff968c13f7f5ad1de6af73ea46e96cf6c868ae5f07301f00b6af51"}}