{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BNVGQSSWAOEBICJLVN4UZ55VRW","short_pith_number":"pith:BNVGQSSW","canonical_record":{"source":{"id":"2409.07967","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T11:54:25Z","cross_cats_sorted":[],"title_canon_sha256":"82af6d227835fc5e0fa96c46a24e641e736012f232ce67ebfc26c95a70be070c","abstract_canon_sha256":"359a250d593970f707854d55f6047a7818b90f602672962f30a471fbdeaf4762"},"schema_version":"1.0"},"canonical_sha256":"0b6a684a56038814092bab794cf7b58d8f494d0c5b407bcb2652fa6435f81c9a","source":{"kind":"arxiv","id":"2409.07967","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07967","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07967v4","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07967","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"pith_short_12","alias_value":"BNVGQSSWAOEB","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"pith_short_16","alias_value":"BNVGQSSWAOEBICJL","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"pith_short_8","alias_value":"BNVGQSSW","created_at":"2026-07-05T11:00:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BNVGQSSWAOEBICJLVN4UZ55VRW","target":"record","payload":{"canonical_record":{"source":{"id":"2409.07967","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T11:54:25Z","cross_cats_sorted":[],"title_canon_sha256":"82af6d227835fc5e0fa96c46a24e641e736012f232ce67ebfc26c95a70be070c","abstract_canon_sha256":"359a250d593970f707854d55f6047a7818b90f602672962f30a471fbdeaf4762"},"schema_version":"1.0"},"canonical_sha256":"0b6a684a56038814092bab794cf7b58d8f494d0c5b407bcb2652fa6435f81c9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:38.942597Z","signature_b64":"M1ABF5lnRnc21eMJqbGzDpAVE6ZVKjRzzYsCUokA6Q36c+tj0kg0dJCNpHIx3Ah9GZnAQUrG7by+ao5++9jPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b6a684a56038814092bab794cf7b58d8f494d0c5b407bcb2652fa6435f81c9a","last_reissued_at":"2026-07-05T11:00:38.941944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:38.941944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.07967","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:00:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gVTGwOCr+/r4QLEDtsd5pDil6ZCH1rDq9mGcDPjGq17rWUM0f6TFn4Yt7JX8jjFkvfAjZr3ONekf3ZE89UJbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:02:01.680233Z"},"content_sha256":"2931e8a4460cd874a53fac0a40d60092e9796a9062f00794b709608f08d94e43","schema_version":"1.0","event_id":"sha256:2931e8a4460cd874a53fac0a40d60092e9796a9062f00794b709608f08d94e43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BNVGQSSWAOEBICJLVN4UZ55VRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Qu, Jinhui Tang, Ling Xing, Rui Yan, Xiangbo Shu","submitted_at":"2024-09-12T11:54:25Z","abstract_excerpt":"Dense-localization Audio-Visual Events (DAVE) aims to identify time boundaries and corresponding categories for events that are both audible and visible in a long video, where events may co-occur and exhibit varying durations. However, complex audio-visual scenes often involve asynchronization between modalities, making accurate localization challenging. Existing DAVE solutions extract audio and visual features through unimodal encoders, and fuse them via dense cross-modal interaction. However, independent unimodal encoding struggles to emphasize shared semantics between modalities without cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07967","kind":"arxiv","version":4},"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/2409.07967/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":"2026-07-05T11:00:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQByIJHhvmlGRJO2M6UWvaATvYf6wYoGa1jgB52o2Ur9a6YGJ7jQR0pFMlehM9/oCbsk60uXZL5hMv/N9HB9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:02:01.680806Z"},"content_sha256":"6b9e6eac9c5e24cc5f9c80dab147a6146942f15cc459cfa9d8efb3579a5a8794","schema_version":"1.0","event_id":"sha256:6b9e6eac9c5e24cc5f9c80dab147a6146942f15cc459cfa9d8efb3579a5a8794"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/bundle.json","state_url":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/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":"2026-08-18T23:02:01Z","links":{"resolver":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW","bundle":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/bundle.json","state":"https://pith.science/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BNVGQSSWAOEBICJLVN4UZ55VRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BNVGQSSWAOEBICJLVN4UZ55VRW","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":"359a250d593970f707854d55f6047a7818b90f602672962f30a471fbdeaf4762","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T11:54:25Z","title_canon_sha256":"82af6d227835fc5e0fa96c46a24e641e736012f232ce67ebfc26c95a70be070c"},"schema_version":"1.0","source":{"id":"2409.07967","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07967","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07967v4","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07967","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"pith_short_12","alias_value":"BNVGQSSWAOEB","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"pith_short_16","alias_value":"BNVGQSSWAOEBICJL","created_at":"2026-07-05T11:00:38Z"},{"alias_kind":"pith_short_8","alias_value":"BNVGQSSW","created_at":"2026-07-05T11:00:38Z"}],"graph_snapshots":[{"event_id":"sha256:6b9e6eac9c5e24cc5f9c80dab147a6146942f15cc459cfa9d8efb3579a5a8794","target":"graph","created_at":"2026-07-05T11:00:38Z","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/2409.07967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense-localization Audio-Visual Events (DAVE) aims to identify time boundaries and corresponding categories for events that are both audible and visible in a long video, where events may co-occur and exhibit varying durations. However, complex audio-visual scenes often involve asynchronization between modalities, making accurate localization challenging. Existing DAVE solutions extract audio and visual features through unimodal encoders, and fuse them via dense cross-modal interaction. However, independent unimodal encoding struggles to emphasize shared semantics between modalities without cro","authors_text":"Hongyu Qu, Jinhui Tang, Ling Xing, Rui Yan, Xiangbo Shu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T11:54:25Z","title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07967","kind":"arxiv","version":4},"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":"sha256:2931e8a4460cd874a53fac0a40d60092e9796a9062f00794b709608f08d94e43","target":"record","created_at":"2026-07-05T11:00:38Z","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":"359a250d593970f707854d55f6047a7818b90f602672962f30a471fbdeaf4762","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T11:54:25Z","title_canon_sha256":"82af6d227835fc5e0fa96c46a24e641e736012f232ce67ebfc26c95a70be070c"},"schema_version":"1.0","source":{"id":"2409.07967","kind":"arxiv","version":4}},"canonical_sha256":"0b6a684a56038814092bab794cf7b58d8f494d0c5b407bcb2652fa6435f81c9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b6a684a56038814092bab794cf7b58d8f494d0c5b407bcb2652fa6435f81c9a","first_computed_at":"2026-07-05T11:00:38.941944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:38.941944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M1ABF5lnRnc21eMJqbGzDpAVE6ZVKjRzzYsCUokA6Q36c+tj0kg0dJCNpHIx3Ah9GZnAQUrG7by+ao5++9jPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:38.942597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07967","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2931e8a4460cd874a53fac0a40d60092e9796a9062f00794b709608f08d94e43","sha256:6b9e6eac9c5e24cc5f9c80dab147a6146942f15cc459cfa9d8efb3579a5a8794"],"state_sha256":"6a3c60b7e61b6f088f8f14a43bd0f233e81699da3709e77b3ba95ecbe85f7ecd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KXGCZjAsUroVkt9AioMsU6m7UTfDA8p8MCodZn/rDJI2JS6xI1tFS7SRmObOnOeocheGxYvD1TbObHDaG8HQBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:02:01.685963Z","bundle_sha256":"d9c2847ce01ff789fed27decc14c7d7f23b2c5f6f3d0c3c8cdc2c4971406234a"}}