{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G6FBVRQCBJFZB4P5DYEVQAE3F7","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":"7d92b4f68439417cbd92b5112069875bbfede1b750d7bfab69de2c81196c9c95","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-04T07:48:12Z","title_canon_sha256":"6ebc52615d8d55d1e26f4ba161045510b7a4eaeb2d9dae3f6c481701e7d423a1"},"schema_version":"1.0","source":{"id":"2408.01952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01952","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01952v1","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01952","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_12","alias_value":"G6FBVRQCBJFZ","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_16","alias_value":"G6FBVRQCBJFZB4P5","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_8","alias_value":"G6FBVRQC","created_at":"2026-07-05T08:52:05Z"}],"graph_snapshots":[{"event_id":"sha256:97b7237e299fe42d007b81a28048527e246beaac0df68bffe066fa4aa39edcca","target":"graph","created_at":"2026-07-05T08:52:05Z","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/2408.01952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The audio-visual event localization task requires identifying concurrent visual and auditory events from unconstrained videos within a network model, locating them, and classifying their category. The efficient extraction and integration of audio and visual modal information have always been challenging in this field. In this paper, we introduce CACE-Net, which differs from most existing methods that solely use audio signals to guide visual information. We propose an audio-visual co-guidance attention mechanism that allows for adaptive bi-directional cross-modal attentional guidance between au","authors_text":"Dongcheng Zhao, Guobin Shen, Qingqun Kong, Xiang He, Xiangxi Liu, Xin Yang, Yang Li, Yi Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-04T07:48:12Z","title":"CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01952","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:c8564105408ed889f6282cf165df59a2464bbc38f90f6b7e59fa79f04548ccc2","target":"record","created_at":"2026-07-05T08:52:05Z","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":"7d92b4f68439417cbd92b5112069875bbfede1b750d7bfab69de2c81196c9c95","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-04T07:48:12Z","title_canon_sha256":"6ebc52615d8d55d1e26f4ba161045510b7a4eaeb2d9dae3f6c481701e7d423a1"},"schema_version":"1.0","source":{"id":"2408.01952","kind":"arxiv","version":1}},"canonical_sha256":"378a1ac6020a4b90f1fd1e0958009b2fe426bbefa49421412b686d73661ed3c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"378a1ac6020a4b90f1fd1e0958009b2fe426bbefa49421412b686d73661ed3c9","first_computed_at":"2026-07-05T08:52:05.468663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:05.468663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BDvRwzYCJcmc+3SnL43q+lP96sgtQc3TDHgEHyIOU4T9vTp/m1dCGDUaEweLG4XgctOIjEJoUzodyRblul20Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:05.469053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8564105408ed889f6282cf165df59a2464bbc38f90f6b7e59fa79f04548ccc2","sha256:97b7237e299fe42d007b81a28048527e246beaac0df68bffe066fa4aa39edcca"],"state_sha256":"16df9456b50bb2547b6f44dd7224f0b7941e72ea958b46eed7f32bf4e86e1840"}