{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WG7JIKF6MLTOO54Q5TOJWSZ6E5","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":"3e56cade3d78bd715a1f683b827b190bf7422449dad20464a5c5e8c730d3d9ee","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-21T01:53:31Z","title_canon_sha256":"6d43a2bfc15cd943e62d4b14d63971954877c64f85cb1b8c16f5f835fced5931"},"schema_version":"1.0","source":{"id":"2007.10558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.10558","created_at":"2026-07-05T01:21:31Z"},{"alias_kind":"arxiv_version","alias_value":"2007.10558v1","created_at":"2026-07-05T01:21:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10558","created_at":"2026-07-05T01:21:31Z"},{"alias_kind":"pith_short_12","alias_value":"WG7JIKF6MLTO","created_at":"2026-07-05T01:21:31Z"},{"alias_kind":"pith_short_16","alias_value":"WG7JIKF6MLTOO54Q","created_at":"2026-07-05T01:21:31Z"},{"alias_kind":"pith_short_8","alias_value":"WG7JIKF6","created_at":"2026-07-05T01:21:31Z"}],"graph_snapshots":[{"event_id":"sha256:b9e6e14abb554e705327839dd3fc211eaa7ba2535a30bfb3b5bb9859f57698f1","target":"graph","created_at":"2026-07-05T01:21:31Z","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/2007.10558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a new problem, named audio-visual video parsing, which aims to parse a video into temporal event segments and label them as either audible, visible, or both. Such a problem is essential for a complete understanding of the scene depicted inside a video. To facilitate exploration, we collect a Look, Listen, and Parse (LLP) dataset to investigate audio-visual video parsing in a weakly-supervised manner. This task can be naturally formulated as a Multimodal Multiple Instance Learning (MMIL) problem. Concretely, we propose a novel hybrid attention network to explore unim","authors_text":"Chenliang Xu, Dingzeyu Li, Yapeng Tian","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-21T01:53:31Z","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10558","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:c2c2484046f37d94f077fb65731a75cb44d02e4a5e0355f8cfcf76166e05e7ed","target":"record","created_at":"2026-07-05T01:21:31Z","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":"3e56cade3d78bd715a1f683b827b190bf7422449dad20464a5c5e8c730d3d9ee","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-21T01:53:31Z","title_canon_sha256":"6d43a2bfc15cd943e62d4b14d63971954877c64f85cb1b8c16f5f835fced5931"},"schema_version":"1.0","source":{"id":"2007.10558","kind":"arxiv","version":1}},"canonical_sha256":"b1be9428be62e6e77790ecdc9b4b3e2769b29ae1d184c8ddb3df5e8d2dec04be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1be9428be62e6e77790ecdc9b4b3e2769b29ae1d184c8ddb3df5e8d2dec04be","first_computed_at":"2026-07-05T01:21:31.944721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:21:31.944721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lEPZECWSeUcswrJ5t00nuLX8xzPviDTM37Axnz8CH0qKYMHhDUiyjSqgKIi145UK7/cZ02J8L/N0IDc7KDL4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:21:31.945128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.10558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2c2484046f37d94f077fb65731a75cb44d02e4a5e0355f8cfcf76166e05e7ed","sha256:b9e6e14abb554e705327839dd3fc211eaa7ba2535a30bfb3b5bb9859f57698f1"],"state_sha256":"f595cbdcfcb107658f32d87fed5abc64fb11b20530cc3ffa086bf000a24b4308"}