{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KIR46Y2YQFYID5HQ3B6HDPQY2R","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":"bc47ff1ab4dd92cd547029886d42b449d080473542846bc62717b88d386c287b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T10:05:56Z","title_canon_sha256":"252076a239518789c8132c73b2f9c91cb706c578845a19004accf5971467e10b"},"schema_version":"1.0","source":{"id":"2412.19563","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19563","created_at":"2026-07-05T09:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19563v1","created_at":"2026-07-05T09:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19563","created_at":"2026-07-05T09:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"KIR46Y2YQFYI","created_at":"2026-07-05T09:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"KIR46Y2YQFYID5HQ","created_at":"2026-07-05T09:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"KIR46Y2Y","created_at":"2026-07-05T09:54:38Z"}],"graph_snapshots":[{"event_id":"sha256:cc61202f9aafd3bcd53107a33ce0f787c6854f524799f28411e2f6de7e74643d","target":"graph","created_at":"2026-07-05T09:54:38Z","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/2412.19563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual video parsing (AVVP) aims to recognize audio and visual event labels with precise temporal boundaries, which is quite challenging since audio or visual modality might include only one event label with only the overall video labels available. Existing label denoising models often treat the denoising process as a separate preprocessing step, leading to a disconnect between label denoising and AVVP tasks. To bridge this gap, we present a novel joint reinforcement learning-based label denoising approach (RLLD). This approach enables simultaneous training of both label denoising and vi","authors_text":"Deng Yu, Guohua Lv, Sijiu Niu, Xiangcheng Sun, Yongbiao Gao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T10:05:56Z","title":"Reinforced Label Denoising for Weakly-Supervised Audio-Visual Video Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19563","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:bf3f968a582ec4f7fc7a53b66f1e320a8646534cdf23bfc6a8aebff3bd333f86","target":"record","created_at":"2026-07-05T09:54:38Z","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":"bc47ff1ab4dd92cd547029886d42b449d080473542846bc62717b88d386c287b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T10:05:56Z","title_canon_sha256":"252076a239518789c8132c73b2f9c91cb706c578845a19004accf5971467e10b"},"schema_version":"1.0","source":{"id":"2412.19563","kind":"arxiv","version":1}},"canonical_sha256":"5223cf6358817081f4f0d87c71be18d468ea48fa4c9eda8d82d9d2967a799617","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5223cf6358817081f4f0d87c71be18d468ea48fa4c9eda8d82d9d2967a799617","first_computed_at":"2026-07-05T09:54:38.015684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:38.015684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"73+A0hWQzT4rqDEnDPKUwQh3DT8reeR0Yp9zag6/KKnqgoBFLiYsl/nJCrTuy4orEX4WdAQp70vyhRqjXnGbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:38.016297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19563","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf3f968a582ec4f7fc7a53b66f1e320a8646534cdf23bfc6a8aebff3bd333f86","sha256:cc61202f9aafd3bcd53107a33ce0f787c6854f524799f28411e2f6de7e74643d"],"state_sha256":"5ce727d015746db0d1470f70c122d13d6c515a9b57ad96dfe3f4b1943fec6411"}