{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C775RCOUINU75S3ZZOIWNKV6CC","short_pith_number":"pith:C775RCOU","schema_version":"1.0","canonical_sha256":"17ffd889d44369fecb79cb9166aabe1081da9a5df12d3466cbaf315a9326b34b","source":{"kind":"arxiv","id":"2507.01384","version":2},"attestation_state":"computed","paper":{"title":"MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingke Zhu, Jinqiao Wang, Langyu Wang, Ming Tang, Yingying Chen, Yiyuan Zhang","submitted_at":"2025-07-02T06:00:49Z","abstract_excerpt":"The weakly-supervised audio-visual video parsing (AVVP) aims to predict all modality-specific events and locate their temporal boundaries. Despite significant progress, due to the limitations of the weakly-supervised and the deficiencies of the model architecture, existing methods are lacking in simultaneously improving both the segment-level prediction and the event-level prediction. In this work, we propose a audio-visual Mamba network with pseudo labeling aUGmentation (MUG) for emphasising the uniqueness of each segment and excluding the noise interference from the alternate modalities. Spe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.01384","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T06:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"36815e4a0e2855a0e31d17189cff835d03a38889b4401cbab00b76674f3a1a57","abstract_canon_sha256":"9343724040de116612cdf3421dc1e33782c7387d9746ad9d33af39f08bdbf6b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:21.828369Z","signature_b64":"B6tIk7Bm471F/YDNl/JoDAwOQulgO5n/b2IVt1gE9UTzWH2aEbwezx9Hfsqlsy8LDKBsVaTzuMbEOTeMC9MQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17ffd889d44369fecb79cb9166aabe1081da9a5df12d3466cbaf315a9326b34b","last_reissued_at":"2026-07-05T11:52:21.827839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:21.827839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingke Zhu, Jinqiao Wang, Langyu Wang, Ming Tang, Yingying Chen, Yiyuan Zhang","submitted_at":"2025-07-02T06:00:49Z","abstract_excerpt":"The weakly-supervised audio-visual video parsing (AVVP) aims to predict all modality-specific events and locate their temporal boundaries. Despite significant progress, due to the limitations of the weakly-supervised and the deficiencies of the model architecture, existing methods are lacking in simultaneously improving both the segment-level prediction and the event-level prediction. In this work, we propose a audio-visual Mamba network with pseudo labeling aUGmentation (MUG) for emphasising the uniqueness of each segment and excluding the noise interference from the alternate modalities. Spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01384","kind":"arxiv","version":2},"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/2507.01384/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.01384","created_at":"2026-07-05T11:52:21.827898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01384v2","created_at":"2026-07-05T11:52:21.827898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01384","created_at":"2026-07-05T11:52:21.827898+00:00"},{"alias_kind":"pith_short_12","alias_value":"C775RCOUINU7","created_at":"2026-07-05T11:52:21.827898+00:00"},{"alias_kind":"pith_short_16","alias_value":"C775RCOUINU75S3Z","created_at":"2026-07-05T11:52:21.827898+00:00"},{"alias_kind":"pith_short_8","alias_value":"C775RCOU","created_at":"2026-07-05T11:52:21.827898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08723","citing_title":"EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC","json":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC.json","graph_json":"https://pith.science/api/pith-number/C775RCOUINU75S3ZZOIWNKV6CC/graph.json","events_json":"https://pith.science/api/pith-number/C775RCOUINU75S3ZZOIWNKV6CC/events.json","paper":"https://pith.science/paper/C775RCOU"},"agent_actions":{"view_html":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC","download_json":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC.json","view_paper":"https://pith.science/paper/C775RCOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01384&json=true","fetch_graph":"https://pith.science/api/pith-number/C775RCOUINU75S3ZZOIWNKV6CC/graph.json","fetch_events":"https://pith.science/api/pith-number/C775RCOUINU75S3ZZOIWNKV6CC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/action/storage_attestation","attest_author":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/action/author_attestation","sign_citation":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/action/citation_signature","submit_replication":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/action/replication_record"}},"created_at":"2026-07-05T11:52:21.827898+00:00","updated_at":"2026-07-05T11:52:21.827898+00:00"}