{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C775RCOUINU75S3ZZOIWNKV6CC","short_pith_number":"pith:C775RCOU","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"},"canonical_sha256":"17ffd889d44369fecb79cb9166aabe1081da9a5df12d3466cbaf315a9326b34b","source":{"kind":"arxiv","id":"2507.01384","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01384","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01384v2","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01384","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"C775RCOUINU7","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"C775RCOUINU75S3Z","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"C775RCOU","created_at":"2026-07-05T11:52:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C775RCOUINU75S3ZZOIWNKV6CC","target":"record","payload":{"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"},"canonical_sha256":"17ffd889d44369fecb79cb9166aabe1081da9a5df12d3466cbaf315a9326b34b","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"},"source_kind":"arxiv","source_id":"2507.01384","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qkt7BSup9gZmPNCSZUTDAYp2vxv1d13ARqGM4chkwEdDtowoq5eTBpWw/B10HbZrCK1rvEkylNFyKSB293hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:03:58.107640Z"},"content_sha256":"c2de2cfed3bb5e4e3ed95e34becd01abdbbd48ff38893fd870d6f1fcde0c0cd1","schema_version":"1.0","event_id":"sha256:c2de2cfed3bb5e4e3ed95e34becd01abdbbd48ff38893fd870d6f1fcde0c0cd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C775RCOUINU75S3ZZOIWNKV6CC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"reAd+LKWL8/rEKocC9Mily6KmvFfDTNmltY55YXnRA4YO6DzqAA6vsj1Cl3B8ZWUA7uyjbbXDjv+fpx7wxgsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:03:58.108195Z"},"content_sha256":"736b15e97757076f6d6aa8daf2ac3abe978f67ffba029794c945dc8c785188dc","schema_version":"1.0","event_id":"sha256:736b15e97757076f6d6aa8daf2ac3abe978f67ffba029794c945dc8c785188dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/bundle.json","state_url":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C775RCOUINU75S3ZZOIWNKV6CC/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":"2026-08-07T18:03:58Z","links":{"resolver":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC","bundle":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/bundle.json","state":"https://pith.science/pith/C775RCOUINU75S3ZZOIWNKV6CC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C775RCOUINU75S3ZZOIWNKV6CC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C775RCOUINU75S3ZZOIWNKV6CC","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":"9343724040de116612cdf3421dc1e33782c7387d9746ad9d33af39f08bdbf6b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T06:00:49Z","title_canon_sha256":"36815e4a0e2855a0e31d17189cff835d03a38889b4401cbab00b76674f3a1a57"},"schema_version":"1.0","source":{"id":"2507.01384","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01384","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01384v2","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01384","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"C775RCOUINU7","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"C775RCOUINU75S3Z","created_at":"2026-07-05T11:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"C775RCOU","created_at":"2026-07-05T11:52:21Z"}],"graph_snapshots":[{"event_id":"sha256:736b15e97757076f6d6aa8daf2ac3abe978f67ffba029794c945dc8c785188dc","target":"graph","created_at":"2026-07-05T11:52:21Z","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/2507.01384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bingke Zhu, Jinqiao Wang, Langyu Wang, Ming Tang, Yingying Chen, Yiyuan Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T06:00:49Z","title":"MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01384","kind":"arxiv","version":2},"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:c2de2cfed3bb5e4e3ed95e34becd01abdbbd48ff38893fd870d6f1fcde0c0cd1","target":"record","created_at":"2026-07-05T11:52:21Z","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":"9343724040de116612cdf3421dc1e33782c7387d9746ad9d33af39f08bdbf6b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T06:00:49Z","title_canon_sha256":"36815e4a0e2855a0e31d17189cff835d03a38889b4401cbab00b76674f3a1a57"},"schema_version":"1.0","source":{"id":"2507.01384","kind":"arxiv","version":2}},"canonical_sha256":"17ffd889d44369fecb79cb9166aabe1081da9a5df12d3466cbaf315a9326b34b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17ffd889d44369fecb79cb9166aabe1081da9a5df12d3466cbaf315a9326b34b","first_computed_at":"2026-07-05T11:52:21.827839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:21.827839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B6tIk7Bm471F/YDNl/JoDAwOQulgO5n/b2IVt1gE9UTzWH2aEbwezx9Hfsqlsy8LDKBsVaTzuMbEOTeMC9MQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:21.828369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01384","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2de2cfed3bb5e4e3ed95e34becd01abdbbd48ff38893fd870d6f1fcde0c0cd1","sha256:736b15e97757076f6d6aa8daf2ac3abe978f67ffba029794c945dc8c785188dc"],"state_sha256":"cf3dec5954c5b78b2e5d8207339e67c96877d292d2c670a15929f09bd250db50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdPbbgvhZpAVl7K5y6ohOarm91+67Zg4wJp043WopYfFmFprxGzwwkRj4WyL4awFAup0tAIp3Ewrpa1ycljBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:03:58.113553Z","bundle_sha256":"add5265131d157ace21f31f7155afc389c7ed55e6dc06e3ec79979bde1a57a48"}}