{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7PKY5GDHK5T5ZHS4YGIPZTQTYC","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":"75af4279639e34080b15f806013acb8ad1b539b2e819b2b75a06315c3cb23e38","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T09:55:09Z","title_canon_sha256":"d3f82789a074e9f0255b240bcc711ad6b6be5a0a010a6e93fe19c505175249d7"},"schema_version":"1.0","source":{"id":"2412.08247","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08247","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08247v2","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08247","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"7PKY5GDHK5T5","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_16","alias_value":"7PKY5GDHK5T5ZHS4","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_8","alias_value":"7PKY5GDH","created_at":"2026-07-05T10:41:51Z"}],"graph_snapshots":[{"event_id":"sha256:b028f6658febe573d86daef5a5334ae2f0e467b04308232ceb94d303d27c0a66","target":"graph","created_at":"2026-07-05T10:41:51Z","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/2412.08247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues. In real-world scenarios, visual cues are not always available due to various impairments, which undermines the stability of AV-TSE. Despite this challenge, humans can maintain attentional momentum over time, even when the target speaker is not visible. In this paper, we introduce the Momentum Multi-modal target Speaker Extraction (MoMuSE), which retains a speaker identity momentum in memory, enabling the model to continuously track t","authors_text":"Haizhou Li, Junjie Li, Ke Zhang, Kong Aik Lee, Man-Wai Mak, Shuai Wang","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T09:55:09Z","title":"MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08247","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":"sha256:21a7ec18e14f48f5b4ac8d5f70c193fa5029ee05c567b8b3d178a7fa67907907","target":"record","created_at":"2026-07-05T10:41:51Z","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":"75af4279639e34080b15f806013acb8ad1b539b2e819b2b75a06315c3cb23e38","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T09:55:09Z","title_canon_sha256":"d3f82789a074e9f0255b240bcc711ad6b6be5a0a010a6e93fe19c505175249d7"},"schema_version":"1.0","source":{"id":"2412.08247","kind":"arxiv","version":2}},"canonical_sha256":"fbd58e98675767dc9e5cc190fcce13c0acf5ec2b6eb192763a456dd4ae463967","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbd58e98675767dc9e5cc190fcce13c0acf5ec2b6eb192763a456dd4ae463967","first_computed_at":"2026-07-05T10:41:51.158191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:51.158191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7GawyHI8iM9Dnvu+JzdrQq0bzu7QRncHXVDAZ+xiJD0VztFWVIqWmhDuQ7mlm45KGIYIcSIEW60X2m0KsBtTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:51.158688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08247","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21a7ec18e14f48f5b4ac8d5f70c193fa5029ee05c567b8b3d178a7fa67907907","sha256:b028f6658febe573d86daef5a5334ae2f0e467b04308232ceb94d303d27c0a66"],"state_sha256":"443c0f5b0dc694242d83c5babd9944b09fdef1772544942c71f69d909791bde9"}