{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:43KO7CLCBMXBWRXPVEMFCVXEHU","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":"83b7cbf1635b2d05b7274582483bc635eacd3854f46a42609dbc5aaf9176cb97","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-29T12:38:00Z","title_canon_sha256":"652385809088fe1f7e42b33f8710afd7e2368d5b0400d5d494a1c1dae25be34e"},"schema_version":"1.0","source":{"id":"2309.17189","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17189","created_at":"2026-07-05T07:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17189v4","created_at":"2026-07-05T07:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17189","created_at":"2026-07-05T07:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"43KO7CLCBMXB","created_at":"2026-07-05T07:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"43KO7CLCBMXBWRXP","created_at":"2026-07-05T07:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"43KO7CLC","created_at":"2026-07-05T07:58:45Z"}],"graph_snapshots":[{"event_id":"sha256:7f80693b1337aa07a52ed141092db15872fd6711e5e36f4d7526113c23b19da7","target":"graph","created_at":"2026-07-05T07:58:45Z","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/2309.17189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA) models operate in the time domain. However, their overly simplistic approach to modeling acoustic features often necessitates larger and more computationally intensive models in order to achieve SOTA performance. In this paper, we present a novel time-frequency domain audio-visual speech separation method: Recurrent Time-Frequency Separation Network (RTFS-Ne","authors_text":"Kai Li, Samuel Pegg, Xiaolin Hu","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-29T12:38:00Z","title":"RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17189","kind":"arxiv","version":4},"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":"sha256:75b83ab993dc0189f42b84e387262628a5f52dff31d2a0dd6c1afd3aa2658816","target":"record","created_at":"2026-07-05T07:58:45Z","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":"83b7cbf1635b2d05b7274582483bc635eacd3854f46a42609dbc5aaf9176cb97","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-29T12:38:00Z","title_canon_sha256":"652385809088fe1f7e42b33f8710afd7e2368d5b0400d5d494a1c1dae25be34e"},"schema_version":"1.0","source":{"id":"2309.17189","kind":"arxiv","version":4}},"canonical_sha256":"e6d4ef89620b2e1b46efa9185156e43d16b69d198051540b468b08a3406b3ffe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6d4ef89620b2e1b46efa9185156e43d16b69d198051540b468b08a3406b3ffe","first_computed_at":"2026-07-05T07:58:45.129976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:45.129976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xhVw3SYL4ZN10uinwU5xETVB+nDQEttpUSsopXHGqgGs2wZUiCdfCqroO9MviyVXGWlL4a6zDLMVlbR0B6rqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:45.130454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.17189","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75b83ab993dc0189f42b84e387262628a5f52dff31d2a0dd6c1afd3aa2658816","sha256:7f80693b1337aa07a52ed141092db15872fd6711e5e36f4d7526113c23b19da7"],"state_sha256":"d980bda055a5f235e30fce241a496989c0f3c4aca0fdde7c54db62229fa0edb5"}