{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PLUW6BU65WOCFI534VG5ZKI6PD","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":"d82f66c90ac37819b4f01ce0f5542930d71cdba853bcc1ee701ea699f434245b","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-25T13:47:22Z","title_canon_sha256":"f0a7dd438457df16837fffde8905a6903f5a07175d0d387a39ded2ecfe844bf1"},"schema_version":"1.0","source":{"id":"2401.14185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14185","created_at":"2026-07-05T07:37:32Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14185v1","created_at":"2026-07-05T07:37:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14185","created_at":"2026-07-05T07:37:32Z"},{"alias_kind":"pith_short_12","alias_value":"PLUW6BU65WOC","created_at":"2026-07-05T07:37:32Z"},{"alias_kind":"pith_short_16","alias_value":"PLUW6BU65WOCFI53","created_at":"2026-07-05T07:37:32Z"},{"alias_kind":"pith_short_8","alias_value":"PLUW6BU6","created_at":"2026-07-05T07:37:32Z"}],"graph_snapshots":[{"event_id":"sha256:0f7c9a24819be76a7f83ea2ca0d5380406ffd0e99178fc0be26e261b805e78af","target":"graph","created_at":"2026-07-05T07:37:32Z","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/2401.14185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speech separation has gained significant traction in recent years due to its potential applications in various fields such as speech recognition, diarization, scene analysis and assistive technologies. Designing a lightweight audio-visual speech separation network is important for low-latency applications, but existing methods often require higher computational costs and more parameters to achieve better separation performance. In this paper, we present an audio-visual speech separation model called Top-Down-Fusion Net (TDFNet), a state-of-the-art (SOTA) model for audio-visual spe","authors_text":"Kai Li, Samuel Pegg, Xiaolin Hu","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-25T13:47:22Z","title":"TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14185","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:e48303c50354437bd87035532a57d0084127e8e39eb9daaedcdd579297dd7ae8","target":"record","created_at":"2026-07-05T07:37:32Z","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":"d82f66c90ac37819b4f01ce0f5542930d71cdba853bcc1ee701ea699f434245b","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-25T13:47:22Z","title_canon_sha256":"f0a7dd438457df16837fffde8905a6903f5a07175d0d387a39ded2ecfe844bf1"},"schema_version":"1.0","source":{"id":"2401.14185","kind":"arxiv","version":1}},"canonical_sha256":"7ae96f069eed9c22a3bbe54ddca91e78c097d5be7fb675102af8d2bf029f3b00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ae96f069eed9c22a3bbe54ddca91e78c097d5be7fb675102af8d2bf029f3b00","first_computed_at":"2026-07-05T07:37:32.558965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:32.558965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kDZNKce8ZbKwnCiEsEHump4cBWr8yP4Dx7k6zsN0oWgupIN5zd2CENv1xXScpdtdmYutf0fF4jr9ZDkWXyoODg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:32.559382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e48303c50354437bd87035532a57d0084127e8e39eb9daaedcdd579297dd7ae8","sha256:0f7c9a24819be76a7f83ea2ca0d5380406ffd0e99178fc0be26e261b805e78af"],"state_sha256":"5b180b288f6646846a8c10ea3664f85feea851d620dd3de6d96cba33405bd49b"}