{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PLUW6BU65WOCFI534VG5ZKI6PD","short_pith_number":"pith:PLUW6BU6","canonical_record":{"source":{"id":"2401.14185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-25T13:47:22Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"f0a7dd438457df16837fffde8905a6903f5a07175d0d387a39ded2ecfe844bf1","abstract_canon_sha256":"d82f66c90ac37819b4f01ce0f5542930d71cdba853bcc1ee701ea699f434245b"},"schema_version":"1.0"},"canonical_sha256":"7ae96f069eed9c22a3bbe54ddca91e78c097d5be7fb675102af8d2bf029f3b00","source":{"kind":"arxiv","id":"2401.14185","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PLUW6BU65WOCFI534VG5ZKI6PD","target":"record","payload":{"canonical_record":{"source":{"id":"2401.14185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-25T13:47:22Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"f0a7dd438457df16837fffde8905a6903f5a07175d0d387a39ded2ecfe844bf1","abstract_canon_sha256":"d82f66c90ac37819b4f01ce0f5542930d71cdba853bcc1ee701ea699f434245b"},"schema_version":"1.0"},"canonical_sha256":"7ae96f069eed9c22a3bbe54ddca91e78c097d5be7fb675102af8d2bf029f3b00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:32.559382Z","signature_b64":"kDZNKce8ZbKwnCiEsEHump4cBWr8yP4Dx7k6zsN0oWgupIN5zd2CENv1xXScpdtdmYutf0fF4jr9ZDkWXyoODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae96f069eed9c22a3bbe54ddca91e78c097d5be7fb675102af8d2bf029f3b00","last_reissued_at":"2026-07-05T07:37:32.558965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:32.558965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.14185","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:37:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HuKUCmPw/7QcXkwdvWCAUouWxKuG2nWJv7zqBjY9MihuaY3a29Gxc6xIG51ym+TnWjWX/xUScKQFHTYzp+T9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:23:58.069968Z"},"content_sha256":"e48303c50354437bd87035532a57d0084127e8e39eb9daaedcdd579297dd7ae8","schema_version":"1.0","event_id":"sha256:e48303c50354437bd87035532a57d0084127e8e39eb9daaedcdd579297dd7ae8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PLUW6BU65WOCFI534VG5ZKI6PD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Li, Samuel Pegg, Xiaolin Hu","submitted_at":"2024-01-25T13:47:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14185","kind":"arxiv","version":1},"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/2401.14185/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":"2026-07-05T07:37:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EEt1VMYsk3QmcenlgYSfsxIYmb7mxS60rz7MfPLFnxKcLPhB+Xw2g28okoF9bB0h1vd3vUzK3tku4Ri4K6SLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:23:58.070525Z"},"content_sha256":"0f7c9a24819be76a7f83ea2ca0d5380406ffd0e99178fc0be26e261b805e78af","schema_version":"1.0","event_id":"sha256:0f7c9a24819be76a7f83ea2ca0d5380406ffd0e99178fc0be26e261b805e78af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/bundle.json","state_url":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLUW6BU65WOCFI534VG5ZKI6PD/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":"2026-08-09T06:23:58Z","links":{"resolver":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD","bundle":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/bundle.json","state":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLUW6BU65WOCFI534VG5ZKI6PD/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A4LZRTbNcT0w4mA1+0/OgWt4Ah38SNOnjCcmuyoivKfYNI+IuZP4nWs5wrZJXlWce3RoDcI1E0Kxb06iqjP/Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:23:58.074731Z","bundle_sha256":"36bbab3c17c2567166309e18fe12d35b6e7b5c626aadf3a28bc6ca50fa96ac2d"}}