{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HJ2ZXVTBAK3XR3WQ4U6GK5BKX5","short_pith_number":"pith:HJ2ZXVTB","canonical_record":{"source":{"id":"2404.18501","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-29T08:43:57Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"19be7d54126195ceb11681e069aa5268e263e903a72f3364d511a0942ffd852f","abstract_canon_sha256":"7d529825ed2e8c9a7e5c263476e7793ae6d54692f4cc3b1a3a535018e6afaf46"},"schema_version":"1.0"},"canonical_sha256":"3a759bd66102b778eed0e53c65742abf42b40fb95de01fd484c0d59fa1cdc579","source":{"kind":"arxiv","id":"2404.18501","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18501","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18501v3","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18501","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"HJ2ZXVTBAK3X","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_16","alias_value":"HJ2ZXVTBAK3XR3WQ","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_8","alias_value":"HJ2ZXVTB","created_at":"2026-07-05T10:22:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HJ2ZXVTBAK3XR3WQ4U6GK5BKX5","target":"record","payload":{"canonical_record":{"source":{"id":"2404.18501","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-29T08:43:57Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"19be7d54126195ceb11681e069aa5268e263e903a72f3364d511a0942ffd852f","abstract_canon_sha256":"7d529825ed2e8c9a7e5c263476e7793ae6d54692f4cc3b1a3a535018e6afaf46"},"schema_version":"1.0"},"canonical_sha256":"3a759bd66102b778eed0e53c65742abf42b40fb95de01fd484c0d59fa1cdc579","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:45.855641Z","signature_b64":"N6xiy7i8q7KL+yZqVXQekw3dVXuUvsJZweC3n4BF2QZ2XOVQ47m7ESxzcVJGr8kJxGNNmHlwLKQXKnM9j2LADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a759bd66102b778eed0e53c65742abf42b40fb95de01fd484c0d59fa1cdc579","last_reissued_at":"2026-07-05T10:22:45.854825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:45.854825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.18501","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YelIPU7AluuhDPsukykU2Yr8rV/y1SrUA2/kzj9tT/LNOBHN1GQXb72YUtDZrZfWbdDR7CBpvHYYEXlkrDJyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T17:41:59.734607Z"},"content_sha256":"d46613a13ed4aad5fa3f44e0dc9a4cd8b10213ebcc29a92c7b070f553f1d11d2","schema_version":"1.0","event_id":"sha256:d46613a13ed4aad5fa3f44e0dc9a4cd8b10213ebcc29a92c7b070f553f1d11d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HJ2ZXVTBAK3XR3WQ4U6GK5BKX5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Target Speaker Extraction with Reverse Selective Auditory Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Jiadong Wang, Junjie Li, Ruijie Tao, Xinyuan Qian, Yidi Jiang","submitted_at":"2024-04-29T08:43:57Z","abstract_excerpt":"Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person's speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization. However, this strategy mainly focuses on the existence of target speech, while ignoring the variations of the noise characteristics, i.e., interference speaker and the background noise. That may result in extracting noisy signals from the incorrect sound source in challenging acoustic situations. To this end, we propose a novel selective auditory attention mechani"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18501","kind":"arxiv","version":3},"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/2404.18501/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":"2026-07-05T10:22:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4shFn5JqDJSXUeRTDQyc/dq7gz3btNVIJC6KzPUBiKFgCLUw6Ferddth4hf1WSi+D+vRDpA52sf2XWbis/JAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T17:41:59.734978Z"},"content_sha256":"33cc3973847da714cc4950271587ae1fc9f875bc441127aeb25a793ffc497699","schema_version":"1.0","event_id":"sha256:33cc3973847da714cc4950271587ae1fc9f875bc441127aeb25a793ffc497699"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJ2ZXVTBAK3XR3WQ4U6GK5BKX5/bundle.json","state_url":"https://pith.science/pith/HJ2ZXVTBAK3XR3WQ4U6GK5BKX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJ2ZXVTBAK3XR3WQ4U6GK5BKX5/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":"2026-07-13T17:41:59Z","links":{"resolver":"https://pith.science/pith/HJ2ZXVTBAK3XR3WQ4U6GK5BKX5","bundle":"https://pith.science/pith/HJ2ZXVTBAK3XR3WQ4U6GK5BKX5/bundle.json","state":"https://pith.science/pith/HJ2ZXVTBAK3XR3WQ4U6GK5BKX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJ2ZXVTBAK3XR3WQ4U6GK5BKX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HJ2ZXVTBAK3XR3WQ4U6GK5BKX5","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":"7d529825ed2e8c9a7e5c263476e7793ae6d54692f4cc3b1a3a535018e6afaf46","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-29T08:43:57Z","title_canon_sha256":"19be7d54126195ceb11681e069aa5268e263e903a72f3364d511a0942ffd852f"},"schema_version":"1.0","source":{"id":"2404.18501","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18501","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18501v3","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18501","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"HJ2ZXVTBAK3X","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_16","alias_value":"HJ2ZXVTBAK3XR3WQ","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_8","alias_value":"HJ2ZXVTB","created_at":"2026-07-05T10:22:45Z"}],"graph_snapshots":[{"event_id":"sha256:33cc3973847da714cc4950271587ae1fc9f875bc441127aeb25a793ffc497699","target":"graph","created_at":"2026-07-05T10:22:45Z","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/2404.18501/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 extract the specific person's speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization. However, this strategy mainly focuses on the existence of target speech, while ignoring the variations of the noise characteristics, i.e., interference speaker and the background noise. That may result in extracting noisy signals from the incorrect sound source in challenging acoustic situations. To this end, we propose a novel selective auditory attention mechani","authors_text":"Haizhou Li, Jiadong Wang, Junjie Li, Ruijie Tao, Xinyuan Qian, Yidi Jiang","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-29T08:43:57Z","title":"Audio-Visual Target Speaker Extraction with Reverse Selective Auditory Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18501","kind":"arxiv","version":3},"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:d46613a13ed4aad5fa3f44e0dc9a4cd8b10213ebcc29a92c7b070f553f1d11d2","target":"record","created_at":"2026-07-05T10:22:45Z","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":"7d529825ed2e8c9a7e5c263476e7793ae6d54692f4cc3b1a3a535018e6afaf46","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-29T08:43:57Z","title_canon_sha256":"19be7d54126195ceb11681e069aa5268e263e903a72f3364d511a0942ffd852f"},"schema_version":"1.0","source":{"id":"2404.18501","kind":"arxiv","version":3}},"canonical_sha256":"3a759bd66102b778eed0e53c65742abf42b40fb95de01fd484c0d59fa1cdc579","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a759bd66102b778eed0e53c65742abf42b40fb95de01fd484c0d59fa1cdc579","first_computed_at":"2026-07-05T10:22:45.854825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:45.854825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N6xiy7i8q7KL+yZqVXQekw3dVXuUvsJZweC3n4BF2QZ2XOVQ47m7ESxzcVJGr8kJxGNNmHlwLKQXKnM9j2LADg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:45.855641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18501","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d46613a13ed4aad5fa3f44e0dc9a4cd8b10213ebcc29a92c7b070f553f1d11d2","sha256:33cc3973847da714cc4950271587ae1fc9f875bc441127aeb25a793ffc497699"],"state_sha256":"ccbbae769c3a6e4975a1f2cf023be50db09f22c617c1491e167188d81261bd4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CsTqQGwvsUkMkfy7Z/2+og02ds73YzEixX9rgy5j1NazRaTk0lofHDgdVibKjyNMXUQurLDklc0JjCnnYekLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T17:41:59.737442Z","bundle_sha256":"9fe20a6f0dd8ed0edcb85d4a22d9b7fc82a58f38e426e4a93d9f284ba2df4490"}}