{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GJ5HK3KBB6BPEOXS2VDFK5BJTH","short_pith_number":"pith:GJ5HK3KB","canonical_record":{"source":{"id":"2406.11619","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T15:04:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5d37de8aa6cb9bfebd3780a4d0d06ddbcf78b2c40dcffcbd6a0844ad210f99cd","abstract_canon_sha256":"73140e26e86d3ef35f323869c017b49468993f03199f870aa8f8263389f584bc"},"schema_version":"1.0"},"canonical_sha256":"327a756d410f82f23af2d54655742999c4c1a5baef44868b66f86fe935a0587b","source":{"kind":"arxiv","id":"2406.11619","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11619","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11619v1","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11619","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_12","alias_value":"GJ5HK3KBB6BP","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_16","alias_value":"GJ5HK3KBB6BPEOXS","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_8","alias_value":"GJ5HK3KB","created_at":"2026-07-05T08:32:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GJ5HK3KBB6BPEOXS2VDFK5BJTH","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11619","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T15:04:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5d37de8aa6cb9bfebd3780a4d0d06ddbcf78b2c40dcffcbd6a0844ad210f99cd","abstract_canon_sha256":"73140e26e86d3ef35f323869c017b49468993f03199f870aa8f8263389f584bc"},"schema_version":"1.0"},"canonical_sha256":"327a756d410f82f23af2d54655742999c4c1a5baef44868b66f86fe935a0587b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:55.645773Z","signature_b64":"QDcfb0KAMsnRgkvg/3Nmiss08kX2wJdESwDOisnS9Khz4brj+WngQ43cmUXRnDkdcx0xyDDWEWaE/s4FtWDqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"327a756d410f82f23af2d54655742999c4c1a5baef44868b66f86fe935a0587b","last_reissued_at":"2026-07-05T08:32:55.645299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:55.645299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11619","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":"2026-07-05T08:32:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EFjJw+GuAHy+tnf55/cI84UNzhEHXJ4PlD1T8PdXsjXr/PjHLKwJtWDujpeX95AF8oIc9gOn++HWRAk6ymTHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:20:49.199627Z"},"content_sha256":"fe4239a44340967748574ebb8c4d0c2430421bc3e9d045a63b44537c1cb68483","schema_version":"1.0","event_id":"sha256:fe4239a44340967748574ebb8c4d0c2430421bc3e9d045a63b44537c1cb68483"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GJ5HK3KBB6BPEOXS2VDFK5BJTH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Anurag Kumar, Buye Xu, Cheng Yu, Deliang Wang, Ke Tan, Vahid Ahmadi Kalkhorani","submitted_at":"2024-06-17T15:04:15Z","abstract_excerpt":"Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an audiovisual (AV) system for speech enhancement, target speaker extraction, and multi-talker speaker separation. AV-CrossNet is extended from the CrossNet architecture, which is a recently proposed network that performs complex spectral mapping for speech separation by leveraging global attention and positional encoding. To effectively utilize visual cues, the proposed system incorporates pre-extracted visual embeddings and employs a visual encoder comprising temporal co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11619","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/2406.11619/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":"2026-07-05T08:32:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0VRhpln0PmFzWR1s5CNDNwbzDRVT2x9Jlq4Dq16sGG7Iy3CoDM/AJehANyY3V8BT82kFydNE2o7lSNHNfXRFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:20:49.200186Z"},"content_sha256":"2af4c10757d94f9472f1f1cb8fb352bd7673872fd55c25befb4251267c14996c","schema_version":"1.0","event_id":"sha256:2af4c10757d94f9472f1f1cb8fb352bd7673872fd55c25befb4251267c14996c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJ5HK3KBB6BPEOXS2VDFK5BJTH/bundle.json","state_url":"https://pith.science/pith/GJ5HK3KBB6BPEOXS2VDFK5BJTH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJ5HK3KBB6BPEOXS2VDFK5BJTH/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":"2026-08-03T19:20:49Z","links":{"resolver":"https://pith.science/pith/GJ5HK3KBB6BPEOXS2VDFK5BJTH","bundle":"https://pith.science/pith/GJ5HK3KBB6BPEOXS2VDFK5BJTH/bundle.json","state":"https://pith.science/pith/GJ5HK3KBB6BPEOXS2VDFK5BJTH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJ5HK3KBB6BPEOXS2VDFK5BJTH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GJ5HK3KBB6BPEOXS2VDFK5BJTH","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":"73140e26e86d3ef35f323869c017b49468993f03199f870aa8f8263389f584bc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T15:04:15Z","title_canon_sha256":"5d37de8aa6cb9bfebd3780a4d0d06ddbcf78b2c40dcffcbd6a0844ad210f99cd"},"schema_version":"1.0","source":{"id":"2406.11619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11619","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11619v1","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11619","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_12","alias_value":"GJ5HK3KBB6BP","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_16","alias_value":"GJ5HK3KBB6BPEOXS","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_8","alias_value":"GJ5HK3KB","created_at":"2026-07-05T08:32:55Z"}],"graph_snapshots":[{"event_id":"sha256:2af4c10757d94f9472f1f1cb8fb352bd7673872fd55c25befb4251267c14996c","target":"graph","created_at":"2026-07-05T08:32:55Z","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/2406.11619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an audiovisual (AV) system for speech enhancement, target speaker extraction, and multi-talker speaker separation. AV-CrossNet is extended from the CrossNet architecture, which is a recently proposed network that performs complex spectral mapping for speech separation by leveraging global attention and positional encoding. To effectively utilize visual cues, the proposed system incorporates pre-extracted visual embeddings and employs a visual encoder comprising temporal co","authors_text":"Anurag Kumar, Buye Xu, Cheng Yu, Deliang Wang, Ke Tan, Vahid Ahmadi Kalkhorani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T15:04:15Z","title":"AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11619","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:fe4239a44340967748574ebb8c4d0c2430421bc3e9d045a63b44537c1cb68483","target":"record","created_at":"2026-07-05T08:32:55Z","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":"73140e26e86d3ef35f323869c017b49468993f03199f870aa8f8263389f584bc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T15:04:15Z","title_canon_sha256":"5d37de8aa6cb9bfebd3780a4d0d06ddbcf78b2c40dcffcbd6a0844ad210f99cd"},"schema_version":"1.0","source":{"id":"2406.11619","kind":"arxiv","version":1}},"canonical_sha256":"327a756d410f82f23af2d54655742999c4c1a5baef44868b66f86fe935a0587b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"327a756d410f82f23af2d54655742999c4c1a5baef44868b66f86fe935a0587b","first_computed_at":"2026-07-05T08:32:55.645299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:55.645299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QDcfb0KAMsnRgkvg/3Nmiss08kX2wJdESwDOisnS9Khz4brj+WngQ43cmUXRnDkdcx0xyDDWEWaE/s4FtWDqCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:55.645773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe4239a44340967748574ebb8c4d0c2430421bc3e9d045a63b44537c1cb68483","sha256:2af4c10757d94f9472f1f1cb8fb352bd7673872fd55c25befb4251267c14996c"],"state_sha256":"4bf598217aa8aa0fc98423ae83bd8344ddfbbdd914a909cc209efeeef1592b5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0VDGzmB7xhN7wwN/COGss7AHZApsSdzUvxPlxXnLNXlifdD9wYkDwte2uScNpjVLMGZVCesIkqPrTnTmVIvlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:20:49.204167Z","bundle_sha256":"4468b710f311dbe6b5f1a0bc9749f57354bdf428a4b68c48f791a0da7f0c4dda"}}