{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BW537P6IREMMR77GWPOEPUJ73J","short_pith_number":"pith:BW537P6I","canonical_record":{"source":{"id":"2404.12725","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-19T09:08:44Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"a44d7dfd72ece6058cfa80172431d2d636ad0161a504377d9b7cf26ba5fba396","abstract_canon_sha256":"fea378182b7b85fc011232fbe20339a7232734077d81d768f9925e51202a69ab"},"schema_version":"1.0"},"canonical_sha256":"0dbbbfbfc88918c8ffe6b3dc47d13fda7e8cfd823fb50cd35a93a279cdecbcd6","source":{"kind":"arxiv","id":"2404.12725","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12725","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12725v2","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12725","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"pith_short_12","alias_value":"BW537P6IREMM","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"pith_short_16","alias_value":"BW537P6IREMMR77G","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"pith_short_8","alias_value":"BW537P6I","created_at":"2026-07-05T08:15:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BW537P6IREMMR77GWPOEPUJ73J","target":"record","payload":{"canonical_record":{"source":{"id":"2404.12725","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-19T09:08:44Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"a44d7dfd72ece6058cfa80172431d2d636ad0161a504377d9b7cf26ba5fba396","abstract_canon_sha256":"fea378182b7b85fc011232fbe20339a7232734077d81d768f9925e51202a69ab"},"schema_version":"1.0"},"canonical_sha256":"0dbbbfbfc88918c8ffe6b3dc47d13fda7e8cfd823fb50cd35a93a279cdecbcd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:49.456943Z","signature_b64":"ocfYnprmoy7lTwkBXK2FpO0tCFyhwGfGv/iPvoLWCyhV1ETN/kG25mo1EvdjXiD8Ay0AwLNRS9F0VTQrR3M8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dbbbfbfc88918c8ffe6b3dc47d13fda7e8cfd823fb50cd35a93a279cdecbcd6","last_reissued_at":"2026-07-05T08:15:49.456467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:49.456467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.12725","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:15:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V+IUIHwbFYbCIIWtLkoAwbmG0RsD1s02+uAwOR7XIuoID5OLopoXeazhULaqm1RoEoA/aoKYw4E5t7a26+WNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:47.123586Z"},"content_sha256":"2a6890bd0044483db99ab23d04fc83e77b8779c6447841246f6ba944604c6bce","schema_version":"1.0","event_id":"sha256:2a6890bd0044483db99ab23d04fc83e77b8779c6447841246f6ba944604c6bce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BW537P6IREMMR77GWPOEPUJ73J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Xinyu Yang, Zhaoxi Mu","submitted_at":"2024-04-19T09:08:44Z","abstract_excerpt":"The integration of visual cues has revitalized the performance of the target speech extraction task, elevating it to the forefront of the field. Nevertheless, this multi-modal learning paradigm often encounters the challenge of modality imbalance. In audio-visual target speech extraction tasks, the audio modality tends to dominate, potentially overshadowing the importance of visual guidance. To tackle this issue, we propose AVSepChain, drawing inspiration from the speech chain concept. Our approach partitions the audio-visual target speech extraction task into two stages: speech perception and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12725","kind":"arxiv","version":2},"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/2404.12725/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":"2026-07-05T08:15:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GFZNtdMvskvh+wkKkVZMOgq6yZeKZyAal31eP0AL8n5KqVPRLrOah7wZ5+bFf4Mprkp8E5MZBzm5KtN1/wQTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:47.124100Z"},"content_sha256":"6b59a930fa08bfd3885cbf747811f1a522ff1d7fd71963e80c714240feac3eb7","schema_version":"1.0","event_id":"sha256:6b59a930fa08bfd3885cbf747811f1a522ff1d7fd71963e80c714240feac3eb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BW537P6IREMMR77GWPOEPUJ73J/bundle.json","state_url":"https://pith.science/pith/BW537P6IREMMR77GWPOEPUJ73J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BW537P6IREMMR77GWPOEPUJ73J/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":"2026-08-08T10:22:47Z","links":{"resolver":"https://pith.science/pith/BW537P6IREMMR77GWPOEPUJ73J","bundle":"https://pith.science/pith/BW537P6IREMMR77GWPOEPUJ73J/bundle.json","state":"https://pith.science/pith/BW537P6IREMMR77GWPOEPUJ73J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BW537P6IREMMR77GWPOEPUJ73J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BW537P6IREMMR77GWPOEPUJ73J","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":"fea378182b7b85fc011232fbe20339a7232734077d81d768f9925e51202a69ab","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-19T09:08:44Z","title_canon_sha256":"a44d7dfd72ece6058cfa80172431d2d636ad0161a504377d9b7cf26ba5fba396"},"schema_version":"1.0","source":{"id":"2404.12725","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12725","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12725v2","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12725","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"pith_short_12","alias_value":"BW537P6IREMM","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"pith_short_16","alias_value":"BW537P6IREMMR77G","created_at":"2026-07-05T08:15:49Z"},{"alias_kind":"pith_short_8","alias_value":"BW537P6I","created_at":"2026-07-05T08:15:49Z"}],"graph_snapshots":[{"event_id":"sha256:6b59a930fa08bfd3885cbf747811f1a522ff1d7fd71963e80c714240feac3eb7","target":"graph","created_at":"2026-07-05T08:15:49Z","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/2404.12725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of visual cues has revitalized the performance of the target speech extraction task, elevating it to the forefront of the field. Nevertheless, this multi-modal learning paradigm often encounters the challenge of modality imbalance. In audio-visual target speech extraction tasks, the audio modality tends to dominate, potentially overshadowing the importance of visual guidance. To tackle this issue, we propose AVSepChain, drawing inspiration from the speech chain concept. Our approach partitions the audio-visual target speech extraction task into two stages: speech perception and","authors_text":"Xinyu Yang, Zhaoxi Mu","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-19T09:08:44Z","title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12725","kind":"arxiv","version":2},"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":"sha256:2a6890bd0044483db99ab23d04fc83e77b8779c6447841246f6ba944604c6bce","target":"record","created_at":"2026-07-05T08:15:49Z","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":"fea378182b7b85fc011232fbe20339a7232734077d81d768f9925e51202a69ab","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-19T09:08:44Z","title_canon_sha256":"a44d7dfd72ece6058cfa80172431d2d636ad0161a504377d9b7cf26ba5fba396"},"schema_version":"1.0","source":{"id":"2404.12725","kind":"arxiv","version":2}},"canonical_sha256":"0dbbbfbfc88918c8ffe6b3dc47d13fda7e8cfd823fb50cd35a93a279cdecbcd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dbbbfbfc88918c8ffe6b3dc47d13fda7e8cfd823fb50cd35a93a279cdecbcd6","first_computed_at":"2026-07-05T08:15:49.456467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:49.456467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ocfYnprmoy7lTwkBXK2FpO0tCFyhwGfGv/iPvoLWCyhV1ETN/kG25mo1EvdjXiD8Ay0AwLNRS9F0VTQrR3M8Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:49.456943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12725","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a6890bd0044483db99ab23d04fc83e77b8779c6447841246f6ba944604c6bce","sha256:6b59a930fa08bfd3885cbf747811f1a522ff1d7fd71963e80c714240feac3eb7"],"state_sha256":"3b9f8b3f1ea2c8a5c5b2842c4e998abe06f12d8485ecc3bf4578da0fd1aa48d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DV48/UvlR1DNhHltUJ01FF46KCdQrRp7kD0rxC/U1bEzYZsXa1OCOC8Trt/X4VHvQkpFt/jVjEpY1yUP6nw+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:22:47.129661Z","bundle_sha256":"3eb29cb65b3563362c0d2769fc4630432f76ce3087f3fd067659abed044545f0"}}