{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2BJ2QB4F3BXS22Q45ONAXUDON6","short_pith_number":"pith:2BJ2QB4F","canonical_record":{"source":{"id":"2505.19314","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-25T21:00:48Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"244c17f44d2d5c68c03ce27b2b846844c313716c54c38444d398d99e98a47c4c","abstract_canon_sha256":"bc924dcc9a24e73ce6c3343eeadf256aede74786f1007517446f4f7f2110531d"},"schema_version":"1.0"},"canonical_sha256":"d053a80785d86f2d6a1ceb9a0bd06e6f8749f0d7d8607e4ad256272378e2bd32","source":{"kind":"arxiv","id":"2505.19314","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19314","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19314v3","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19314","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"2BJ2QB4F3BXS","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"2BJ2QB4F3BXS22Q4","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"2BJ2QB4F","created_at":"2026-07-05T12:06:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2BJ2QB4F3BXS22Q45ONAXUDON6","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19314","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-25T21:00:48Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"244c17f44d2d5c68c03ce27b2b846844c313716c54c38444d398d99e98a47c4c","abstract_canon_sha256":"bc924dcc9a24e73ce6c3343eeadf256aede74786f1007517446f4f7f2110531d"},"schema_version":"1.0"},"canonical_sha256":"d053a80785d86f2d6a1ceb9a0bd06e6f8749f0d7d8607e4ad256272378e2bd32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:13.069753Z","signature_b64":"0lI++uIKt1ivdW4CNgg1E0LTClp++0+TI6JMDxkbO4dOxzeUJOcJIZh5lCCnH1eVrHKxvlCBnYcXay1oTmJbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d053a80785d86f2d6a1ceb9a0bd06e6f8749f0d7d8607e4ad256272378e2bd32","last_reissued_at":"2026-07-05T12:06:13.069231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:13.069231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19314","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":"2026-07-05T12:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C9PLTVf/4XAqpYZicVF8gXNKwJLQ2UCv+QGvI0x3IV7ZUkbKMZ24lQDuyZIeJ4bN1+Nqg8C7hVHmcYKZ7W04BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T05:58:09.507723Z"},"content_sha256":"819623cb637ccf49cb1196c687e51839fe34dabbdbe44833401fd555f7bac5f0","schema_version":"1.0","event_id":"sha256:819623cb637ccf49cb1196c687e51839fe34dabbdbe44833401fd555f7bac5f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2BJ2QB4F3BXS22Q45ONAXUDON6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chen Chen, Dongchao Yang, Helin Wang, Jesus Villalba, Jiarui Hai, Junyi Peng, Kai Li, Laureano Moro Velazquez, Najim Dehak, Thomas Thebaud","submitted_at":"2025-05-25T21:00:48Z","abstract_excerpt":"Target Speech Extraction (TSE) aims to isolate a target speaker's voice from a mixture of multiple speakers by leveraging speaker-specific cues, typically provided as auxiliary audio (a.k.a. cue audio). Although recent advancements in TSE have primarily employed discriminative models that offer high perceptual quality, these models often introduce unwanted artifacts, reduce naturalness, and are sensitive to discrepancies between training and testing environments. On the other hand, generative models for TSE lag in perceptual quality and intelligibility. To address these challenges, we present "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19314","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/2505.19314/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":"2026-07-05T12:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LaASG5fmrL3OgBOytU0pMv77XbK+Sm1eShSweDnTo8dT4qqYoHmXqSQ9n31mZuQptoRwQ0voGOWhR4IrLdcFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T05:58:09.508146Z"},"content_sha256":"d5547928077b72a38a6589961d5e965a87519639941620138ba3a41dcb17f336","schema_version":"1.0","event_id":"sha256:d5547928077b72a38a6589961d5e965a87519639941620138ba3a41dcb17f336"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BJ2QB4F3BXS22Q45ONAXUDON6/bundle.json","state_url":"https://pith.science/pith/2BJ2QB4F3BXS22Q45ONAXUDON6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BJ2QB4F3BXS22Q45ONAXUDON6/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":"2026-07-13T05:58:09Z","links":{"resolver":"https://pith.science/pith/2BJ2QB4F3BXS22Q45ONAXUDON6","bundle":"https://pith.science/pith/2BJ2QB4F3BXS22Q45ONAXUDON6/bundle.json","state":"https://pith.science/pith/2BJ2QB4F3BXS22Q45ONAXUDON6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BJ2QB4F3BXS22Q45ONAXUDON6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2BJ2QB4F3BXS22Q45ONAXUDON6","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":"bc924dcc9a24e73ce6c3343eeadf256aede74786f1007517446f4f7f2110531d","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-25T21:00:48Z","title_canon_sha256":"244c17f44d2d5c68c03ce27b2b846844c313716c54c38444d398d99e98a47c4c"},"schema_version":"1.0","source":{"id":"2505.19314","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19314","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19314v3","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19314","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"2BJ2QB4F3BXS","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"2BJ2QB4F3BXS22Q4","created_at":"2026-07-05T12:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"2BJ2QB4F","created_at":"2026-07-05T12:06:13Z"}],"graph_snapshots":[{"event_id":"sha256:d5547928077b72a38a6589961d5e965a87519639941620138ba3a41dcb17f336","target":"graph","created_at":"2026-07-05T12:06:13Z","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/2505.19314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target Speech Extraction (TSE) aims to isolate a target speaker's voice from a mixture of multiple speakers by leveraging speaker-specific cues, typically provided as auxiliary audio (a.k.a. cue audio). Although recent advancements in TSE have primarily employed discriminative models that offer high perceptual quality, these models often introduce unwanted artifacts, reduce naturalness, and are sensitive to discrepancies between training and testing environments. On the other hand, generative models for TSE lag in perceptual quality and intelligibility. To address these challenges, we present ","authors_text":"Chen Chen, Dongchao Yang, Helin Wang, Jesus Villalba, Jiarui Hai, Junyi Peng, Kai Li, Laureano Moro Velazquez, Najim Dehak, Thomas Thebaud","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-25T21:00:48Z","title":"SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19314","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":"sha256:819623cb637ccf49cb1196c687e51839fe34dabbdbe44833401fd555f7bac5f0","target":"record","created_at":"2026-07-05T12:06:13Z","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":"bc924dcc9a24e73ce6c3343eeadf256aede74786f1007517446f4f7f2110531d","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-25T21:00:48Z","title_canon_sha256":"244c17f44d2d5c68c03ce27b2b846844c313716c54c38444d398d99e98a47c4c"},"schema_version":"1.0","source":{"id":"2505.19314","kind":"arxiv","version":3}},"canonical_sha256":"d053a80785d86f2d6a1ceb9a0bd06e6f8749f0d7d8607e4ad256272378e2bd32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d053a80785d86f2d6a1ceb9a0bd06e6f8749f0d7d8607e4ad256272378e2bd32","first_computed_at":"2026-07-05T12:06:13.069231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:13.069231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0lI++uIKt1ivdW4CNgg1E0LTClp++0+TI6JMDxkbO4dOxzeUJOcJIZh5lCCnH1eVrHKxvlCBnYcXay1oTmJbDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:13.069753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19314","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:819623cb637ccf49cb1196c687e51839fe34dabbdbe44833401fd555f7bac5f0","sha256:d5547928077b72a38a6589961d5e965a87519639941620138ba3a41dcb17f336"],"state_sha256":"6b440f75446bc7c59045cbacb896d5298bb04e4dbc0848467bbcdcb5925521c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDMPY/mSspkiAbtksogU39uZFGRcggGyHA5vYl7bIjDKSTTAYJhK+1gw6M3iK43kamvYR/knRB8TpN2z/uxpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T05:58:09.510336Z","bundle_sha256":"5e4883cdf179577cc2667dc6bf24ffd02469a51728d1812b1674064821b88196"}}