{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7JP2KIVP4CT7SYHFDSCXKA77NS","short_pith_number":"pith:7JP2KIVP","schema_version":"1.0","canonical_sha256":"fa5fa522afe0a7f960e51c857503ff6cbf040bbabc846232728c5bdbd36bb61e","source":{"kind":"arxiv","id":"2409.07614","version":3},"attestation_state":"computed","paper":{"title":"FlowSep: Language-Queried Sound Separation with Rectified Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Mark D. Plumbley, Wenwu Wang, Xubo Liu, Yi Yuan","submitted_at":"2024-09-11T20:54:23Z","abstract_excerpt":"Language-queried audio source separation (LASS) focuses on separating sounds using textual descriptions of the desired sources. Current methods mainly use discriminative approaches, such as time-frequency masking, to separate target sounds and minimize interference from other sources. However, these models face challenges when separating overlapping soundtracks, which may lead to artifacts such as spectral holes or incomplete separation. Rectified flow matching (RFM), a generative model that establishes linear relations between the distribution of data and noise, offers superior theoretical pr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.07614","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-11T20:54:23Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"dfaffe248bff5b9882fa00b1bf6cf972170d1faeff6b239ea052774a61fc3a9a","abstract_canon_sha256":"cd28d1bee9aa0ceb659890a8089b8e88654d93d7fbb67c94d26cbd680e38c80c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:59.846066Z","signature_b64":"9vzgF9Bb5R+g+bGpE/4zNcq/smiQ28gXRf/9utPVTNSGDYugE7WDWZwvuOtlbBY1JzwnC/wz+LsejXMF/YdgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa5fa522afe0a7f960e51c857503ff6cbf040bbabc846232728c5bdbd36bb61e","last_reissued_at":"2026-07-05T09:58:59.845607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:59.845607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowSep: Language-Queried Sound Separation with Rectified Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Mark D. Plumbley, Wenwu Wang, Xubo Liu, Yi Yuan","submitted_at":"2024-09-11T20:54:23Z","abstract_excerpt":"Language-queried audio source separation (LASS) focuses on separating sounds using textual descriptions of the desired sources. Current methods mainly use discriminative approaches, such as time-frequency masking, to separate target sounds and minimize interference from other sources. However, these models face challenges when separating overlapping soundtracks, which may lead to artifacts such as spectral holes or incomplete separation. Rectified flow matching (RFM), a generative model that establishes linear relations between the distribution of data and noise, offers superior theoretical pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07614","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/2409.07614/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.07614","created_at":"2026-07-05T09:58:59.845663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07614v3","created_at":"2026-07-05T09:58:59.845663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07614","created_at":"2026-07-05T09:58:59.845663+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JP2KIVP4CT7","created_at":"2026-07-05T09:58:59.845663+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JP2KIVP4CT7SYHF","created_at":"2026-07-05T09:58:59.845663+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JP2KIVP","created_at":"2026-07-05T09:58:59.845663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.06027","citing_title":"DreamAudio: Customized Text-to-Audio Generation with Diffusion Models","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS","json":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS.json","graph_json":"https://pith.science/api/pith-number/7JP2KIVP4CT7SYHFDSCXKA77NS/graph.json","events_json":"https://pith.science/api/pith-number/7JP2KIVP4CT7SYHFDSCXKA77NS/events.json","paper":"https://pith.science/paper/7JP2KIVP"},"agent_actions":{"view_html":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS","download_json":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS.json","view_paper":"https://pith.science/paper/7JP2KIVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07614&json=true","fetch_graph":"https://pith.science/api/pith-number/7JP2KIVP4CT7SYHFDSCXKA77NS/graph.json","fetch_events":"https://pith.science/api/pith-number/7JP2KIVP4CT7SYHFDSCXKA77NS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS/action/storage_attestation","attest_author":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS/action/author_attestation","sign_citation":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS/action/citation_signature","submit_replication":"https://pith.science/pith/7JP2KIVP4CT7SYHFDSCXKA77NS/action/replication_record"}},"created_at":"2026-07-05T09:58:59.845663+00:00","updated_at":"2026-07-05T09:58:59.845663+00:00"}