{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E2TXEIX7XASUYG4G37FO2F6KNY","short_pith_number":"pith:E2TXEIX7","schema_version":"1.0","canonical_sha256":"26a77222ffb8254c1b86dfcaed17ca6e3fc22d3c45c7dd93de6992c69986b2a6","source":{"kind":"arxiv","id":"2505.16119","version":2},"attestation_state":"computed","paper":{"title":"Source Separation by Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Arnaud Doucet, Henry Li, John R. Hershey, Robin Scheibler","submitted_at":"2025-05-22T01:52:06Z","abstract_excerpt":"We consider the problem of single-channel audio source separation with the goal of reconstructing $K$ sources from their mixture. We address this ill-posed problem with FLOSS (FLOw matching for Source Separation), a constrained generation method based on flow matching, ensuring strict mixture consistency. Flow matching is a general methodology that, when given samples from two probability distributions defined on the same space, learns an ordinary differential equation to output a sample from one of the distributions when provided with a sample from the other. In our context, we have access to"},"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":"2505.16119","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-22T01:52:06Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e63d7ddbbf54dd700d9b4a0bf88d88cd160e517fc5a5e57fcef5b32d01f4cc07","abstract_canon_sha256":"bd7a6bdae568f89ac22f6405357095f7095fccd77edb974ba6895a0259c595f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:11.668610Z","signature_b64":"NVc5kOCW7iZJJOC7UILqR0NRnBgS6RFZ83mmC/+z2xB+djjMoDVwy2sb55J1AZqe9kT0BYgbD2hxch80N98dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26a77222ffb8254c1b86dfcaed17ca6e3fc22d3c45c7dd93de6992c69986b2a6","last_reissued_at":"2026-07-05T11:39:11.668119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:11.668119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Source Separation by Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Arnaud Doucet, Henry Li, John R. Hershey, Robin Scheibler","submitted_at":"2025-05-22T01:52:06Z","abstract_excerpt":"We consider the problem of single-channel audio source separation with the goal of reconstructing $K$ sources from their mixture. We address this ill-posed problem with FLOSS (FLOw matching for Source Separation), a constrained generation method based on flow matching, ensuring strict mixture consistency. Flow matching is a general methodology that, when given samples from two probability distributions defined on the same space, learns an ordinary differential equation to output a sample from one of the distributions when provided with a sample from the other. In our context, we have access to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16119","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/2505.16119/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":"2505.16119","created_at":"2026-07-05T11:39:11.668179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16119v2","created_at":"2026-07-05T11:39:11.668179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16119","created_at":"2026-07-05T11:39:11.668179+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2TXEIX7XASU","created_at":"2026-07-05T11:39:11.668179+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2TXEIX7XASUYG4G","created_at":"2026-07-05T11:39:11.668179+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2TXEIX7","created_at":"2026-07-05T11:39:11.668179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09803","citing_title":"MAGE: Modality-Agnostic Music Generation and Target-Source Extraction","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY","json":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY.json","graph_json":"https://pith.science/api/pith-number/E2TXEIX7XASUYG4G37FO2F6KNY/graph.json","events_json":"https://pith.science/api/pith-number/E2TXEIX7XASUYG4G37FO2F6KNY/events.json","paper":"https://pith.science/paper/E2TXEIX7"},"agent_actions":{"view_html":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY","download_json":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY.json","view_paper":"https://pith.science/paper/E2TXEIX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16119&json=true","fetch_graph":"https://pith.science/api/pith-number/E2TXEIX7XASUYG4G37FO2F6KNY/graph.json","fetch_events":"https://pith.science/api/pith-number/E2TXEIX7XASUYG4G37FO2F6KNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY/action/storage_attestation","attest_author":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY/action/author_attestation","sign_citation":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY/action/citation_signature","submit_replication":"https://pith.science/pith/E2TXEIX7XASUYG4G37FO2F6KNY/action/replication_record"}},"created_at":"2026-07-05T11:39:11.668179+00:00","updated_at":"2026-07-05T11:39:11.668179+00:00"}