{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:44IPKYSUKK3WJF4YO5HWRAGIYY","short_pith_number":"pith:44IPKYSU","schema_version":"1.0","canonical_sha256":"e710f5625452b7649798774f6880c8c610fa6be9b63b2a999ec758d87dbed1ff","source":{"kind":"arxiv","id":"1911.13254","version":2},"attestation_state":"computed","paper":{"title":"Music Source Separation in the Waveform Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Alexandre D\\'efossez (FAIR, Francis Bach (DI-ENS, L\\'eon Bottou (FAIR), Nicolas Usunier (FAIR), PSL, PSL), SIERRA, SIERRA)","submitted_at":"2019-11-27T13:50:45Z","abstract_excerpt":"Source separation for music is the task of isolating contributions, or stems, from different instruments    recorded individually and arranged together to form a song. Such components include voice, bass, drums and any other accompaniments.Contrarily to many audio synthesis tasks where the best performances are achieved by models that directly generate the waveform, the state-of-the-art in source separation for music is to compute masks on the magnitude spectrum. In this paper, we compare two waveform domain architectures. We first adapt Conv-Tasnet, initially developed for speech source separ"},"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":"1911.13254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-11-27T13:50:45Z","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"b1d4bc7db76b8f427e2625c700fc228a2ec6ff5700e97475a6f3dbf9fd855c66","abstract_canon_sha256":"c147e874b88a4442603e438e8a1f7f181b3a672f199d7b176bdb17262d750fb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:03.227932Z","signature_b64":"bix2CksfEJQ8lkFTWLbRXyukf9I+KxHSKMGhKUgWJnwzusHTDJJFkSTp6hwjMZUwTI86HRsfYvsnvcgWFuenAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e710f5625452b7649798774f6880c8c610fa6be9b63b2a999ec758d87dbed1ff","last_reissued_at":"2026-07-05T02:36:03.227504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:03.227504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Music Source Separation in the Waveform Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Alexandre D\\'efossez (FAIR, Francis Bach (DI-ENS, L\\'eon Bottou (FAIR), Nicolas Usunier (FAIR), PSL, PSL), SIERRA, SIERRA)","submitted_at":"2019-11-27T13:50:45Z","abstract_excerpt":"Source separation for music is the task of isolating contributions, or stems, from different instruments    recorded individually and arranged together to form a song. Such components include voice, bass, drums and any other accompaniments.Contrarily to many audio synthesis tasks where the best performances are achieved by models that directly generate the waveform, the state-of-the-art in source separation for music is to compute masks on the magnitude spectrum. In this paper, we compare two waveform domain architectures. We first adapt Conv-Tasnet, initially developed for speech source separ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.13254","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/1911.13254/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":"1911.13254","created_at":"2026-07-05T02:36:03.227558+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.13254v2","created_at":"2026-07-05T02:36:03.227558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.13254","created_at":"2026-07-05T02:36:03.227558+00:00"},{"alias_kind":"pith_short_12","alias_value":"44IPKYSUKK3W","created_at":"2026-07-05T02:36:03.227558+00:00"},{"alias_kind":"pith_short_16","alias_value":"44IPKYSUKK3WJF4Y","created_at":"2026-07-05T02:36:03.227558+00:00"},{"alias_kind":"pith_short_8","alias_value":"44IPKYSU","created_at":"2026-07-05T02:36:03.227558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24127","citing_title":"DTT-BSR+: A Generative-Regression Cascade for Music Source Restoration","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21670","citing_title":"Improving Text-to-Music Generation with Human Preference Rewards","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17800","citing_title":"MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06965","citing_title":"Improving Music Source Separation with Diffusion and Consistency Refinement","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11717","citing_title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21247","citing_title":"The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2210.13438","citing_title":"High Fidelity Neural Audio Compression","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09371","citing_title":"Discrete Token Modeling for Multi-Stem Music Source Separation with Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09803","citing_title":"MAGE: Modality-Agnostic Music Generation and Target-Source Extraction","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16254","citing_title":"ArtifactNet: Detecting AI-Generated Music via Forensic Residual Physics","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY","json":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY.json","graph_json":"https://pith.science/api/pith-number/44IPKYSUKK3WJF4YO5HWRAGIYY/graph.json","events_json":"https://pith.science/api/pith-number/44IPKYSUKK3WJF4YO5HWRAGIYY/events.json","paper":"https://pith.science/paper/44IPKYSU"},"agent_actions":{"view_html":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY","download_json":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY.json","view_paper":"https://pith.science/paper/44IPKYSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.13254&json=true","fetch_graph":"https://pith.science/api/pith-number/44IPKYSUKK3WJF4YO5HWRAGIYY/graph.json","fetch_events":"https://pith.science/api/pith-number/44IPKYSUKK3WJF4YO5HWRAGIYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY/action/storage_attestation","attest_author":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY/action/author_attestation","sign_citation":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY/action/citation_signature","submit_replication":"https://pith.science/pith/44IPKYSUKK3WJF4YO5HWRAGIYY/action/replication_record"}},"created_at":"2026-07-05T02:36:03.227558+00:00","updated_at":"2026-07-05T02:36:03.227558+00:00"}