{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VGJWP3WVOZVXRIGK65Q6EZQZAA","short_pith_number":"pith:VGJWP3WV","schema_version":"1.0","canonical_sha256":"a99367eed5766b78a0caf761e26619000e9942940a8371fa762ac5c1167db62c","source":{"kind":"arxiv","id":"2109.05418","version":1},"attestation_state":"computed","paper":{"title":"Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Keunwoo Choi, Qiuqiang Kong, Yin Cao, Yuxuan Wang","submitted_at":"2021-09-12T03:42:48Z","abstract_excerpt":"Deep neural network based methods have been successfully applied to music source separation. They typically learn a mapping from a mixture spectrogram to a set of source spectrograms, all with magnitudes only. This approach has several limitations: 1) its incorrect phase reconstruction degrades the performance, 2) it limits the magnitude of masks between 0 and 1 while we observe that 22% of time-frequency bins have ideal ratio mask values of over~1 in a popular dataset, MUSDB18, 3) its potential on very deep architectures is under-explored. Our proposed system is designed to overcome these. Fi"},"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":"2109.05418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-09-12T03:42:48Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f70ee190492b2ea063a81dbf46577b0359367302c025a22a3bc3a1de5c2d5929","abstract_canon_sha256":"5bd3b8dbe3f101e90c8f312601943120d060645125b55f8ad9140e29359511ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:38.759408Z","signature_b64":"xUv5wxB8eZdqpur8NmOGItJML/F3BwpKjgQRj5isZbZXQfWzmNkp9FftvObotxNqdRzFlKLUAgNEk/SuMW+pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a99367eed5766b78a0caf761e26619000e9942940a8371fa762ac5c1167db62c","last_reissued_at":"2026-07-05T03:13:38.759012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:38.759012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Keunwoo Choi, Qiuqiang Kong, Yin Cao, Yuxuan Wang","submitted_at":"2021-09-12T03:42:48Z","abstract_excerpt":"Deep neural network based methods have been successfully applied to music source separation. They typically learn a mapping from a mixture spectrogram to a set of source spectrograms, all with magnitudes only. This approach has several limitations: 1) its incorrect phase reconstruction degrades the performance, 2) it limits the magnitude of masks between 0 and 1 while we observe that 22% of time-frequency bins have ideal ratio mask values of over~1 in a popular dataset, MUSDB18, 3) its potential on very deep architectures is under-explored. Our proposed system is designed to overcome these. Fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05418","kind":"arxiv","version":1},"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/2109.05418/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":"2109.05418","created_at":"2026-07-05T03:13:38.759068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05418v1","created_at":"2026-07-05T03:13:38.759068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05418","created_at":"2026-07-05T03:13:38.759068+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGJWP3WVOZVX","created_at":"2026-07-05T03:13:38.759068+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGJWP3WVOZVXRIGK","created_at":"2026-07-05T03:13:38.759068+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGJWP3WV","created_at":"2026-07-05T03:13:38.759068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA","json":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA.json","graph_json":"https://pith.science/api/pith-number/VGJWP3WVOZVXRIGK65Q6EZQZAA/graph.json","events_json":"https://pith.science/api/pith-number/VGJWP3WVOZVXRIGK65Q6EZQZAA/events.json","paper":"https://pith.science/paper/VGJWP3WV"},"agent_actions":{"view_html":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA","download_json":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA.json","view_paper":"https://pith.science/paper/VGJWP3WV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05418&json=true","fetch_graph":"https://pith.science/api/pith-number/VGJWP3WVOZVXRIGK65Q6EZQZAA/graph.json","fetch_events":"https://pith.science/api/pith-number/VGJWP3WVOZVXRIGK65Q6EZQZAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA/action/storage_attestation","attest_author":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA/action/author_attestation","sign_citation":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA/action/citation_signature","submit_replication":"https://pith.science/pith/VGJWP3WVOZVXRIGK65Q6EZQZAA/action/replication_record"}},"created_at":"2026-07-05T03:13:38.759068+00:00","updated_at":"2026-07-05T03:13:38.759068+00:00"}