{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I37FSKMLHZXWLKS5X7T2ZECODY","short_pith_number":"pith:I37FSKML","schema_version":"1.0","canonical_sha256":"46fe59298b3e6f65aa5dbfe7ac904e1e34d4f62eb011fccd228208621d6eddf1","source":{"kind":"arxiv","id":"2310.01809","version":1},"attestation_state":"computed","paper":{"title":"Mel-Band RoFormer for Music Source Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ju-Chiang Wang, Minz Won, Wei-Tsung Lu","submitted_at":"2023-10-03T05:53:23Z","abstract_excerpt":"Recently, multi-band spectrogram-based approaches such as Band-Split RNN (BSRNN) have demonstrated promising results for music source separation. In our recent work, we introduce the BS-RoFormer model which inherits the idea of band-split scheme in BSRNN at the front-end, and then uses the hierarchical Transformer with Rotary Position Embedding (RoPE) to model the inner-band and inter-band sequences for multi-band mask estimation. This model has achieved state-of-the-art performance, but the band-split scheme is defined empirically, without analytic supports from the literature. In this paper,"},"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":"2310.01809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-03T05:53:23Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c7d35d544273f6b5110d34a588b750251e29c6dffdbac45a77ecf0916fd172da","abstract_canon_sha256":"102f291c288dcc0852afab9b08b2f16b22056fb5a8ff0e0ac8fcd2e6e1f7026b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:46.287221Z","signature_b64":"M1Xv/y5jpt54Qem09SUfHOTYKPbopn4sZOX4rpoTUQRl3O13xD6lk3Tgs4cfkxK4/lsRCDVRCyS+/nf6MIrtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46fe59298b3e6f65aa5dbfe7ac904e1e34d4f62eb011fccd228208621d6eddf1","last_reissued_at":"2026-07-05T06:56:46.286623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:46.286623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mel-Band RoFormer for Music Source Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ju-Chiang Wang, Minz Won, Wei-Tsung Lu","submitted_at":"2023-10-03T05:53:23Z","abstract_excerpt":"Recently, multi-band spectrogram-based approaches such as Band-Split RNN (BSRNN) have demonstrated promising results for music source separation. In our recent work, we introduce the BS-RoFormer model which inherits the idea of band-split scheme in BSRNN at the front-end, and then uses the hierarchical Transformer with Rotary Position Embedding (RoPE) to model the inner-band and inter-band sequences for multi-band mask estimation. This model has achieved state-of-the-art performance, but the band-split scheme is defined empirically, without analytic supports from the literature. In this paper,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01809","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/2310.01809/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":"2310.01809","created_at":"2026-07-05T06:56:46.286697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01809v1","created_at":"2026-07-05T06:56:46.286697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01809","created_at":"2026-07-05T06:56:46.286697+00:00"},{"alias_kind":"pith_short_12","alias_value":"I37FSKMLHZXW","created_at":"2026-07-05T06:56:46.286697+00:00"},{"alias_kind":"pith_short_16","alias_value":"I37FSKMLHZXWLKS5","created_at":"2026-07-05T06:56:46.286697+00:00"},{"alias_kind":"pith_short_8","alias_value":"I37FSKML","created_at":"2026-07-05T06:56:46.286697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09098","citing_title":"HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio Synthesis","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21538","citing_title":"Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14765","citing_title":"Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21538","citing_title":"Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15831","citing_title":"Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22029","citing_title":"MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24589","citing_title":"YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY","json":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY.json","graph_json":"https://pith.science/api/pith-number/I37FSKMLHZXWLKS5X7T2ZECODY/graph.json","events_json":"https://pith.science/api/pith-number/I37FSKMLHZXWLKS5X7T2ZECODY/events.json","paper":"https://pith.science/paper/I37FSKML"},"agent_actions":{"view_html":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY","download_json":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY.json","view_paper":"https://pith.science/paper/I37FSKML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01809&json=true","fetch_graph":"https://pith.science/api/pith-number/I37FSKMLHZXWLKS5X7T2ZECODY/graph.json","fetch_events":"https://pith.science/api/pith-number/I37FSKMLHZXWLKS5X7T2ZECODY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY/action/storage_attestation","attest_author":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY/action/author_attestation","sign_citation":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY/action/citation_signature","submit_replication":"https://pith.science/pith/I37FSKMLHZXWLKS5X7T2ZECODY/action/replication_record"}},"created_at":"2026-07-05T06:56:46.286697+00:00","updated_at":"2026-07-05T06:56:46.286697+00:00"}