{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JVSIFUXWZYDNA4OU76ENV4GGNH","short_pith_number":"pith:JVSIFUXW","schema_version":"1.0","canonical_sha256":"4d6482d2f6ce06d071d4ff88daf0c669f13cefec16971d3e590a5d7fbb8c0c2c","source":{"kind":"arxiv","id":"2309.02612","version":2},"attestation_state":"computed","paper":{"title":"Music Source Separation with Band-Split RoPE Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ju-Chiang Wang, Qiuqiang Kong, Wei-Tsung Lu, Yun-Ning Hung","submitted_at":"2023-09-05T23:11:50Z","abstract_excerpt":"Music source separation (MSS) aims to separate a music recording into multiple musically distinct stems, such as vocals, bass, drums, and more. Recently, deep learning approaches such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been used, but the improvement is still limited. In this paper, we propose a novel frequency-domain approach based on a Band-Split RoPE Transformer (called BS-RoFormer). BS-RoFormer relies on a band-split module to project the input complex spectrogram into subband-level representations, and then arranges a stack of hierarchical Tra"},"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":"2309.02612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-05T23:11:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"724dd7c6e5199cbd3582fb729944d6c52f67c76d1461be9197e4840b82ed9eb6","abstract_canon_sha256":"c750323e07c6e8cfd295b08647a3866dbe46820f32d146ac8d81df17246bf00f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:26.390027Z","signature_b64":"1UfJnHqVCtjUisK/j+2J2KF3kYqRmA+/DO1bGpHfdewZYS1Ap+Dj35j6UhYMoj2PjkeNhHhxRp3/KGzqsmevAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d6482d2f6ce06d071d4ff88daf0c669f13cefec16971d3e590a5d7fbb8c0c2c","last_reissued_at":"2026-07-05T06:49:26.389544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:26.389544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Music Source Separation with Band-Split RoPE Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ju-Chiang Wang, Qiuqiang Kong, Wei-Tsung Lu, Yun-Ning Hung","submitted_at":"2023-09-05T23:11:50Z","abstract_excerpt":"Music source separation (MSS) aims to separate a music recording into multiple musically distinct stems, such as vocals, bass, drums, and more. Recently, deep learning approaches such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been used, but the improvement is still limited. In this paper, we propose a novel frequency-domain approach based on a Band-Split RoPE Transformer (called BS-RoFormer). BS-RoFormer relies on a band-split module to project the input complex spectrogram into subband-level representations, and then arranges a stack of hierarchical Tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02612","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/2309.02612/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":"2309.02612","created_at":"2026-07-05T06:49:26.389601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02612v2","created_at":"2026-07-05T06:49:26.389601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02612","created_at":"2026-07-05T06:49:26.389601+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVSIFUXWZYDN","created_at":"2026-07-05T06:49:26.389601+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVSIFUXWZYDNA4OU","created_at":"2026-07-05T06:49:26.389601+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVSIFUXW","created_at":"2026-07-05T06:49:26.389601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14765","citing_title":"Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06685","citing_title":"An audio-to-analysis pipeline with certified transcription for information-theoretic profiling of the piano repertoire","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH","json":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH.json","graph_json":"https://pith.science/api/pith-number/JVSIFUXWZYDNA4OU76ENV4GGNH/graph.json","events_json":"https://pith.science/api/pith-number/JVSIFUXWZYDNA4OU76ENV4GGNH/events.json","paper":"https://pith.science/paper/JVSIFUXW"},"agent_actions":{"view_html":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH","download_json":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH.json","view_paper":"https://pith.science/paper/JVSIFUXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02612&json=true","fetch_graph":"https://pith.science/api/pith-number/JVSIFUXWZYDNA4OU76ENV4GGNH/graph.json","fetch_events":"https://pith.science/api/pith-number/JVSIFUXWZYDNA4OU76ENV4GGNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH/action/storage_attestation","attest_author":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH/action/author_attestation","sign_citation":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH/action/citation_signature","submit_replication":"https://pith.science/pith/JVSIFUXWZYDNA4OU76ENV4GGNH/action/replication_record"}},"created_at":"2026-07-05T06:49:26.389601+00:00","updated_at":"2026-07-05T06:49:26.389601+00:00"}