{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DI3DTZAML5FBSYS7NGLUTURA66","short_pith_number":"pith:DI3DTZAM","schema_version":"1.0","canonical_sha256":"1a3639e40c5f4a19625f699749d220f78bfe0f693f2b5131d99aae024744e918","source":{"kind":"arxiv","id":"2209.07140","version":1},"attestation_state":"computed","paper":{"title":"Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Gus Xia, Jingwei Zhao, Ye Wang","submitted_at":"2022-09-15T08:38:58Z","abstract_excerpt":"We propose Beat Transformer, a novel Transformer encoder architecture for joint beat and downbeat tracking. Different from previous models that track beats solely based on the spectrogram of an audio mixture, our model deals with demixed spectrograms with multiple instrument channels. This is inspired by the fact that humans perceive metrical structures from richer musical contexts, such as chord progression and instrumentation. To this end, we develop a Transformer model with both time-wise attention and instrument-wise attention to capture deep-buried metrical cues. Moreover, our model adopt"},"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":"2209.07140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-09-15T08:38:58Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"983a3b6ebd11689632334bd0c476134ea3a7a40ac1594ca3f52fefae496e01f7","abstract_canon_sha256":"bcb8e9035d6db054130d8c331eee6cb91906e24a0f7864882d91131e91885143"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:51.906580Z","signature_b64":"mTTaa3fWpx0PZtHJWTsFQUkdPKif+10DIXFMIG/qzr8l1BoLmuwnBZgXzN/sQgtXjebhsFXO8kDv9cnb7/cVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a3639e40c5f4a19625f699749d220f78bfe0f693f2b5131d99aae024744e918","last_reissued_at":"2026-07-05T04:57:51.906135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:51.906135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Gus Xia, Jingwei Zhao, Ye Wang","submitted_at":"2022-09-15T08:38:58Z","abstract_excerpt":"We propose Beat Transformer, a novel Transformer encoder architecture for joint beat and downbeat tracking. Different from previous models that track beats solely based on the spectrogram of an audio mixture, our model deals with demixed spectrograms with multiple instrument channels. This is inspired by the fact that humans perceive metrical structures from richer musical contexts, such as chord progression and instrumentation. To this end, we develop a Transformer model with both time-wise attention and instrument-wise attention to capture deep-buried metrical cues. Moreover, our model adopt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07140","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/2209.07140/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":"2209.07140","created_at":"2026-07-05T04:57:51.906198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07140v1","created_at":"2026-07-05T04:57:51.906198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07140","created_at":"2026-07-05T04:57:51.906198+00:00"},{"alias_kind":"pith_short_12","alias_value":"DI3DTZAML5FB","created_at":"2026-07-05T04:57:51.906198+00:00"},{"alias_kind":"pith_short_16","alias_value":"DI3DTZAML5FBSYS7","created_at":"2026-07-05T04:57:51.906198+00:00"},{"alias_kind":"pith_short_8","alias_value":"DI3DTZAM","created_at":"2026-07-05T04:57:51.906198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12287","citing_title":"The SMC Blind Spot: A Failure Mode Analysis of State-of-the-Art Beat Tracking","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66","json":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66.json","graph_json":"https://pith.science/api/pith-number/DI3DTZAML5FBSYS7NGLUTURA66/graph.json","events_json":"https://pith.science/api/pith-number/DI3DTZAML5FBSYS7NGLUTURA66/events.json","paper":"https://pith.science/paper/DI3DTZAM"},"agent_actions":{"view_html":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66","download_json":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66.json","view_paper":"https://pith.science/paper/DI3DTZAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07140&json=true","fetch_graph":"https://pith.science/api/pith-number/DI3DTZAML5FBSYS7NGLUTURA66/graph.json","fetch_events":"https://pith.science/api/pith-number/DI3DTZAML5FBSYS7NGLUTURA66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66/action/storage_attestation","attest_author":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66/action/author_attestation","sign_citation":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66/action/citation_signature","submit_replication":"https://pith.science/pith/DI3DTZAML5FBSYS7NGLUTURA66/action/replication_record"}},"created_at":"2026-07-05T04:57:51.906198+00:00","updated_at":"2026-07-05T04:57:51.906198+00:00"}