{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DPWIHBYXRVOJ3BC7M4XGO442GB","short_pith_number":"pith:DPWIHBYX","schema_version":"1.0","canonical_sha256":"1bec8387178d5c9d845f672e67739a305e6180d88e8e0de25d57111fcedc8922","source":{"kind":"arxiv","id":"2111.03017","version":4},"attestation_state":"computed","paper":{"title":"MT3: Multi-Task Multitrack Music Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Curtis Hawthorne, Ethan Manilow, Ian Simon, Jesse Engel, Josh Gardner","submitted_at":"2021-11-04T17:19:39Z","abstract_excerpt":"Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding. Unlike Automatic Speech Recognition (ASR), which typically focuses on the words of a single speaker, AMT often requires transcribing multiple instruments simultaneously, all while preserving fine-scale pitch and timing information. Further, many AMT datasets are \"low-resource\", as even expert musicians find music transcription difficult and time-consuming. Thus, prior work has focused on task-specific architectures, tailored to the individual instruments of eac"},"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":"2111.03017","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-11-04T17:19:39Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"9f343311a170ef8517b292a139ea983726df4de24b0a2c5c424b1c77d37988b6","abstract_canon_sha256":"8fd0cf43ec0c253d47bcb300640c091994dd705ead8dfe3e94e3d4a51781d4f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:14.235511Z","signature_b64":"ctQt887A9yPBup6eOFj2bCo4Kx9EVFiZB1mtBogcWv+JacGMfPmrUwAHuY1Or34Ki49A0JGnfh7SQ1Cv9t5GAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bec8387178d5c9d845f672e67739a305e6180d88e8e0de25d57111fcedc8922","last_reissued_at":"2026-07-05T04:05:14.235047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:14.235047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MT3: Multi-Task Multitrack Music Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Curtis Hawthorne, Ethan Manilow, Ian Simon, Jesse Engel, Josh Gardner","submitted_at":"2021-11-04T17:19:39Z","abstract_excerpt":"Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding. Unlike Automatic Speech Recognition (ASR), which typically focuses on the words of a single speaker, AMT often requires transcribing multiple instruments simultaneously, all while preserving fine-scale pitch and timing information. Further, many AMT datasets are \"low-resource\", as even expert musicians find music transcription difficult and time-consuming. Thus, prior work has focused on task-specific architectures, tailored to the individual instruments of eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03017","kind":"arxiv","version":4},"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/2111.03017/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":"2111.03017","created_at":"2026-07-05T04:05:14.235099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.03017v4","created_at":"2026-07-05T04:05:14.235099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03017","created_at":"2026-07-05T04:05:14.235099+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPWIHBYXRVOJ","created_at":"2026-07-05T04:05:14.235099+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPWIHBYXRVOJ3BC7","created_at":"2026-07-05T04:05:14.235099+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPWIHBYX","created_at":"2026-07-05T04:05:14.235099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08756","citing_title":"MulTTiPop: A Multitrack Transcription Dataset for Pop Music","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24193","citing_title":"Music Transcription with (Almost) No Supervision","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24291","citing_title":"Rubato: Transcribing Piano Music with Timestamps","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30613","citing_title":"Sequential Planning via Anchored Robotic Keypoints","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14555","citing_title":"Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12135","citing_title":"STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20719","citing_title":"ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB","json":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB.json","graph_json":"https://pith.science/api/pith-number/DPWIHBYXRVOJ3BC7M4XGO442GB/graph.json","events_json":"https://pith.science/api/pith-number/DPWIHBYXRVOJ3BC7M4XGO442GB/events.json","paper":"https://pith.science/paper/DPWIHBYX"},"agent_actions":{"view_html":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB","download_json":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB.json","view_paper":"https://pith.science/paper/DPWIHBYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.03017&json=true","fetch_graph":"https://pith.science/api/pith-number/DPWIHBYXRVOJ3BC7M4XGO442GB/graph.json","fetch_events":"https://pith.science/api/pith-number/DPWIHBYXRVOJ3BC7M4XGO442GB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB/action/storage_attestation","attest_author":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB/action/author_attestation","sign_citation":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB/action/citation_signature","submit_replication":"https://pith.science/pith/DPWIHBYXRVOJ3BC7M4XGO442GB/action/replication_record"}},"created_at":"2026-07-05T04:05:14.235099+00:00","updated_at":"2026-07-05T04:05:14.235099+00:00"}