{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EGCKZ5TRHDDI2QPANBUFSTBFQN","short_pith_number":"pith:EGCKZ5TR","schema_version":"1.0","canonical_sha256":"2184acf67138c68d41e06868594c258366cbb59c8a627ede04c59a0259291e85","source":{"kind":"arxiv","id":"2004.00188","version":5},"attestation_state":"computed","paper":{"title":"Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Curtis Hawthorne, Jesse Engel, Lee Callender","submitted_at":"2020-04-01T01:24:42Z","abstract_excerpt":"We introduce the Expanded Groove MIDI dataset (E-GMD), an automatic drum transcription (ADT) dataset that contains 444 hours of audio from 43 drum kits, making it an order of magnitude larger than similar datasets, and the first with human-performed velocity annotations. We use E-GMD to optimize classifiers for use in downstream generation by predicting expressive dynamics (velocity) and show with listening tests that they produce outputs with improved perceptual quality, despite similar results on classification metrics. Via the listening tests, we argue that standard classifier metrics, such"},"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":"2004.00188","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-04-01T01:24:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7d6bb4e8859c61f61c87a72d98ba4ec7f04480fa368c4953a1c9a327c27dec5c","abstract_canon_sha256":"fd88b456504600e89cc56e275bc4d7f37d94e8f335f36be272a5b1481336fb3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:49.397228Z","signature_b64":"S9lyEIH3Bp4meWbLamcjuiQ77gv0l1bFcIlPPdRjKXrZg8SaOfJ16M6RRZPjk4Qp5A6Mfw+uAgyUNq5LFTIVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2184acf67138c68d41e06868594c258366cbb59c8a627ede04c59a0259291e85","last_reissued_at":"2026-07-05T01:55:49.396673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:49.396673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Curtis Hawthorne, Jesse Engel, Lee Callender","submitted_at":"2020-04-01T01:24:42Z","abstract_excerpt":"We introduce the Expanded Groove MIDI dataset (E-GMD), an automatic drum transcription (ADT) dataset that contains 444 hours of audio from 43 drum kits, making it an order of magnitude larger than similar datasets, and the first with human-performed velocity annotations. We use E-GMD to optimize classifiers for use in downstream generation by predicting expressive dynamics (velocity) and show with listening tests that they produce outputs with improved perceptual quality, despite similar results on classification metrics. Via the listening tests, we argue that standard classifier metrics, such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00188","kind":"arxiv","version":5},"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/2004.00188/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":"2004.00188","created_at":"2026-07-05T01:55:49.396752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.00188v5","created_at":"2026-07-05T01:55:49.396752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00188","created_at":"2026-07-05T01:55:49.396752+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGCKZ5TRHDDI","created_at":"2026-07-05T01:55:49.396752+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGCKZ5TRHDDI2QPA","created_at":"2026-07-05T01:55:49.396752+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGCKZ5TR","created_at":"2026-07-05T01:55:49.396752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14555","citing_title":"Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10281","citing_title":"Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN","json":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN.json","graph_json":"https://pith.science/api/pith-number/EGCKZ5TRHDDI2QPANBUFSTBFQN/graph.json","events_json":"https://pith.science/api/pith-number/EGCKZ5TRHDDI2QPANBUFSTBFQN/events.json","paper":"https://pith.science/paper/EGCKZ5TR"},"agent_actions":{"view_html":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN","download_json":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN.json","view_paper":"https://pith.science/paper/EGCKZ5TR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.00188&json=true","fetch_graph":"https://pith.science/api/pith-number/EGCKZ5TRHDDI2QPANBUFSTBFQN/graph.json","fetch_events":"https://pith.science/api/pith-number/EGCKZ5TRHDDI2QPANBUFSTBFQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN/action/storage_attestation","attest_author":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN/action/author_attestation","sign_citation":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN/action/citation_signature","submit_replication":"https://pith.science/pith/EGCKZ5TRHDDI2QPANBUFSTBFQN/action/replication_record"}},"created_at":"2026-07-05T01:55:49.396752+00:00","updated_at":"2026-07-05T01:55:49.396752+00:00"}