{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SQPDOUYCT6P4I4T6WPIRYURF7S","short_pith_number":"pith:SQPDOUYC","schema_version":"1.0","canonical_sha256":"941e3753029f9fc4727eb3d11c5225fc9b74e2daff8ef12c2a6eae0995b9022a","source":{"kind":"arxiv","id":"1611.09827","version":2},"attestation_state":"computed","paper":{"title":"Learning Features of Music from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"stat.ML","authors_text":"John Thickstun, Sham Kakade, Zaid Harchaoui","submitted_at":"2016-11-29T20:26:00Z","abstract_excerpt":"This paper introduces a new large-scale music dataset, MusicNet, to serve as a source of supervision and evaluation of machine learning methods for music research. MusicNet consists of hundreds of freely-licensed classical music recordings by 10 composers, written for 11 instruments, together with instrument/note annotations resulting in over 1 million temporal labels on 34 hours of chamber music performances under various studio and microphone conditions.\n  The paper defines a multi-label classification task to predict notes in musical recordings, along with an evaluation protocol, and benchm"},"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":"1611.09827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-29T20:26:00Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"0c781ce09a27b1cf38d597b66a52ed2bb218195f4f048db26f99466939f98773","abstract_canon_sha256":"e571ec215548381229a9ff8a98bef06acddc83bbb20677243e697f3a2c859c97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:55.317146Z","signature_b64":"RhJgb5O0N4fgxbRrrff5OI6mpEaY79TiXXQR0GqqcE47pPB9QqPaxd+m+SLfNDW6VQThS5SZ/pC2M5dDkqQhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"941e3753029f9fc4727eb3d11c5225fc9b74e2daff8ef12c2a6eae0995b9022a","last_reissued_at":"2026-05-18T00:46:55.316560Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:55.316560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Features of Music from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"stat.ML","authors_text":"John Thickstun, Sham Kakade, Zaid Harchaoui","submitted_at":"2016-11-29T20:26:00Z","abstract_excerpt":"This paper introduces a new large-scale music dataset, MusicNet, to serve as a source of supervision and evaluation of machine learning methods for music research. MusicNet consists of hundreds of freely-licensed classical music recordings by 10 composers, written for 11 instruments, together with instrument/note annotations resulting in over 1 million temporal labels on 34 hours of chamber music performances under various studio and microphone conditions.\n  The paper defines a multi-label classification task to predict notes in musical recordings, along with an evaluation protocol, and benchm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09827","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":""},"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":"1611.09827","created_at":"2026-05-18T00:46:55.316661+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.09827v2","created_at":"2026-05-18T00:46:55.316661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09827","created_at":"2026-05-18T00:46:55.316661+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQPDOUYCT6P4","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQPDOUYCT6P4I4T6","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQPDOUYC","created_at":"2026-05-18T12:30:44.179134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19101","citing_title":"Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S","json":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S.json","graph_json":"https://pith.science/api/pith-number/SQPDOUYCT6P4I4T6WPIRYURF7S/graph.json","events_json":"https://pith.science/api/pith-number/SQPDOUYCT6P4I4T6WPIRYURF7S/events.json","paper":"https://pith.science/paper/SQPDOUYC"},"agent_actions":{"view_html":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S","download_json":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S.json","view_paper":"https://pith.science/paper/SQPDOUYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.09827&json=true","fetch_graph":"https://pith.science/api/pith-number/SQPDOUYCT6P4I4T6WPIRYURF7S/graph.json","fetch_events":"https://pith.science/api/pith-number/SQPDOUYCT6P4I4T6WPIRYURF7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S/action/storage_attestation","attest_author":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S/action/author_attestation","sign_citation":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S/action/citation_signature","submit_replication":"https://pith.science/pith/SQPDOUYCT6P4I4T6WPIRYURF7S/action/replication_record"}},"created_at":"2026-05-18T00:46:55.316661+00:00","updated_at":"2026-05-18T00:46:55.316661+00:00"}