{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OUZFZGLHFVFCIMIVUMCFBFQZXD","short_pith_number":"pith:OUZFZGLH","schema_version":"1.0","canonical_sha256":"75325c99672d4a243115a304509619b8faf69cbcabfc2228aad88120040898af","source":{"kind":"arxiv","id":"1907.04868","version":1},"attestation_state":"computed","paper":{"title":"LakhNES: Improving multi-instrumental music generation with cross-domain pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Chris Donahue, Garrison W. Cottrell, Huanru Henry Mao, Julian McAuley, Yiting Ethan Li","submitted_at":"2019-07-10T18:00:04Z","abstract_excerpt":"We are interested in the task of generating multi-instrumental music scores. The Transformer architecture has recently shown great promise for the task of piano score generation; here we adapt it to the multi-instrumental setting. Transformers are complex, high-dimensional language models which are capable of capturing long-term structure in sequence data, but require large amounts of data to fit. Their success on piano score generation is partially explained by the large volumes of symbolic data readily available for that domain. We leverage the recently-introduced NES-MDB dataset of four-ins"},"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":"1907.04868","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2019-07-10T18:00:04Z","cross_cats_sorted":["cs.LG","cs.MM","eess.AS","stat.ML"],"title_canon_sha256":"0dada876b3fde12b734b9af9e762a69abbe5ad3bee43a67525c674931c96d269","abstract_canon_sha256":"317a2747a9e4d301cd5b4e3f0e5a49fdeced3841de7134ca3ad94509c0e402a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:54.748721Z","signature_b64":"F0I2NJrUPDoZ6ZAhrmbVL+gLkmGM4d6Jal71v+97AqdH/WUeunUQiUwJ+AbvgrBLGu2HLqKyaucm6MESTbLQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75325c99672d4a243115a304509619b8faf69cbcabfc2228aad88120040898af","last_reissued_at":"2026-05-17T23:40:54.747909Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:54.747909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LakhNES: Improving multi-instrumental music generation with cross-domain pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Chris Donahue, Garrison W. Cottrell, Huanru Henry Mao, Julian McAuley, Yiting Ethan Li","submitted_at":"2019-07-10T18:00:04Z","abstract_excerpt":"We are interested in the task of generating multi-instrumental music scores. The Transformer architecture has recently shown great promise for the task of piano score generation; here we adapt it to the multi-instrumental setting. Transformers are complex, high-dimensional language models which are capable of capturing long-term structure in sequence data, but require large amounts of data to fit. Their success on piano score generation is partially explained by the large volumes of symbolic data readily available for that domain. We leverage the recently-introduced NES-MDB dataset of four-ins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04868","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":""},"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":"1907.04868","created_at":"2026-05-17T23:40:54.748034+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04868v1","created_at":"2026-05-17T23:40:54.748034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04868","created_at":"2026-05-17T23:40:54.748034+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUZFZGLHFVFC","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUZFZGLHFVFCIMIV","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUZFZGLH","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04868","citing_title":"LakhNES: Improving multi-instrumental music generation with cross-domain pre-training","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD","json":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD.json","graph_json":"https://pith.science/api/pith-number/OUZFZGLHFVFCIMIVUMCFBFQZXD/graph.json","events_json":"https://pith.science/api/pith-number/OUZFZGLHFVFCIMIVUMCFBFQZXD/events.json","paper":"https://pith.science/paper/OUZFZGLH"},"agent_actions":{"view_html":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD","download_json":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD.json","view_paper":"https://pith.science/paper/OUZFZGLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04868&json=true","fetch_graph":"https://pith.science/api/pith-number/OUZFZGLHFVFCIMIVUMCFBFQZXD/graph.json","fetch_events":"https://pith.science/api/pith-number/OUZFZGLHFVFCIMIVUMCFBFQZXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD/action/storage_attestation","attest_author":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD/action/author_attestation","sign_citation":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD/action/citation_signature","submit_replication":"https://pith.science/pith/OUZFZGLHFVFCIMIVUMCFBFQZXD/action/replication_record"}},"created_at":"2026-05-17T23:40:54.748034+00:00","updated_at":"2026-05-17T23:40:54.748034+00:00"}