{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JRRGZDMMZY5HHDQVNQYOKO2IYN","short_pith_number":"pith:JRRGZDMM","schema_version":"1.0","canonical_sha256":"4c626c8d8cce3a738e156c30e53b48c36bd4b253cc1b4cf81513899919fb0949","source":{"kind":"arxiv","id":"1809.07600","version":1},"attestation_state":"computed","paper":{"title":"MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Andres Konrad, Gino Brunner, Roger Wattenhofer, Yuyi Wang","submitted_at":"2018-09-20T13:02:30Z","abstract_excerpt":"We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating note durations and velocities. We show that MIDI-VAE can perform style transfer on symbolic music by automatically changing pitches, dynamics and instruments of a music piece from, e.g., a Classical to a Jazz style. We evaluate the efficacy of the style transfer by training separate style validation classifiers. Our model can also interpolate between short pieces of music, produce"},"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":"1809.07600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-09-20T13:02:30Z","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"39e0d4cfd6d6397bf490e6f472f23d12ecef2550e4ca85068f3f4f8fd17bcb98","abstract_canon_sha256":"1e736bfe70cdb5c0809264b8d5d29ee5e0c21e40a69f95dfd454cc5c6ad4f3eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:15.770652Z","signature_b64":"wKQzOyfzNn1FLYuSPAUBgkCxiVTr7JSdereWTzIIckinVLGDvy/6ZFlSeFO70qvpGl3x2Up+rZ91XiHbasxbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c626c8d8cce3a738e156c30e53b48c36bd4b253cc1b4cf81513899919fb0949","last_reissued_at":"2026-05-18T00:05:15.769989Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:15.769989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Andres Konrad, Gino Brunner, Roger Wattenhofer, Yuyi Wang","submitted_at":"2018-09-20T13:02:30Z","abstract_excerpt":"We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating note durations and velocities. We show that MIDI-VAE can perform style transfer on symbolic music by automatically changing pitches, dynamics and instruments of a music piece from, e.g., a Classical to a Jazz style. We evaluate the efficacy of the style transfer by training separate style validation classifiers. Our model can also interpolate between short pieces of music, produce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07600","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":"1809.07600","created_at":"2026-05-18T00:05:15.770097+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.07600v1","created_at":"2026-05-18T00:05:15.770097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07600","created_at":"2026-05-18T00:05:15.770097+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRRGZDMMZY5H","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRRGZDMMZY5HHDQV","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRRGZDMM","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.21081","citing_title":"Musical Attention Transformer: Music Generation Using a Music-Specific Attention Model","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2601.03612","citing_title":"Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN","json":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN.json","graph_json":"https://pith.science/api/pith-number/JRRGZDMMZY5HHDQVNQYOKO2IYN/graph.json","events_json":"https://pith.science/api/pith-number/JRRGZDMMZY5HHDQVNQYOKO2IYN/events.json","paper":"https://pith.science/paper/JRRGZDMM"},"agent_actions":{"view_html":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN","download_json":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN.json","view_paper":"https://pith.science/paper/JRRGZDMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.07600&json=true","fetch_graph":"https://pith.science/api/pith-number/JRRGZDMMZY5HHDQVNQYOKO2IYN/graph.json","fetch_events":"https://pith.science/api/pith-number/JRRGZDMMZY5HHDQVNQYOKO2IYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN/action/storage_attestation","attest_author":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN/action/author_attestation","sign_citation":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN/action/citation_signature","submit_replication":"https://pith.science/pith/JRRGZDMMZY5HHDQVNQYOKO2IYN/action/replication_record"}},"created_at":"2026-05-18T00:05:15.770097+00:00","updated_at":"2026-05-18T00:05:15.770097+00:00"}