{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:G27XBONN4RPT4C3ZFKLOI7T2N2","short_pith_number":"pith:G27XBONN","schema_version":"1.0","canonical_sha256":"36bf70b9ade45f3e0b792a96e47e7a6e9475b0ccea21612b1d45fcdb9b97b770","source":{"kind":"arxiv","id":"1806.10474","version":1},"attestation_state":"computed","paper":{"title":"The challenge of realistic music generation: modelling raw audio at scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"A\\\"aron van den Oord, Karen Simonyan, Sander Dieleman","submitted_at":"2018-06-26T16:48:59Z","abstract_excerpt":"Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular performance. But these nuances are very important for our perception of musicality and realism, so in this work we embark on modelling music in the raw audio domain. It has been shown that autoregressive models excel at generating raw audio waveforms of speech, but when applied to music, we find them biased towards capturing local signal structure at the ex"},"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":"1806.10474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-06-26T16:48:59Z","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"a5d0ab8d3d34a09d1ab1f01fd5e5872793008da19c17929a9ec540e7fb2ea0ed","abstract_canon_sha256":"9dcab961467bae05b7fc1e0adfa692cb00f35b9457d1fba91050fc8c7a6538c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:12.286890Z","signature_b64":"2Tc8aW7JbpwRBCe+2Iq4hfMHmCHYfKjO+lHEjbT+BLJOgigHRl1Mr9PQbKw5ozVkp4ePuDzIhaOdEJUJ3aJMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36bf70b9ade45f3e0b792a96e47e7a6e9475b0ccea21612b1d45fcdb9b97b770","last_reissued_at":"2026-05-18T00:12:12.286149Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:12.286149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The challenge of realistic music generation: modelling raw audio at scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"A\\\"aron van den Oord, Karen Simonyan, Sander Dieleman","submitted_at":"2018-06-26T16:48:59Z","abstract_excerpt":"Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular performance. But these nuances are very important for our perception of musicality and realism, so in this work we embark on modelling music in the raw audio domain. It has been shown that autoregressive models excel at generating raw audio waveforms of speech, but when applied to music, we find them biased towards capturing local signal structure at the ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.10474","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":"1806.10474","created_at":"2026-05-18T00:12:12.286250+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.10474v1","created_at":"2026-05-18T00:12:12.286250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.10474","created_at":"2026-05-18T00:12:12.286250+00:00"},{"alias_kind":"pith_short_12","alias_value":"G27XBONN4RPT","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"G27XBONN4RPT4C3Z","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"G27XBONN","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06286","citing_title":"Autoencoding sensory substitution","ref_index":198,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2","json":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2.json","graph_json":"https://pith.science/api/pith-number/G27XBONN4RPT4C3ZFKLOI7T2N2/graph.json","events_json":"https://pith.science/api/pith-number/G27XBONN4RPT4C3ZFKLOI7T2N2/events.json","paper":"https://pith.science/paper/G27XBONN"},"agent_actions":{"view_html":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2","download_json":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2.json","view_paper":"https://pith.science/paper/G27XBONN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.10474&json=true","fetch_graph":"https://pith.science/api/pith-number/G27XBONN4RPT4C3ZFKLOI7T2N2/graph.json","fetch_events":"https://pith.science/api/pith-number/G27XBONN4RPT4C3ZFKLOI7T2N2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2/action/storage_attestation","attest_author":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2/action/author_attestation","sign_citation":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2/action/citation_signature","submit_replication":"https://pith.science/pith/G27XBONN4RPT4C3ZFKLOI7T2N2/action/replication_record"}},"created_at":"2026-05-18T00:12:12.286250+00:00","updated_at":"2026-05-18T00:12:12.286250+00:00"}