{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WKZR3WBNTAQYDFV2DC4QR7OV74","short_pith_number":"pith:WKZR3WBN","schema_version":"1.0","canonical_sha256":"b2b31dd82d98218196ba18b908fdd5ff04d39c11bad67738762f9fcd2167e77c","source":{"kind":"arxiv","id":"1704.01279","version":1},"attestation_state":"computed","paper":{"title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.LG","authors_text":"Adam Roberts, Cinjon Resnick, Douglas Eck, Jesse Engel, Karen Simonyan, Mohammad Norouzi, Sander Dieleman","submitted_at":"2017-04-05T06:34:22Z","abstract_excerpt":"Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets. In this paper, we offer contributions in both these areas to enable similar progress in audio modeling. First, we detail a powerful new WaveNet-style autoencoder model that conditions an autoregressive decoder on temporal codes learned from the raw audio waveform. Second, we introduce NSynth, a large-scale and high-quality dataset of musical notes that is an order of magnitude larger than comparable public datasets. Using NSynth, we demonstrate improved qual"},"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":"1704.01279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-05T06:34:22Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"644e9149b7d3761d5cbda0d36e68b63ae034617e355270d76d92150269e95440","abstract_canon_sha256":"3562cf8ba6841e5ebbad118f081b4f444e9d3ad168a2dde492e591b5d036d75b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:58.572334Z","signature_b64":"wXX6C02RBlzx0IBmS88/nZSWkxiYCS3W+K2NGAmqItbmC96z85XyDaBvz96qdobt05jBpZS2NAupYubFNLHrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b31dd82d98218196ba18b908fdd5ff04d39c11bad67738762f9fcd2167e77c","last_reissued_at":"2026-05-18T00:46:58.571855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:58.571855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.LG","authors_text":"Adam Roberts, Cinjon Resnick, Douglas Eck, Jesse Engel, Karen Simonyan, Mohammad Norouzi, Sander Dieleman","submitted_at":"2017-04-05T06:34:22Z","abstract_excerpt":"Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets. In this paper, we offer contributions in both these areas to enable similar progress in audio modeling. First, we detail a powerful new WaveNet-style autoencoder model that conditions an autoregressive decoder on temporal codes learned from the raw audio waveform. Second, we introduce NSynth, a large-scale and high-quality dataset of musical notes that is an order of magnitude larger than comparable public datasets. Using NSynth, we demonstrate improved qual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01279","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":"1704.01279","created_at":"2026-05-18T00:46:58.571927+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.01279v1","created_at":"2026-05-18T00:46:58.571927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01279","created_at":"2026-05-18T00:46:58.571927+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKZR3WBNTAQY","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKZR3WBNTAQYDFV2","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKZR3WBN","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09972","citing_title":"Classical Music Prediction and Composition by means of Variational Autoencoders","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06286","citing_title":"Autoencoding sensory substitution","ref_index":197,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74","json":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74.json","graph_json":"https://pith.science/api/pith-number/WKZR3WBNTAQYDFV2DC4QR7OV74/graph.json","events_json":"https://pith.science/api/pith-number/WKZR3WBNTAQYDFV2DC4QR7OV74/events.json","paper":"https://pith.science/paper/WKZR3WBN"},"agent_actions":{"view_html":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74","download_json":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74.json","view_paper":"https://pith.science/paper/WKZR3WBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.01279&json=true","fetch_graph":"https://pith.science/api/pith-number/WKZR3WBNTAQYDFV2DC4QR7OV74/graph.json","fetch_events":"https://pith.science/api/pith-number/WKZR3WBNTAQYDFV2DC4QR7OV74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74/action/storage_attestation","attest_author":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74/action/author_attestation","sign_citation":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74/action/citation_signature","submit_replication":"https://pith.science/pith/WKZR3WBNTAQYDFV2DC4QR7OV74/action/replication_record"}},"created_at":"2026-05-18T00:46:58.571927+00:00","updated_at":"2026-05-18T00:46:58.571927+00:00"}