{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7STPR47NR2ZJUR6W7ANTABZTVH","short_pith_number":"pith:7STPR47N","schema_version":"1.0","canonical_sha256":"fca6f8f3ed8eb29a47d6f81b300733a9e03391f50ea29206bc33b01346b35233","source":{"kind":"arxiv","id":"1906.01083","version":1},"attestation_state":"computed","paper":{"title":"MelNet: A Generative Model for Audio in the Frequency Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Mike Lewis, Sean Vasquez","submitted_at":"2019-06-04T04:58:19Z","abstract_excerpt":"Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can be more tractably modelled in two-dimensional time-frequency representations such as spectrograms. By leveraging this representational advantage, in conjunction with a highly expressive probabilistic model and a multiscale generation procedure, we design a model capable of generating high-fidelity audio samples which capture structure at timescales that time"},"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":"1906.01083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-04T04:58:19Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"891fb3dd55f6b68eb344ea450d47c43958f7cb40cb3aed7758c73fa412473ad4","abstract_canon_sha256":"805eecf76bd69bf202bd2fa19002a8ba61bd8dca3962d2ecee57418b60e683b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:17.907840Z","signature_b64":"Xi60tSyt+cxu/XoOfGtIshTQre+CoU8xd7Dkw+EylUe/vR/OGEPjd5+oRepYvrtCghUvMf+NxDdaUqwazlUHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fca6f8f3ed8eb29a47d6f81b300733a9e03391f50ea29206bc33b01346b35233","last_reissued_at":"2026-05-17T23:44:17.907126Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:17.907126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MelNet: A Generative Model for Audio in the Frequency Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Mike Lewis, Sean Vasquez","submitted_at":"2019-06-04T04:58:19Z","abstract_excerpt":"Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can be more tractably modelled in two-dimensional time-frequency representations such as spectrograms. By leveraging this representational advantage, in conjunction with a highly expressive probabilistic model and a multiscale generation procedure, we design a model capable of generating high-fidelity audio samples which capture structure at timescales that time"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01083","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":"1906.01083","created_at":"2026-05-17T23:44:17.907257+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01083v1","created_at":"2026-05-17T23:44:17.907257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01083","created_at":"2026-05-17T23:44:17.907257+00:00"},{"alias_kind":"pith_short_12","alias_value":"7STPR47NR2ZJ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7STPR47NR2ZJUR6W","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7STPR47N","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2005.00341","citing_title":"Jukebox: A Generative Model for Music","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26007","citing_title":"MARS: Sound Generation via Multi-Channel Autoregression on Spectrograms","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2009.09761","citing_title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05700","citing_title":"Optimal-Transport-Guided Functional Flow Matching for Turbulent Field Generation in Hilbert Space","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH","json":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH.json","graph_json":"https://pith.science/api/pith-number/7STPR47NR2ZJUR6W7ANTABZTVH/graph.json","events_json":"https://pith.science/api/pith-number/7STPR47NR2ZJUR6W7ANTABZTVH/events.json","paper":"https://pith.science/paper/7STPR47N"},"agent_actions":{"view_html":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH","download_json":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH.json","view_paper":"https://pith.science/paper/7STPR47N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01083&json=true","fetch_graph":"https://pith.science/api/pith-number/7STPR47NR2ZJUR6W7ANTABZTVH/graph.json","fetch_events":"https://pith.science/api/pith-number/7STPR47NR2ZJUR6W7ANTABZTVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH/action/storage_attestation","attest_author":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH/action/author_attestation","sign_citation":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH/action/citation_signature","submit_replication":"https://pith.science/pith/7STPR47NR2ZJUR6W7ANTABZTVH/action/replication_record"}},"created_at":"2026-05-17T23:44:17.907257+00:00","updated_at":"2026-05-17T23:44:17.907257+00:00"}