{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5UQU6FN66BDDLRHFIZVVV4GOXU","short_pith_number":"pith:5UQU6FN6","schema_version":"1.0","canonical_sha256":"ed214f15bef04635c4e5466b5af0cebd2724f157e5a0240132f51406db5f18e3","source":{"kind":"arxiv","id":"2009.00713","version":2},"attestation_state":"computed","paper":{"title":"WaveGrad: Estimating Gradients for Waveform Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Heiga Zen, Mohammad Norouzi, Nanxin Chen, Ron J. Weiss, William Chan, Yu Zhang","submitted_at":"2020-09-02T17:44:10Z","abstract_excerpt":"This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian white noise signal and iteratively refines the signal via a gradient-based sampler conditioned on the mel-spectrogram. WaveGrad offers a natural way to trade inference speed for sample quality by adjusting the number of refinement steps, and bridges the gap between non-autoregressive and autoregressive models in terms of audio quality. We find that it can genera"},"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":"2009.00713","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-09-02T17:44:10Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"c19a14d1a52173a30556efe1abc52d45a2ef8f0f5a44717b3435750c023681c8","abstract_canon_sha256":"f914bd5dfa19c40d11b51e1aabb2a8ebc00c124779632887eedeef8f6cf5174d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:33.421062Z","signature_b64":"6GUY79cTlzWHvffINNxnSHYLN56/xoylPFnX4HDeBMnac1NxZz0GeyxZR0n6JHC97g3w1aAWriY8IsHH2LS4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed214f15bef04635c4e5466b5af0cebd2724f157e5a0240132f51406db5f18e3","last_reissued_at":"2026-07-05T01:41:33.420593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:33.420593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WaveGrad: Estimating Gradients for Waveform Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Heiga Zen, Mohammad Norouzi, Nanxin Chen, Ron J. Weiss, William Chan, Yu Zhang","submitted_at":"2020-09-02T17:44:10Z","abstract_excerpt":"This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian white noise signal and iteratively refines the signal via a gradient-based sampler conditioned on the mel-spectrogram. WaveGrad offers a natural way to trade inference speed for sample quality by adjusting the number of refinement steps, and bridges the gap between non-autoregressive and autoregressive models in terms of audio quality. We find that it can genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.00713","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.00713/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2009.00713","created_at":"2026-07-05T01:41:33.420651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.00713v2","created_at":"2026-07-05T01:41:33.420651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.00713","created_at":"2026-07-05T01:41:33.420651+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UQU6FN66BDD","created_at":"2026-07-05T01:41:33.420651+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UQU6FN66BDDLRHF","created_at":"2026-07-05T01:41:33.420651+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UQU6FN6","created_at":"2026-07-05T01:41:33.420651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27696","citing_title":"Class-frequency Guided Noise Schedule for Diffusion Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2010.02502","citing_title":"Denoising Diffusion Implicit Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2011.13456","citing_title":"Score-Based Generative Modeling through Stochastic Differential Equations","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19261","citing_title":"Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2009.09761","citing_title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14988","citing_title":"DreamFusion: Text-to-3D using 2D Diffusion","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU","json":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU.json","graph_json":"https://pith.science/api/pith-number/5UQU6FN66BDDLRHFIZVVV4GOXU/graph.json","events_json":"https://pith.science/api/pith-number/5UQU6FN66BDDLRHFIZVVV4GOXU/events.json","paper":"https://pith.science/paper/5UQU6FN6"},"agent_actions":{"view_html":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU","download_json":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU.json","view_paper":"https://pith.science/paper/5UQU6FN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.00713&json=true","fetch_graph":"https://pith.science/api/pith-number/5UQU6FN66BDDLRHFIZVVV4GOXU/graph.json","fetch_events":"https://pith.science/api/pith-number/5UQU6FN66BDDLRHFIZVVV4GOXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU/action/storage_attestation","attest_author":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU/action/author_attestation","sign_citation":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU/action/citation_signature","submit_replication":"https://pith.science/pith/5UQU6FN66BDDLRHFIZVVV4GOXU/action/replication_record"}},"created_at":"2026-07-05T01:41:33.420651+00:00","updated_at":"2026-07-05T01:41:33.420651+00:00"}