{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YQXC7D4BI46I5QFM7GQBUSWTC7","short_pith_number":"pith:YQXC7D4B","schema_version":"1.0","canonical_sha256":"c42e2f8f81473c8ec0acf9a01a4ad317d7e3e84a7d25a9827204bbf6bc9a6812","source":{"kind":"arxiv","id":"2001.04643","version":1},"attestation_state":"computed","paper":{"title":"DDSP: Differentiable Digital Signal Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Roberts, Chenjie Gu, Jesse Engel, Lamtharn Hantrakul","submitted_at":"2020-01-14T06:49:37Z","abstract_excerpt":"Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is generated and perceived. A third approach (vocoders/synthesizers) successfully incorporates strong domain knowledge of signal processing and perception, but has been less actively researched due to limited expressivity and difficulty integrating with modern auto-differentiation-based machine learning methods. In this paper, we introduce the Differentiable Digit"},"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":"2001.04643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-14T06:49:37Z","cross_cats_sorted":["cs.SD","eess.AS","eess.SP","stat.ML"],"title_canon_sha256":"769bd373611794c444c1b9e36bac1401735bd2ff80f5fabe36bd4f24b068edeb","abstract_canon_sha256":"fdf42120b7f34720ac19149a6875f3855422acf46bf00831dd785f8587dab131"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:27.805374Z","signature_b64":"6jv21HjVfQN9afoXki5g5zB8kSh7IhwbguCuduKMJe1qjEoJk3G1Lc62W8i060LFyg4U/f4YucoMEzIZ9poaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c42e2f8f81473c8ec0acf9a01a4ad317d7e3e84a7d25a9827204bbf6bc9a6812","last_reissued_at":"2026-07-05T00:33:27.804961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:27.804961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DDSP: Differentiable Digital Signal Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Roberts, Chenjie Gu, Jesse Engel, Lamtharn Hantrakul","submitted_at":"2020-01-14T06:49:37Z","abstract_excerpt":"Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is generated and perceived. A third approach (vocoders/synthesizers) successfully incorporates strong domain knowledge of signal processing and perception, but has been less actively researched due to limited expressivity and difficulty integrating with modern auto-differentiation-based machine learning methods. In this paper, we introduce the Differentiable Digit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04643","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.04643/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":"2001.04643","created_at":"2026-07-05T00:33:27.805013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.04643v1","created_at":"2026-07-05T00:33:27.805013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04643","created_at":"2026-07-05T00:33:27.805013+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQXC7D4BI46I","created_at":"2026-07-05T00:33:27.805013+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQXC7D4BI46I5QFM","created_at":"2026-07-05T00:33:27.805013+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQXC7D4B","created_at":"2026-07-05T00:33:27.805013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10868","citing_title":"When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02171","citing_title":"Go witheFlow: Real-time Emotion Driven Audio Effects Modulation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15946","citing_title":"Differentiable Acoustic Radiance Transfer","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16318","citing_title":"Learning Filters in Feedback Delay Networks from Noisy Room Impulse Responses","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2009.09761","citing_title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7","json":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7.json","graph_json":"https://pith.science/api/pith-number/YQXC7D4BI46I5QFM7GQBUSWTC7/graph.json","events_json":"https://pith.science/api/pith-number/YQXC7D4BI46I5QFM7GQBUSWTC7/events.json","paper":"https://pith.science/paper/YQXC7D4B"},"agent_actions":{"view_html":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7","download_json":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7.json","view_paper":"https://pith.science/paper/YQXC7D4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.04643&json=true","fetch_graph":"https://pith.science/api/pith-number/YQXC7D4BI46I5QFM7GQBUSWTC7/graph.json","fetch_events":"https://pith.science/api/pith-number/YQXC7D4BI46I5QFM7GQBUSWTC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7/action/storage_attestation","attest_author":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7/action/author_attestation","sign_citation":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7/action/citation_signature","submit_replication":"https://pith.science/pith/YQXC7D4BI46I5QFM7GQBUSWTC7/action/replication_record"}},"created_at":"2026-07-05T00:33:27.805013+00:00","updated_at":"2026-07-05T00:33:27.805013+00:00"}