{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ILGAJQHUIXQUODLRB62FEMGGWK","short_pith_number":"pith:ILGAJQHU","schema_version":"1.0","canonical_sha256":"42cc04c0f445e1470d710fb45230c6b2a82d697af5cb3267da0d6082adf75a6c","source":{"kind":"arxiv","id":"2105.04752","version":1},"attestation_state":"computed","paper":{"title":"Differentiable Signal Processing With Black-Box Audio Effects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Marco A. Mart\\'inez Ram\\'irez, Nicholas J. Bryan, Oliver Wang, Paris Smaragdis","submitted_at":"2021-05-11T02:20:22Z","abstract_excerpt":"We present a data-driven approach to automate audio signal processing by incorporating stateful third-party, audio effects as layers within a deep neural network. We then train a deep encoder to analyze input audio and control effect parameters to perform the desired signal manipulation, requiring only input-target paired audio data as supervision. To train our network with non-differentiable black-box effects layers, we use a fast, parallel stochastic gradient approximation scheme within a standard auto differentiation graph, yielding efficient end-to-end backpropagation. We demonstrate the p"},"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":"2105.04752","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-05-11T02:20:22Z","cross_cats_sorted":["cs.LG","cs.SD","eess.SP"],"title_canon_sha256":"9863c11b2df02783bbad223444c0c2d776349c71b064c111ade69e46ab097ac0","abstract_canon_sha256":"fba158dce66d8cc4a3849d886dd83d1a57f6cbbddd47ccbc4ff450a6dbb68e71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:23.805034Z","signature_b64":"PvCDhDohGSnfSA2P1FK+gQZ2ksTum9fR8u/KzgD7ZFecGm+q72yuzdYwbYjZ1Gor8+XvYsQW7sjL6+Jh+eLdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42cc04c0f445e1470d710fb45230c6b2a82d697af5cb3267da0d6082adf75a6c","last_reissued_at":"2026-07-05T02:39:23.804593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:23.804593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Signal Processing With Black-Box Audio Effects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Marco A. Mart\\'inez Ram\\'irez, Nicholas J. Bryan, Oliver Wang, Paris Smaragdis","submitted_at":"2021-05-11T02:20:22Z","abstract_excerpt":"We present a data-driven approach to automate audio signal processing by incorporating stateful third-party, audio effects as layers within a deep neural network. We then train a deep encoder to analyze input audio and control effect parameters to perform the desired signal manipulation, requiring only input-target paired audio data as supervision. To train our network with non-differentiable black-box effects layers, we use a fast, parallel stochastic gradient approximation scheme within a standard auto differentiation graph, yielding efficient end-to-end backpropagation. We demonstrate the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04752","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/2105.04752/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":"2105.04752","created_at":"2026-07-05T02:39:23.804650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04752v1","created_at":"2026-07-05T02:39:23.804650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04752","created_at":"2026-07-05T02:39:23.804650+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILGAJQHUIXQU","created_at":"2026-07-05T02:39:23.804650+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILGAJQHUIXQUODLR","created_at":"2026-07-05T02:39:23.804650+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILGAJQHU","created_at":"2026-07-05T02:39:23.804650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK","json":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK.json","graph_json":"https://pith.science/api/pith-number/ILGAJQHUIXQUODLRB62FEMGGWK/graph.json","events_json":"https://pith.science/api/pith-number/ILGAJQHUIXQUODLRB62FEMGGWK/events.json","paper":"https://pith.science/paper/ILGAJQHU"},"agent_actions":{"view_html":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK","download_json":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK.json","view_paper":"https://pith.science/paper/ILGAJQHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04752&json=true","fetch_graph":"https://pith.science/api/pith-number/ILGAJQHUIXQUODLRB62FEMGGWK/graph.json","fetch_events":"https://pith.science/api/pith-number/ILGAJQHUIXQUODLRB62FEMGGWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK/action/storage_attestation","attest_author":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK/action/author_attestation","sign_citation":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK/action/citation_signature","submit_replication":"https://pith.science/pith/ILGAJQHUIXQUODLRB62FEMGGWK/action/replication_record"}},"created_at":"2026-07-05T02:39:23.804650+00:00","updated_at":"2026-07-05T02:39:23.804650+00:00"}