{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SLS5ULW2TQLZCJ2SJOBWUYBHW2","short_pith_number":"pith:SLS5ULW2","schema_version":"1.0","canonical_sha256":"92e5da2eda9c179127524b836a6027b6ba8c4090544c0f234b092b371b0b5763","source":{"kind":"arxiv","id":"2410.21233","version":1},"attestation_state":"computed","paper":{"title":"ST-ITO: Controlling Audio Effects for Style Transfer with Inference-Time Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Christian J. Steinmetz, Emmanouil Benetos, Ilias Ibnyahya, Joshua D. Reiss, Marco Comunit\\`a, Shanxin Yuan, Shubhr Singh","submitted_at":"2024-10-28T17:24:37Z","abstract_excerpt":"Audio production style transfer is the task of processing an input to impart stylistic elements from a reference recording. Existing approaches often train a neural network to estimate control parameters for a set of audio effects. However, these approaches are limited in that they can only control a fixed set of effects, where the effects must be differentiable or otherwise employ specialized training techniques. In this work, we introduce ST-ITO, Style Transfer with Inference-Time Optimization, an approach that instead searches the parameter space of an audio effect chain at inference. This "},"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":"2410.21233","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-28T17:24:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5a85f589c02316f215045a1bfacd98ecb8ddc74e60be2d9b680d6965e3dcc145","abstract_canon_sha256":"ea0e9a3e51a1a4ea849e21c583eec5c35856d4701777d515bdcd111d1865f060"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:17.229369Z","signature_b64":"v70ZULY9YkkPy5LVFyh+2ajFPdx51hUhdy3Y1AiRl8ltraZ6sUOZrJD8Vzv/WbEiuZKEZvKS9yAvP/zFbIzHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e5da2eda9c179127524b836a6027b6ba8c4090544c0f234b092b371b0b5763","last_reissued_at":"2026-07-05T09:27:17.228883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:17.228883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ST-ITO: Controlling Audio Effects for Style Transfer with Inference-Time Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Christian J. Steinmetz, Emmanouil Benetos, Ilias Ibnyahya, Joshua D. Reiss, Marco Comunit\\`a, Shanxin Yuan, Shubhr Singh","submitted_at":"2024-10-28T17:24:37Z","abstract_excerpt":"Audio production style transfer is the task of processing an input to impart stylistic elements from a reference recording. Existing approaches often train a neural network to estimate control parameters for a set of audio effects. However, these approaches are limited in that they can only control a fixed set of effects, where the effects must be differentiable or otherwise employ specialized training techniques. In this work, we introduce ST-ITO, Style Transfer with Inference-Time Optimization, an approach that instead searches the parameter space of an audio effect chain at inference. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21233","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/2410.21233/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":"2410.21233","created_at":"2026-07-05T09:27:17.228943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21233v1","created_at":"2026-07-05T09:27:17.228943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21233","created_at":"2026-07-05T09:27:17.228943+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLS5ULW2TQLZ","created_at":"2026-07-05T09:27:17.228943+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLS5ULW2TQLZCJ2S","created_at":"2026-07-05T09:27:17.228943+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLS5ULW2","created_at":"2026-07-05T09:27:17.228943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08286","citing_title":"FXplorer: A Map-Based Interface for Exploratory Audio Effect Design","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2","json":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2.json","graph_json":"https://pith.science/api/pith-number/SLS5ULW2TQLZCJ2SJOBWUYBHW2/graph.json","events_json":"https://pith.science/api/pith-number/SLS5ULW2TQLZCJ2SJOBWUYBHW2/events.json","paper":"https://pith.science/paper/SLS5ULW2"},"agent_actions":{"view_html":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2","download_json":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2.json","view_paper":"https://pith.science/paper/SLS5ULW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21233&json=true","fetch_graph":"https://pith.science/api/pith-number/SLS5ULW2TQLZCJ2SJOBWUYBHW2/graph.json","fetch_events":"https://pith.science/api/pith-number/SLS5ULW2TQLZCJ2SJOBWUYBHW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2/action/storage_attestation","attest_author":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2/action/author_attestation","sign_citation":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2/action/citation_signature","submit_replication":"https://pith.science/pith/SLS5ULW2TQLZCJ2SJOBWUYBHW2/action/replication_record"}},"created_at":"2026-07-05T09:27:17.228943+00:00","updated_at":"2026-07-05T09:27:17.228943+00:00"}