{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XQ3PF2UGOZQWY5BZ5QPCR6YIYP","short_pith_number":"pith:XQ3PF2UG","schema_version":"1.0","canonical_sha256":"bc36f2ea8676616c7439ec1e28fb08c3fc9cb7cd1b3bd1e2586182bb7d1c350e","source":{"kind":"arxiv","id":"2406.01049","version":2},"attestation_state":"computed","paper":{"title":"Searching For Music Mixing Graphs: A Pruning Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Giorgio Fabbro, Kyogu Lee, Marco A. Mart\\'inez-Ram\\'irez, Stefan Uhlich, Sungho Lee, Wei-Hsiang Liao, Yuki Mitsufuji","submitted_at":"2024-06-03T06:56:34Z","abstract_excerpt":"Music mixing is compositional -- experts combine multiple audio processors to achieve a cohesive mix from dry source tracks. We propose a method to reverse engineer this process from the input and output audio. First, we create a mixing console that applies all available processors to every chain. Then, after the initial console parameter optimization, we alternate between removing redundant processors and fine-tuning. We achieve this through differentiable implementation of both processors and pruning. Consequently, we find a sparse mixing graph that achieves nearly identical matching quality"},"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":"2406.01049","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-03T06:56:34Z","cross_cats_sorted":[],"title_canon_sha256":"07d75c1a80b76929896deb12e9900c8cdf9d39fe75abc376d500774cc8db7329","abstract_canon_sha256":"55ff8016ccb199d578d7600735490351aa472a6a714cc737aacc8e28e01fa29c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:33.623276Z","signature_b64":"HtJn1iWRXwOGbfgICa6gS2h3yEYNxhEbgd6d4q59fcjwJKqI2sTTc3JANT94lDRAB6c19qs24OzWfppOmRMoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc36f2ea8676616c7439ec1e28fb08c3fc9cb7cd1b3bd1e2586182bb7d1c350e","last_reissued_at":"2026-07-05T08:52:33.622816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:33.622816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Searching For Music Mixing Graphs: A Pruning Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Giorgio Fabbro, Kyogu Lee, Marco A. Mart\\'inez-Ram\\'irez, Stefan Uhlich, Sungho Lee, Wei-Hsiang Liao, Yuki Mitsufuji","submitted_at":"2024-06-03T06:56:34Z","abstract_excerpt":"Music mixing is compositional -- experts combine multiple audio processors to achieve a cohesive mix from dry source tracks. We propose a method to reverse engineer this process from the input and output audio. First, we create a mixing console that applies all available processors to every chain. Then, after the initial console parameter optimization, we alternate between removing redundant processors and fine-tuning. We achieve this through differentiable implementation of both processors and pruning. Consequently, we find a sparse mixing graph that achieves nearly identical matching quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01049","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/2406.01049/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":"2406.01049","created_at":"2026-07-05T08:52:33.622874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01049v2","created_at":"2026-07-05T08:52:33.622874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01049","created_at":"2026-07-05T08:52:33.622874+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQ3PF2UGOZQW","created_at":"2026-07-05T08:52:33.622874+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQ3PF2UGOZQWY5BZ","created_at":"2026-07-05T08:52:33.622874+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQ3PF2UG","created_at":"2026-07-05T08:52:33.622874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.03448","citing_title":"SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP","json":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP.json","graph_json":"https://pith.science/api/pith-number/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/graph.json","events_json":"https://pith.science/api/pith-number/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/events.json","paper":"https://pith.science/paper/XQ3PF2UG"},"agent_actions":{"view_html":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP","download_json":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP.json","view_paper":"https://pith.science/paper/XQ3PF2UG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01049&json=true","fetch_graph":"https://pith.science/api/pith-number/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/graph.json","fetch_events":"https://pith.science/api/pith-number/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/action/storage_attestation","attest_author":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/action/author_attestation","sign_citation":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/action/citation_signature","submit_replication":"https://pith.science/pith/XQ3PF2UGOZQWY5BZ5QPCR6YIYP/action/replication_record"}},"created_at":"2026-07-05T08:52:33.622874+00:00","updated_at":"2026-07-05T08:52:33.622874+00:00"}