{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VEV7T6GMLXHUFQWGBPRICTYQES","short_pith_number":"pith:VEV7T6GM","schema_version":"1.0","canonical_sha256":"a92bf9f8cc5dcf42c2c60be2814f10249d945f68fecaaf89c6e9d240a96f2e0c","source":{"kind":"arxiv","id":"2608.05506","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Automatic Music Mixing as Sequential Stem Blending","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chung-Jui Chan, Yen-Tung Yeh, Yi-Hsuan Yang, Yun-Ning (Amy) Hung","submitted_at":"2026-08-06T01:16:18Z","abstract_excerpt":"Automatic music mixing, the task of automatically combining individual audio tracks into a cohesive mixture, is typically addressed by parallelized architectures that process all input tracks in a single pass. In this work, inspired by how human mix engineers process stems one at a time, we propose a paradigm shift and ask whether automatic music mixing can be reformulated as a sequential stem blending task, where each stem is blended into a growing submix. Specifically, we train a latent flow matching model conditioned on the submix context, enabling sequential processing of an arbitrary numb"},"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":"2608.05506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-08-06T01:16:18Z","cross_cats_sorted":[],"title_canon_sha256":"278e00afd704d7437e19fd42e543f4e010e341a9031da25d9ffa6e097ea24ae2","abstract_canon_sha256":"34c3cb284254a9cbb493ee1ee35c071ae55735b9b5692194fe53195f112ea8d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:47:59.702569Z","signature_b64":"9fX17ZZaDVWCsbtzNbADke7wUyvKcgscpXmkgNHwppH++mI14c8g1pcQQnhytGJ9e7rfPmR5a7KMYZ0ryr5qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a92bf9f8cc5dcf42c2c60be2814f10249d945f68fecaaf89c6e9d240a96f2e0c","last_reissued_at":"2026-08-07T00:47:59.701249Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:47:59.701249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Automatic Music Mixing as Sequential Stem Blending","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chung-Jui Chan, Yen-Tung Yeh, Yi-Hsuan Yang, Yun-Ning (Amy) Hung","submitted_at":"2026-08-06T01:16:18Z","abstract_excerpt":"Automatic music mixing, the task of automatically combining individual audio tracks into a cohesive mixture, is typically addressed by parallelized architectures that process all input tracks in a single pass. In this work, inspired by how human mix engineers process stems one at a time, we propose a paradigm shift and ask whether automatic music mixing can be reformulated as a sequential stem blending task, where each stem is blended into a growing submix. Specifically, we train a latent flow matching model conditioned on the submix context, enabling sequential processing of an arbitrary numb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05506","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/2608.05506/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":"2608.05506","created_at":"2026-08-07T00:47:59.702551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05506v1","created_at":"2026-08-07T00:47:59.702551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05506","created_at":"2026-08-07T00:47:59.702551+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEV7T6GMLXHU","created_at":"2026-08-07T00:47:59.702551+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEV7T6GMLXHUFQWG","created_at":"2026-08-07T00:47:59.702551+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEV7T6GM","created_at":"2026-08-07T00:47:59.702551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05506","citing_title":"Rethinking Automatic Music Mixing as Sequential Stem Blending","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES","json":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES.json","graph_json":"https://pith.science/api/pith-number/VEV7T6GMLXHUFQWGBPRICTYQES/graph.json","events_json":"https://pith.science/api/pith-number/VEV7T6GMLXHUFQWGBPRICTYQES/events.json","paper":"https://pith.science/paper/VEV7T6GM"},"agent_actions":{"view_html":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES","download_json":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES.json","view_paper":"https://pith.science/paper/VEV7T6GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05506&json=true","fetch_graph":"https://pith.science/api/pith-number/VEV7T6GMLXHUFQWGBPRICTYQES/graph.json","fetch_events":"https://pith.science/api/pith-number/VEV7T6GMLXHUFQWGBPRICTYQES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES/action/storage_attestation","attest_author":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES/action/author_attestation","sign_citation":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES/action/citation_signature","submit_replication":"https://pith.science/pith/VEV7T6GMLXHUFQWGBPRICTYQES/action/replication_record"}},"created_at":"2026-08-07T00:47:59.702551+00:00","updated_at":"2026-08-07T00:47:59.702551+00:00"}