{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PZV5KWNDJ4R34LPJERVPA7R2PR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3540e743b593aa4ed05e84103b7f52029c404f557cbc0ba3a474a0254c6caf56","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-22T13:59:58Z","title_canon_sha256":"ebf92609993c22a6384d009d994477e87150ba7a1c60b6496212212ef976ac6b"},"schema_version":"1.0","source":{"id":"2407.15641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15641","created_at":"2026-07-05T08:46:59Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15641v1","created_at":"2026-07-05T08:46:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15641","created_at":"2026-07-05T08:46:59Z"},{"alias_kind":"pith_short_12","alias_value":"PZV5KWNDJ4R3","created_at":"2026-07-05T08:46:59Z"},{"alias_kind":"pith_short_16","alias_value":"PZV5KWNDJ4R34LPJ","created_at":"2026-07-05T08:46:59Z"},{"alias_kind":"pith_short_8","alias_value":"PZV5KWND","created_at":"2026-07-05T08:46:59Z"}],"graph_snapshots":[{"event_id":"sha256:e6ced96fddca3e19ac34ffbeacd8c4b57dfe52a9b86bbbb236ec1ba6e1201b38","target":"graph","created_at":"2026-07-05T08:46:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.15641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose and investigate the use of neural audio codec language models for the automatic generation of sample-based musical instruments based on text or reference audio prompts. Our approach extends a generative audio framework to condition on pitch across an 88-key spectrum, velocity, and a combined text/audio embedding. We identify maintaining timbral consistency within the generated instruments as a major challenge. To tackle this issue, we introduce three distinct conditioning schemes. We analyze our methods through objective metrics and human listening tests, demonstratin","authors_text":"Frederik Blang, Johannes Imort, Ninon Devis, Shahan Nercessian","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-22T13:59:58Z","title":"Generating Sample-Based Musical Instruments Using Neural Audio Codec Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15641","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f49c9cd6eb99a55e5778a7b55914b1ff6120e8d6506b25853ddf56e446090169","target":"record","created_at":"2026-07-05T08:46:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3540e743b593aa4ed05e84103b7f52029c404f557cbc0ba3a474a0254c6caf56","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-22T13:59:58Z","title_canon_sha256":"ebf92609993c22a6384d009d994477e87150ba7a1c60b6496212212ef976ac6b"},"schema_version":"1.0","source":{"id":"2407.15641","kind":"arxiv","version":1}},"canonical_sha256":"7e6bd559a34f23be2de9246af07e3a7c679a0d7a2efc8ece935c9fbafdc5b717","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e6bd559a34f23be2de9246af07e3a7c679a0d7a2efc8ece935c9fbafdc5b717","first_computed_at":"2026-07-05T08:46:59.194779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:59.194779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ungmMjwr7leh0FQoKAswXTrUczPYsBXnVj87nKQWlePi33zuJ3cWYmL4Nfx9m4cYuP3Y/VzmR/bnoT1qxleBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:59.195347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f49c9cd6eb99a55e5778a7b55914b1ff6120e8d6506b25853ddf56e446090169","sha256:e6ced96fddca3e19ac34ffbeacd8c4b57dfe52a9b86bbbb236ec1ba6e1201b38"],"state_sha256":"ca630cec1f04102b2d9c434fece1679f5196804e0f470129373555a3d7d307a3"}