{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YV4PCFHKW3V3HU5GAIU2VHOCNL","short_pith_number":"pith:YV4PCFHK","schema_version":"1.0","canonical_sha256":"c578f114eab6ebb3d3a60229aa9dc26ace3b33d360c4c73f831e952867ddd2c9","source":{"kind":"arxiv","id":"2311.04339","version":1},"attestation_state":"computed","paper":{"title":"InstrumentGen: Generating Sample-Based Musical Instruments From Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Johannes Imort, Shahan Nercessian","submitted_at":"2023-11-07T20:45:59Z","abstract_excerpt":"We introduce the text-to-instrument task, which aims at generating sample-based musical instruments based on textual prompts. Accordingly, we propose InstrumentGen, a model that extends a text-prompted generative audio framework to condition on instrument family, source type, pitch (across an 88-key spectrum), velocity, and a joint text/audio embedding. Furthermore, we present a differentiable loss function to evaluate the intra-instrument timbral consistency of sample-based instruments. Our results establish a foundational text-to-instrument baseline, extending research in the domain of autom"},"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":"2311.04339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-07T20:45:59Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"e6eca30a7c0e700df8898980bcef7cf5844d27e16d9a87293f3fb6b52674d492","abstract_canon_sha256":"0866132ff110568f201bb7610e726d0f9ab04c27f8e1d743b8677f3447cd3bcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:34.227212Z","signature_b64":"32SIisI5NFWr20FGkBKnyvcA+vYnh4Tp5BMVOJUCBqiapIXhK/hn6AsIFvB+EVJBzhlwksvAicxIKVz/RLwxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c578f114eab6ebb3d3a60229aa9dc26ace3b33d360c4c73f831e952867ddd2c9","last_reissued_at":"2026-07-05T07:10:34.226812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:34.226812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstrumentGen: Generating Sample-Based Musical Instruments From Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Johannes Imort, Shahan Nercessian","submitted_at":"2023-11-07T20:45:59Z","abstract_excerpt":"We introduce the text-to-instrument task, which aims at generating sample-based musical instruments based on textual prompts. Accordingly, we propose InstrumentGen, a model that extends a text-prompted generative audio framework to condition on instrument family, source type, pitch (across an 88-key spectrum), velocity, and a joint text/audio embedding. Furthermore, we present a differentiable loss function to evaluate the intra-instrument timbral consistency of sample-based instruments. Our results establish a foundational text-to-instrument baseline, extending research in the domain of autom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04339","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/2311.04339/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":"2311.04339","created_at":"2026-07-05T07:10:34.226865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04339v1","created_at":"2026-07-05T07:10:34.226865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04339","created_at":"2026-07-05T07:10:34.226865+00:00"},{"alias_kind":"pith_short_12","alias_value":"YV4PCFHKW3V3","created_at":"2026-07-05T07:10:34.226865+00:00"},{"alias_kind":"pith_short_16","alias_value":"YV4PCFHKW3V3HU5G","created_at":"2026-07-05T07:10:34.226865+00:00"},{"alias_kind":"pith_short_8","alias_value":"YV4PCFHK","created_at":"2026-07-05T07:10:34.226865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10534","citing_title":"WildFX: A DAW-Powered Pipeline for In-the-Wild Audio FX Graph Modeling","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL","json":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL.json","graph_json":"https://pith.science/api/pith-number/YV4PCFHKW3V3HU5GAIU2VHOCNL/graph.json","events_json":"https://pith.science/api/pith-number/YV4PCFHKW3V3HU5GAIU2VHOCNL/events.json","paper":"https://pith.science/paper/YV4PCFHK"},"agent_actions":{"view_html":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL","download_json":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL.json","view_paper":"https://pith.science/paper/YV4PCFHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04339&json=true","fetch_graph":"https://pith.science/api/pith-number/YV4PCFHKW3V3HU5GAIU2VHOCNL/graph.json","fetch_events":"https://pith.science/api/pith-number/YV4PCFHKW3V3HU5GAIU2VHOCNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL/action/storage_attestation","attest_author":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL/action/author_attestation","sign_citation":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL/action/citation_signature","submit_replication":"https://pith.science/pith/YV4PCFHKW3V3HU5GAIU2VHOCNL/action/replication_record"}},"created_at":"2026-07-05T07:10:34.226865+00:00","updated_at":"2026-07-05T07:10:34.226865+00:00"}