{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCMB3YLOWJ7FDEMDK4JNFAAUCI","short_pith_number":"pith:FCMB3YLO","schema_version":"1.0","canonical_sha256":"28981de16eb27e5191835712d280141237bb7b861bed7e06ace8a12be2945060","source":{"kind":"arxiv","id":"2502.04522","version":4},"attestation_state":"computed","paper":{"title":"ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dorien Herremans, Fareza R. Enus, Keshav Bhandari, Louis B. Bradshaw, Simon Colton, Sungkyun Chang, Tongyu Lu","submitted_at":"2025-02-06T21:45:38Z","abstract_excerpt":"Despite deep learning's remarkable advances in style transfer across various domains, generating controllable performance-level musical style transfer for complete symbolically represented musical works remains a challenging area of research. Much of this is owed to limited datasets, especially for genres such as jazz, and the lack of unified models that can handle multiple music generation tasks. This paper presents ImprovNet, a transformer-based architecture that generates expressive and controllable musical improvisations through a self-supervised corruption-refinement training strategy. Th"},"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":"2502.04522","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T21:45:38Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"c1697aa087fa6bb9ef463ce66a7cc39470f58dcaf6f8a2ce775e96ab6fd00ede","abstract_canon_sha256":"b486bfd57b62ca892db5ebdc4022f44734d53aa35aaf38107e345e0396e0658e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:56.308910Z","signature_b64":"Wz4HqRxjI/KVFGRViGTBIo/P4vSGHC65D71kZi5tttCeFLwttaza6Kvgfp6nTIGRR+kpVfbL3f9RH0nVQBaJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28981de16eb27e5191835712d280141237bb7b861bed7e06ace8a12be2945060","last_reissued_at":"2026-07-05T11:03:56.308367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:56.308367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dorien Herremans, Fareza R. Enus, Keshav Bhandari, Louis B. Bradshaw, Simon Colton, Sungkyun Chang, Tongyu Lu","submitted_at":"2025-02-06T21:45:38Z","abstract_excerpt":"Despite deep learning's remarkable advances in style transfer across various domains, generating controllable performance-level musical style transfer for complete symbolically represented musical works remains a challenging area of research. Much of this is owed to limited datasets, especially for genres such as jazz, and the lack of unified models that can handle multiple music generation tasks. This paper presents ImprovNet, a transformer-based architecture that generates expressive and controllable musical improvisations through a self-supervised corruption-refinement training strategy. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04522","kind":"arxiv","version":4},"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/2502.04522/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":"2502.04522","created_at":"2026-07-05T11:03:56.308445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04522v4","created_at":"2026-07-05T11:03:56.308445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04522","created_at":"2026-07-05T11:03:56.308445+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCMB3YLOWJ7F","created_at":"2026-07-05T11:03:56.308445+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCMB3YLOWJ7FDEMD","created_at":"2026-07-05T11:03:56.308445+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCMB3YLO","created_at":"2026-07-05T11:03:56.308445+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":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI","json":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI.json","graph_json":"https://pith.science/api/pith-number/FCMB3YLOWJ7FDEMDK4JNFAAUCI/graph.json","events_json":"https://pith.science/api/pith-number/FCMB3YLOWJ7FDEMDK4JNFAAUCI/events.json","paper":"https://pith.science/paper/FCMB3YLO"},"agent_actions":{"view_html":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI","download_json":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI.json","view_paper":"https://pith.science/paper/FCMB3YLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04522&json=true","fetch_graph":"https://pith.science/api/pith-number/FCMB3YLOWJ7FDEMDK4JNFAAUCI/graph.json","fetch_events":"https://pith.science/api/pith-number/FCMB3YLOWJ7FDEMDK4JNFAAUCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI/action/storage_attestation","attest_author":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI/action/author_attestation","sign_citation":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI/action/citation_signature","submit_replication":"https://pith.science/pith/FCMB3YLOWJ7FDEMDK4JNFAAUCI/action/replication_record"}},"created_at":"2026-07-05T11:03:56.308445+00:00","updated_at":"2026-07-05T11:03:56.308445+00:00"}