{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:67MW3N2EHDCNJSIPA342I6C76I","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":"3645d8f4dbb3e592d7cba7dc502ca6c12492743bbeb406d2997d374740b0e933","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-21T05:27:53Z","title_canon_sha256":"56a064bc8ccc2ed832771c699a3da4ceca29591cb95157ca05433e250c1029ad"},"schema_version":"1.0","source":{"id":"2407.15060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15060","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15060v1","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15060","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"67MW3N2EHDCN","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"67MW3N2EHDCNJSIP","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"67MW3N2E","created_at":"2026-07-05T08:46:38Z"}],"graph_snapshots":[{"event_id":"sha256:efd8f35e590dc26c8318627c8dc066c5fa02efb944372923555889ae79823b37","target":"graph","created_at":"2026-07-05T08:46:38Z","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/2407.15060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing text-to-music models can produce high-quality audio with great diversity. However, textual prompts alone cannot precisely control temporal musical features such as chords and rhythm of the generated music. To address this challenge, we introduce MusiConGen, a temporally-conditioned Transformer-based text-to-music model that builds upon the pretrained MusicGen framework. Our innovation lies in an efficient finetuning mechanism, tailored for consumer-grade GPUs, that integrates automatically-extracted rhythm and chords as the condition signal. During inference, the condition can either ","authors_text":"Hao-Chung Cheng, Wen-Yi Hsiao, Yi-Hsuan Yang, Yun-Han Lan","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-21T05:27:53Z","title":"MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15060","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":"sha256:5a4530602aa4145fbecae7bea891ede1c19e798357d9b1e8caf78b3ec032df2c","target":"record","created_at":"2026-07-05T08:46:38Z","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":"3645d8f4dbb3e592d7cba7dc502ca6c12492743bbeb406d2997d374740b0e933","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-21T05:27:53Z","title_canon_sha256":"56a064bc8ccc2ed832771c699a3da4ceca29591cb95157ca05433e250c1029ad"},"schema_version":"1.0","source":{"id":"2407.15060","kind":"arxiv","version":1}},"canonical_sha256":"f7d96db74438c4d4c90f06f9a4785ff21b1c2aea0377adf0a75ae20aad683b93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7d96db74438c4d4c90f06f9a4785ff21b1c2aea0377adf0a75ae20aad683b93","first_computed_at":"2026-07-05T08:46:38.212017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:38.212017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q1+z7ZnyizQFrzuZ2R/idqdmU2zfdz76p4mPaUcMm+HavjlunCdZj+JEuVHLYmX9W1n5XHG+CpPK9snbjfwRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:38.212453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a4530602aa4145fbecae7bea891ede1c19e798357d9b1e8caf78b3ec032df2c","sha256:efd8f35e590dc26c8318627c8dc066c5fa02efb944372923555889ae79823b37"],"state_sha256":"a8b03cf7b8b63a74c63651ae5edbe526709764b832378c5d450f5d27ffa50ac5"}