{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S5O3POKXYJAENN2HDPS2EPHRML","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":"59bd04c1c21b5e6697ef7038859dcd71f06c8397185a51dd37c7c2ff15e5d66a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-14T17:54:38Z","title_canon_sha256":"378719008f6dba060673275ebcd9dc436edbc8f08777173c049d20cd388041be"},"schema_version":"1.0","source":{"id":"2311.08355","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08355","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08355v3","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08355","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"S5O3POKXYJAE","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"S5O3POKXYJAENN2H","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"S5O3POKX","created_at":"2026-07-05T11:22:29Z"}],"graph_snapshots":[{"event_id":"sha256:28ec9a78ec1d0ab91003d584b3de84deb3de70ddb05e455749c86a92e532e9a5","target":"graph","created_at":"2026-07-05T11:22:29Z","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/2311.08355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality of the text-to-music models has reached new heights due to recent advancements in diffusion models. The controllability of various musical aspects, however, has barely been explored. In this paper, we propose Mustango: a music-domain-knowledge-inspired text-to-music system based on diffusion. Mustango aims to control the generated music, not only with general text captions, but with more rich captions that can include specific instructions related to chords, beats, tempo, and key. At the core of Mustango is MuNet, a Music-Domain-Knowledge-Informed UNet guidance module that steers t","authors_text":"Deepanway Ghosal, Dorien Herremans, Jan Melechovsky, Navonil Majumder, Soujanya Poria, Zixun Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-14T17:54:38Z","title":"Mustango: Toward Controllable Text-to-Music Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08355","kind":"arxiv","version":3},"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":"sha256:7640b5302829b72bec5e0fe2a6adbae52085d97c99ff6f1d18c59b168d31fd93","target":"record","created_at":"2026-07-05T11:22:29Z","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":"59bd04c1c21b5e6697ef7038859dcd71f06c8397185a51dd37c7c2ff15e5d66a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-14T17:54:38Z","title_canon_sha256":"378719008f6dba060673275ebcd9dc436edbc8f08777173c049d20cd388041be"},"schema_version":"1.0","source":{"id":"2311.08355","kind":"arxiv","version":3}},"canonical_sha256":"975db7b957c24046b7471be5a23cf162ef34116bb92ef4fad1d991fc94f6a383","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"975db7b957c24046b7471be5a23cf162ef34116bb92ef4fad1d991fc94f6a383","first_computed_at":"2026-07-05T11:22:29.173387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:29.173387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3L9JJBySVVg0tAMlSrbWGfwZeXNqchSRRG7QpN/UFGyI1nACSLsKfjekxGfTKI16mi5rlrPie06kYEG9abQZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:29.173886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08355","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7640b5302829b72bec5e0fe2a6adbae52085d97c99ff6f1d18c59b168d31fd93","sha256:28ec9a78ec1d0ab91003d584b3de84deb3de70ddb05e455749c86a92e532e9a5"],"state_sha256":"100b51b32aa2545eda0f3ea41a8b99b1322263087c46784b4fcb304988abb5d3"}