{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WMSLA6S2TQN3DWJD2RWQUB3EB3","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":"fc2948279fd7e2e123543f9ae2e3f32c3e0da3532f88bf9e026a1bbb630cf02d","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-21T08:09:12Z","title_canon_sha256":"68e57e3f2e9642929271523fbacc40d1615e33c05363c321497adb066c18e90a"},"schema_version":"1.0","source":{"id":"2412.16526","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16526","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16526v2","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16526","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"WMSLA6S2TQN3","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"WMSLA6S2TQN3DWJD","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"WMSLA6S2","created_at":"2026-07-05T11:22:35Z"}],"graph_snapshots":[{"event_id":"sha256:90a3a78e4ee48c057d3c67ac04395ce987d716de0bf2abe905668fd2978fff87","target":"graph","created_at":"2026-07-05T11:22:35Z","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/2412.16526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces text2midi, an end-to-end model to generate MIDI files from textual descriptions. Leveraging the growing popularity of multimodal generative approaches, text2midi capitalizes on the extensive availability of textual data and the success of large language models (LLMs). Our end-to-end system harnesses the power of LLMs to generate symbolic music in the form of MIDI files. Specifically, we utilize a pretrained LLM encoder to process captions, which then condition an autoregressive transformer decoder to produce MIDI sequences that accurately reflect the provided descriptions","authors_text":"Abhinaba Roy, Dorien Herremans, Geeta Puri, Keshav Bhandari, Kyra Wang, Simon Colton","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-21T08:09:12Z","title":"Text2midi: Generating Symbolic Music from Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16526","kind":"arxiv","version":2},"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":"sha256:85579cbdc9614dc887fd002001b6405891cf679cc2dcc66fab5e5d359784684d","target":"record","created_at":"2026-07-05T11:22:35Z","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":"fc2948279fd7e2e123543f9ae2e3f32c3e0da3532f88bf9e026a1bbb630cf02d","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-21T08:09:12Z","title_canon_sha256":"68e57e3f2e9642929271523fbacc40d1615e33c05363c321497adb066c18e90a"},"schema_version":"1.0","source":{"id":"2412.16526","kind":"arxiv","version":2}},"canonical_sha256":"b324b07a5a9c1bb1d923d46d0a07640eea00619f8fcac064e847fc39cc43b50e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b324b07a5a9c1bb1d923d46d0a07640eea00619f8fcac064e847fc39cc43b50e","first_computed_at":"2026-07-05T11:22:35.112368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:35.112368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rjh7lIglaHEZg27ub3GP5HlH8Akq5mGHs/HbIJzPAbpFrhjOuRytgymRKwuwga8QQ0Fv/6qNNk1oKnt5XW9/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:35.112908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16526","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85579cbdc9614dc887fd002001b6405891cf679cc2dcc66fab5e5d359784684d","sha256:90a3a78e4ee48c057d3c67ac04395ce987d716de0bf2abe905668fd2978fff87"],"state_sha256":"962f3550253d3a443edb37f6a0caa5f5d49dd41511697d286f340637d36b8d43"}