{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CTYJPZXSO3NFWM6MW2ZOESGKCI","short_pith_number":"pith:CTYJPZXS","canonical_record":{"source":{"id":"2511.03942","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-11-06T00:40:07Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"d2efa23ce5b99dc2a4c887b3fb38df86cf3a19de2abdc3583084c2b14bcac061","abstract_canon_sha256":"9e971bb886d6b270f17b608a4f1582be5d18529ad5103e07c7a3d02cdcfa9e12"},"schema_version":"1.0"},"canonical_sha256":"14f097e6f276da5b33ccb6b2e248ca1205704cbc6ee62d06e71c870bd37eb513","source":{"kind":"arxiv","id":"2511.03942","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.03942","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"2511.03942v2","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.03942","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"CTYJPZXSO3NF","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"CTYJPZXSO3NFWM6M","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"CTYJPZXS","created_at":"2026-08-05T00:41:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CTYJPZXSO3NFWM6MW2ZOESGKCI","target":"record","payload":{"canonical_record":{"source":{"id":"2511.03942","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-11-06T00:40:07Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"d2efa23ce5b99dc2a4c887b3fb38df86cf3a19de2abdc3583084c2b14bcac061","abstract_canon_sha256":"9e971bb886d6b270f17b608a4f1582be5d18529ad5103e07c7a3d02cdcfa9e12"},"schema_version":"1.0"},"canonical_sha256":"14f097e6f276da5b33ccb6b2e248ca1205704cbc6ee62d06e71c870bd37eb513","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:41:00.198371Z","signature_b64":"OPH3iH94XD3tzYXczF2TkRGTAcNc9pWwc4ORfgWbw+ETQIU2N5zwRtQV4XxSTv+NWLAF3Et61jU1HlOvOpccCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14f097e6f276da5b33ccb6b2e248ca1205704cbc6ee62d06e71c870bd37eb513","last_reissued_at":"2026-08-05T00:41:00.194700Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:41:00.194700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.03942","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T00:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yhiheoIOFGcUo/YzH5CzpwSm7ttvKPQrEGDvXJWyctO9jGKj0MSlIlISMWb8YnFpdfQqPQAz9PfiUvfOgGNkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:23:09.708311Z"},"content_sha256":"371a8ed3ddae7d6cb7833d6db2461bd6e21266526d8e747870668f1bcd1b2a10","schema_version":"1.0","event_id":"sha256:371a8ed3ddae7d6cb7833d6db2461bd6e21266526d8e747870668f1bcd1b2a10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CTYJPZXSO3NFWM6MW2ZOESGKCI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIDI-LLM: Improving Text-to-MIDI Music Generation via Adapting Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.SD","authors_text":"Cheng-Zhi Anna Huang, Chris Donahue, Dave Carlton, Ryan Miyakawa, Shih-Lun Wu, Yoon Kim","submitted_at":"2025-11-06T00:40:07Z","abstract_excerpt":"We present MIDI-LLM, a recipe that improves multitrack text-to-MIDI generation via adapting Large Language Models (LLMs). MIDI-LLM expands an LLM's text vocabulary to include MIDI tokens and employs a two-stage training pipeline: (i) unimodal continued pretraining on music-adjacent text and standalone MIDIs, and (ii) multimodal supervised finetuning on text-MIDI pairs. Our instantiation of MIDI-LLM based on Llama 3.2 (1B) outperforms the recent Text2midi model in both text control and musical quality, and readily integrates with optimized inference ecosystems like vLLM. To align with real-worl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.03942","kind":"arxiv","version":2},"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/2511.03942/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T00:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0zEOhUEjaXOi0M3jevn083h2PS6YO51W0D3Ipej67IkUlQKoHw7cyNO1aC1xDnIOIjluuBGrfdrDxug/Gs6WAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:23:09.709229Z"},"content_sha256":"4977ece170da54c89c08ae77bf1b3f2462e4ee1d8dfcb020c7c6cb75a86ff3f3","schema_version":"1.0","event_id":"sha256:4977ece170da54c89c08ae77bf1b3f2462e4ee1d8dfcb020c7c6cb75a86ff3f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTYJPZXSO3NFWM6MW2ZOESGKCI/bundle.json","state_url":"https://pith.science/pith/CTYJPZXSO3NFWM6MW2ZOESGKCI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTYJPZXSO3NFWM6MW2ZOESGKCI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T17:23:09Z","links":{"resolver":"https://pith.science/pith/CTYJPZXSO3NFWM6MW2ZOESGKCI","bundle":"https://pith.science/pith/CTYJPZXSO3NFWM6MW2ZOESGKCI/bundle.json","state":"https://pith.science/pith/CTYJPZXSO3NFWM6MW2ZOESGKCI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTYJPZXSO3NFWM6MW2ZOESGKCI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CTYJPZXSO3NFWM6MW2ZOESGKCI","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":"9e971bb886d6b270f17b608a4f1582be5d18529ad5103e07c7a3d02cdcfa9e12","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-11-06T00:40:07Z","title_canon_sha256":"d2efa23ce5b99dc2a4c887b3fb38df86cf3a19de2abdc3583084c2b14bcac061"},"schema_version":"1.0","source":{"id":"2511.03942","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.03942","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"2511.03942v2","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.03942","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"CTYJPZXSO3NF","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"CTYJPZXSO3NFWM6M","created_at":"2026-08-05T00:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"CTYJPZXS","created_at":"2026-08-05T00:41:00Z"}],"graph_snapshots":[{"event_id":"sha256:4977ece170da54c89c08ae77bf1b3f2462e4ee1d8dfcb020c7c6cb75a86ff3f3","target":"graph","created_at":"2026-08-05T00:41:00Z","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/2511.03942/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MIDI-LLM, a recipe that improves multitrack text-to-MIDI generation via adapting Large Language Models (LLMs). MIDI-LLM expands an LLM's text vocabulary to include MIDI tokens and employs a two-stage training pipeline: (i) unimodal continued pretraining on music-adjacent text and standalone MIDIs, and (ii) multimodal supervised finetuning on text-MIDI pairs. Our instantiation of MIDI-LLM based on Llama 3.2 (1B) outperforms the recent Text2midi model in both text control and musical quality, and readily integrates with optimized inference ecosystems like vLLM. To align with real-worl","authors_text":"Cheng-Zhi Anna Huang, Chris Donahue, Dave Carlton, Ryan Miyakawa, Shih-Lun Wu, Yoon Kim","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-11-06T00:40:07Z","title":"MIDI-LLM: Improving Text-to-MIDI Music Generation via Adapting Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.03942","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":"sha256:371a8ed3ddae7d6cb7833d6db2461bd6e21266526d8e747870668f1bcd1b2a10","target":"record","created_at":"2026-08-05T00:41:00Z","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":"9e971bb886d6b270f17b608a4f1582be5d18529ad5103e07c7a3d02cdcfa9e12","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-11-06T00:40:07Z","title_canon_sha256":"d2efa23ce5b99dc2a4c887b3fb38df86cf3a19de2abdc3583084c2b14bcac061"},"schema_version":"1.0","source":{"id":"2511.03942","kind":"arxiv","version":2}},"canonical_sha256":"14f097e6f276da5b33ccb6b2e248ca1205704cbc6ee62d06e71c870bd37eb513","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14f097e6f276da5b33ccb6b2e248ca1205704cbc6ee62d06e71c870bd37eb513","first_computed_at":"2026-08-05T00:41:00.194700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:41:00.194700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OPH3iH94XD3tzYXczF2TkRGTAcNc9pWwc4ORfgWbw+ETQIU2N5zwRtQV4XxSTv+NWLAF3Et61jU1HlOvOpccCA==","signature_status":"signed_v1","signed_at":"2026-08-05T00:41:00.198371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.03942","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:371a8ed3ddae7d6cb7833d6db2461bd6e21266526d8e747870668f1bcd1b2a10","sha256:4977ece170da54c89c08ae77bf1b3f2462e4ee1d8dfcb020c7c6cb75a86ff3f3"],"state_sha256":"16d9ce79c01acdbe9d359d63f421b7630d7c737b37c42d737c21d4f31f921d18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fhk/5G8TLZlyStNXNs4lKTQ8+t5z1IXWfXEFV5QzWGqwB/rC1psa8OaACkqHrPQzZ7j8vH7cWwWa56pMKS+IBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:23:09.715258Z","bundle_sha256":"253db687e6b94615278b893d8892dde0db98931afb0f4ced0dd80b92a330df69"}}