{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5WARY7L4I3KIFIB6VQ45IFOT47","short_pith_number":"pith:5WARY7L4","canonical_record":{"source":{"id":"2406.02255","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T12:21:55Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD"],"title_canon_sha256":"1f513008584b41526fd8433110b8fec2b6df86cbbeea17b67580eaebe2f36cf9","abstract_canon_sha256":"540e56b28d64dde1b0a5ea80554be3cba8567634230598810f3ff300e5e9350c"},"schema_version":"1.0"},"canonical_sha256":"ed811c7d7c46d482a03eac39d415d3e7ff3264afd9e5abb537e08fdc926738c9","source":{"kind":"arxiv","id":"2406.02255","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02255","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02255v2","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02255","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"5WARY7L4I3KI","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_16","alias_value":"5WARY7L4I3KIFIB6","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_8","alias_value":"5WARY7L4","created_at":"2026-07-05T11:49:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5WARY7L4I3KIFIB6VQ45IFOT47","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02255","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T12:21:55Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD"],"title_canon_sha256":"1f513008584b41526fd8433110b8fec2b6df86cbbeea17b67580eaebe2f36cf9","abstract_canon_sha256":"540e56b28d64dde1b0a5ea80554be3cba8567634230598810f3ff300e5e9350c"},"schema_version":"1.0"},"canonical_sha256":"ed811c7d7c46d482a03eac39d415d3e7ff3264afd9e5abb537e08fdc926738c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:45.608747Z","signature_b64":"0+9zg+9cE9zD2VbJBuWQgaXgFuJdcc4TqMp+GcOXR6JFBrHn+nA3o6cfAr++bDubMuKxi+i9X3D4AwRvebobBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed811c7d7c46d482a03eac39d415d3e7ff3264afd9e5abb537e08fdc926738c9","last_reissued_at":"2026-07-05T11:49:45.608275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:45.608275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02255","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":"2026-07-05T11:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tt8EreJVPeWQbGJ47gotcAWcmChQhpZEbbbwCwtn7D1PhWU+Fur8gNYsh8XIW6HltOkNK7VKmBtRYc0TjCUaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:31:01.340991Z"},"content_sha256":"e4503933b4502d57448678f97468ba79b40e106d90a75116cb0349056865bd0c","schema_version":"1.0","event_id":"sha256:e4503933b4502d57448678f97468ba79b40e106d90a75116cb0349056865bd0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5WARY7L4I3KIFIB6VQ45IFOT47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MidiCaps: A large-scale MIDI dataset with text captions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abhinaba Roy, Dorien Herremans, Jan Melechovsky","submitted_at":"2024-06-04T12:21:55Z","abstract_excerpt":"Generative models guided by text prompts are increasingly becoming more popular. However, no text-to-MIDI models currently exist due to the lack of a captioned MIDI dataset. This work aims to enable research that combines LLMs with symbolic music by presenting, the first openly available large-scale MIDI dataset with text captions. MIDI (Musical Instrument Digital Interface) files are widely used for encoding musical information and can capture the nuances of musical composition. They are widely used by music producers, composers, musicologists, and performers alike. Inspired by recent advance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02255","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/2406.02255/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":"2026-07-05T11:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aqJ0rBBzDNcWScZkR/js8CjRwvMplr4jvj648XreW6lhAG7ort5JINVTd5Q6gku5XLx/oeoSl0MEMzgU8wYxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:31:01.341508Z"},"content_sha256":"52e91894cf9c7695bdf9a49163c4aae20f762516862bf43344951f4576d2f5d3","schema_version":"1.0","event_id":"sha256:52e91894cf9c7695bdf9a49163c4aae20f762516862bf43344951f4576d2f5d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WARY7L4I3KIFIB6VQ45IFOT47/bundle.json","state_url":"https://pith.science/pith/5WARY7L4I3KIFIB6VQ45IFOT47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WARY7L4I3KIFIB6VQ45IFOT47/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":"2026-08-08T23:31:01Z","links":{"resolver":"https://pith.science/pith/5WARY7L4I3KIFIB6VQ45IFOT47","bundle":"https://pith.science/pith/5WARY7L4I3KIFIB6VQ45IFOT47/bundle.json","state":"https://pith.science/pith/5WARY7L4I3KIFIB6VQ45IFOT47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WARY7L4I3KIFIB6VQ45IFOT47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5WARY7L4I3KIFIB6VQ45IFOT47","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":"540e56b28d64dde1b0a5ea80554be3cba8567634230598810f3ff300e5e9350c","cross_cats_sorted":["cs.LG","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T12:21:55Z","title_canon_sha256":"1f513008584b41526fd8433110b8fec2b6df86cbbeea17b67580eaebe2f36cf9"},"schema_version":"1.0","source":{"id":"2406.02255","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02255","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02255v2","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02255","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"5WARY7L4I3KI","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_16","alias_value":"5WARY7L4I3KIFIB6","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_8","alias_value":"5WARY7L4","created_at":"2026-07-05T11:49:45Z"}],"graph_snapshots":[{"event_id":"sha256:52e91894cf9c7695bdf9a49163c4aae20f762516862bf43344951f4576d2f5d3","target":"graph","created_at":"2026-07-05T11:49:45Z","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/2406.02255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative models guided by text prompts are increasingly becoming more popular. However, no text-to-MIDI models currently exist due to the lack of a captioned MIDI dataset. This work aims to enable research that combines LLMs with symbolic music by presenting, the first openly available large-scale MIDI dataset with text captions. MIDI (Musical Instrument Digital Interface) files are widely used for encoding musical information and can capture the nuances of musical composition. They are widely used by music producers, composers, musicologists, and performers alike. Inspired by recent advance","authors_text":"Abhinaba Roy, Dorien Herremans, Jan Melechovsky","cross_cats":["cs.LG","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T12:21:55Z","title":"MidiCaps: A large-scale MIDI dataset with text captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02255","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:e4503933b4502d57448678f97468ba79b40e106d90a75116cb0349056865bd0c","target":"record","created_at":"2026-07-05T11:49:45Z","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":"540e56b28d64dde1b0a5ea80554be3cba8567634230598810f3ff300e5e9350c","cross_cats_sorted":["cs.LG","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T12:21:55Z","title_canon_sha256":"1f513008584b41526fd8433110b8fec2b6df86cbbeea17b67580eaebe2f36cf9"},"schema_version":"1.0","source":{"id":"2406.02255","kind":"arxiv","version":2}},"canonical_sha256":"ed811c7d7c46d482a03eac39d415d3e7ff3264afd9e5abb537e08fdc926738c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed811c7d7c46d482a03eac39d415d3e7ff3264afd9e5abb537e08fdc926738c9","first_computed_at":"2026-07-05T11:49:45.608275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:45.608275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0+9zg+9cE9zD2VbJBuWQgaXgFuJdcc4TqMp+GcOXR6JFBrHn+nA3o6cfAr++bDubMuKxi+i9X3D4AwRvebobBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:45.608747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02255","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4503933b4502d57448678f97468ba79b40e106d90a75116cb0349056865bd0c","sha256:52e91894cf9c7695bdf9a49163c4aae20f762516862bf43344951f4576d2f5d3"],"state_sha256":"fc23e29947883fc9c9d959a6a2f0a458d9c82f61b2ca5200ac438513f373a140"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2NZVt98l5jiTCr1KBCefPDufQPD+0G4fjVgaCriHgknUs/paYtb0caYlXdHdWwjJujlRJ3t4radyBVHhWDhYCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:31:01.346501Z","bundle_sha256":"1e540ef20202bbcc88e89442ae6388e000782c6516437159b6f4ff9f42ed4eaf"}}