{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MSAYK3M3KMO4WTAGOJUXKGYLHI","short_pith_number":"pith:MSAYK3M3","canonical_record":{"source":{"id":"2311.11255","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-19T06:50:52Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"021f2d9e2b27d48fcfe08fca1334564325975d373830509433e4d3153ef50020","abstract_canon_sha256":"c4f866057190994afca8a0cf2e8c5b8ae74601788211b5e79648430c96bd1793"},"schema_version":"1.0"},"canonical_sha256":"6481856d9b531dcb4c067269751b0b3a3a66d1a8f4563a69da042cb5092dfbf7","source":{"kind":"arxiv","id":"2311.11255","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11255","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11255v5","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11255","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"pith_short_12","alias_value":"MSAYK3M3KMO4","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"pith_short_16","alias_value":"MSAYK3M3KMO4WTAG","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"pith_short_8","alias_value":"MSAYK3M3","created_at":"2026-07-05T09:46:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MSAYK3M3KMO4WTAGOJUXKGYLHI","target":"record","payload":{"canonical_record":{"source":{"id":"2311.11255","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-19T06:50:52Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"021f2d9e2b27d48fcfe08fca1334564325975d373830509433e4d3153ef50020","abstract_canon_sha256":"c4f866057190994afca8a0cf2e8c5b8ae74601788211b5e79648430c96bd1793"},"schema_version":"1.0"},"canonical_sha256":"6481856d9b531dcb4c067269751b0b3a3a66d1a8f4563a69da042cb5092dfbf7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:26.805500Z","signature_b64":"ZquBa2jj39Cnz1buQhhPO4RYvhbGnyRmzURUBwFOXpZ5Aj0fRX8pjxW7wECbOEu0pAEcIWRxrx2zG7GIphDIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6481856d9b531dcb4c067269751b0b3a3a66d1a8f4563a69da042cb5092dfbf7","last_reissued_at":"2026-07-05T09:46:26.805142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:26.805142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.11255","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EemxiAmRx4+jdnS7ioCqBl0cToS6AlQVkPycdxmLYC2CgY4zUaa/31hSae5nBd7Jq7DFMJhLfKAOkXvFy1vhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:23:04.307280Z"},"content_sha256":"db40c0da3c001333c23eaec724b424be47f197240d13d344511239a41d9a0da5","schema_version":"1.0","event_id":"sha256:db40c0da3c001333c23eaec724b424be47f197240d13d344511239a41d9a0da5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MSAYK3M3KMO4WTAGOJUXKGYLHI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M$^{2}$UGen: Multi-modal Music Understanding and Generation with the Power of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Atin Sakkeer Hussain, Chenshuo Sun, Qilong Wu, Shansong Liu, Ying Shan","submitted_at":"2023-11-19T06:50:52Z","abstract_excerpt":"The current landscape of research leveraging large language models (LLMs) is experiencing a surge. Many works harness the powerful reasoning capabilities of these models to comprehend various modalities, such as text, speech, images, videos, etc. They also utilize LLMs to understand human intention and generate desired outputs like images, videos, and music. However, research that combines both understanding and generation using LLMs is still limited and in its nascent stage. To address this gap, we introduce a Multi-modal Music Understanding and Generation (M$^{2}$UGen) framework that integra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11255","kind":"arxiv","version":5},"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/2311.11255/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":"2026-07-05T09:46:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"asYwl579ve4M9H4c/UKohox/yKU3WiGPK1mtwlUXwrt2v3tOKn1u6tns7tT84MBcphvLqaLGjevEs26xiMYUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:23:04.307820Z"},"content_sha256":"69116a7dc48c55369744302241fd0f75714452c38c720886c2d0d5a72ffddc01","schema_version":"1.0","event_id":"sha256:69116a7dc48c55369744302241fd0f75714452c38c720886c2d0d5a72ffddc01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSAYK3M3KMO4WTAGOJUXKGYLHI/bundle.json","state_url":"https://pith.science/pith/MSAYK3M3KMO4WTAGOJUXKGYLHI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSAYK3M3KMO4WTAGOJUXKGYLHI/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":"2026-08-09T23:23:04Z","links":{"resolver":"https://pith.science/pith/MSAYK3M3KMO4WTAGOJUXKGYLHI","bundle":"https://pith.science/pith/MSAYK3M3KMO4WTAGOJUXKGYLHI/bundle.json","state":"https://pith.science/pith/MSAYK3M3KMO4WTAGOJUXKGYLHI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSAYK3M3KMO4WTAGOJUXKGYLHI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MSAYK3M3KMO4WTAGOJUXKGYLHI","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":"c4f866057190994afca8a0cf2e8c5b8ae74601788211b5e79648430c96bd1793","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-19T06:50:52Z","title_canon_sha256":"021f2d9e2b27d48fcfe08fca1334564325975d373830509433e4d3153ef50020"},"schema_version":"1.0","source":{"id":"2311.11255","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11255","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11255v5","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11255","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"pith_short_12","alias_value":"MSAYK3M3KMO4","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"pith_short_16","alias_value":"MSAYK3M3KMO4WTAG","created_at":"2026-07-05T09:46:26Z"},{"alias_kind":"pith_short_8","alias_value":"MSAYK3M3","created_at":"2026-07-05T09:46:26Z"}],"graph_snapshots":[{"event_id":"sha256:69116a7dc48c55369744302241fd0f75714452c38c720886c2d0d5a72ffddc01","target":"graph","created_at":"2026-07-05T09:46:26Z","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/2311.11255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The current landscape of research leveraging large language models (LLMs) is experiencing a surge. Many works harness the powerful reasoning capabilities of these models to comprehend various modalities, such as text, speech, images, videos, etc. They also utilize LLMs to understand human intention and generate desired outputs like images, videos, and music. However, research that combines both understanding and generation using LLMs is still limited and in its nascent stage. To address this gap, we introduce a Multi-modal Music Understanding and Generation (M$^{2}$UGen) framework that integra","authors_text":"Atin Sakkeer Hussain, Chenshuo Sun, Qilong Wu, Shansong Liu, Ying Shan","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-19T06:50:52Z","title":"M$^{2}$UGen: Multi-modal Music Understanding and Generation with the Power of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11255","kind":"arxiv","version":5},"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:db40c0da3c001333c23eaec724b424be47f197240d13d344511239a41d9a0da5","target":"record","created_at":"2026-07-05T09:46:26Z","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":"c4f866057190994afca8a0cf2e8c5b8ae74601788211b5e79648430c96bd1793","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-19T06:50:52Z","title_canon_sha256":"021f2d9e2b27d48fcfe08fca1334564325975d373830509433e4d3153ef50020"},"schema_version":"1.0","source":{"id":"2311.11255","kind":"arxiv","version":5}},"canonical_sha256":"6481856d9b531dcb4c067269751b0b3a3a66d1a8f4563a69da042cb5092dfbf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6481856d9b531dcb4c067269751b0b3a3a66d1a8f4563a69da042cb5092dfbf7","first_computed_at":"2026-07-05T09:46:26.805142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:26.805142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZquBa2jj39Cnz1buQhhPO4RYvhbGnyRmzURUBwFOXpZ5Aj0fRX8pjxW7wECbOEu0pAEcIWRxrx2zG7GIphDIAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:26.805500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.11255","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db40c0da3c001333c23eaec724b424be47f197240d13d344511239a41d9a0da5","sha256:69116a7dc48c55369744302241fd0f75714452c38c720886c2d0d5a72ffddc01"],"state_sha256":"0f58c236ede239e1bb6f48f0171216fc9ef0b7345eba839e2f3675e8a56ba8e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOF3Wk3pN59kFc9qoNewRyNrHOdlA6pcbw3sKkiNpM69FtUnU05miCVD9Si+w9iCah5w+oVU2EfhHtvi0u+BAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:23:04.311405Z","bundle_sha256":"b37be68f97a7ad665dc9af3e95704fc9eda9e7843f24290e21f6c2f50ba62971"}}