{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K6W7MAQYGWSHSKBPK5OVLWDOUQ","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":"9e75c9f19a19908ec0bc15107b2016418e593c43d59b0aeb6e97d75a800f2b17","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-22T08:43:33Z","title_canon_sha256":"196867e9072bb82def15ccf3d74b7eabe640a73f5c1948bcf0c64477028321df"},"schema_version":"1.0","source":{"id":"2308.11276","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11276","created_at":"2026-07-05T06:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11276v1","created_at":"2026-07-05T06:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11276","created_at":"2026-07-05T06:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"K6W7MAQYGWSH","created_at":"2026-07-05T06:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"K6W7MAQYGWSHSKBP","created_at":"2026-07-05T06:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"K6W7MAQY","created_at":"2026-07-05T06:43:32Z"}],"graph_snapshots":[{"event_id":"sha256:46322389668b259e87dad6b8f036c0d317870bf6659eace7277ea75e4ce2d671","target":"graph","created_at":"2026-07-05T06:43:32Z","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/2308.11276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-music generation (T2M-Gen) faces a major obstacle due to the scarcity of large-scale publicly available music datasets with natural language captions. To address this, we propose the Music Understanding LLaMA (MU-LLaMA), capable of answering music-related questions and generating captions for music files. Our model utilizes audio representations from a pretrained MERT model to extract music features. However, obtaining a suitable dataset for training the MU-LLaMA model remains challenging, as existing publicly accessible audio question answering datasets lack the necessary depth for op","authors_text":"Atin Sakkeer Hussain, Chenshuo Sun, Shansong Liu, Ying Shan","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-22T08:43:33Z","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11276","kind":"arxiv","version":1},"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:ca1e79d1428c8148682eb6a2cc15ab6422d27586ce99bddc3d5cc935194f7a2d","target":"record","created_at":"2026-07-05T06:43:32Z","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":"9e75c9f19a19908ec0bc15107b2016418e593c43d59b0aeb6e97d75a800f2b17","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-22T08:43:33Z","title_canon_sha256":"196867e9072bb82def15ccf3d74b7eabe640a73f5c1948bcf0c64477028321df"},"schema_version":"1.0","source":{"id":"2308.11276","kind":"arxiv","version":1}},"canonical_sha256":"57adf6021835a479282f575d55d86ea41b6ac5ff836033bac8f016ef5c98de4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57adf6021835a479282f575d55d86ea41b6ac5ff836033bac8f016ef5c98de4c","first_computed_at":"2026-07-05T06:43:32.136112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:32.136112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zOpNbVHWdkZkLT6PBwiJDtnxp8VjUPI+a1dLnOx50kB0KJ82EX0nIoxptYg7CTTfEjOmTkoK3TkGDmyJ4SQKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:32.136541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11276","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca1e79d1428c8148682eb6a2cc15ab6422d27586ce99bddc3d5cc935194f7a2d","sha256:46322389668b259e87dad6b8f036c0d317870bf6659eace7277ea75e4ce2d671"],"state_sha256":"95dad763abb82af72c3b0c73e071d7b2ed220f16dfd6b912937550e9f5bcdb64"}