{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K6W7MAQYGWSHSKBPK5OVLWDOUQ","short_pith_number":"pith:K6W7MAQY","schema_version":"1.0","canonical_sha256":"57adf6021835a479282f575d55d86ea41b6ac5ff836033bac8f016ef5c98de4c","source":{"kind":"arxiv","id":"2308.11276","version":1},"attestation_state":"computed","paper":{"title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Atin Sakkeer Hussain, Chenshuo Sun, Shansong Liu, Ying Shan","submitted_at":"2023-08-22T08:43:33Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.11276","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-22T08:43:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"196867e9072bb82def15ccf3d74b7eabe640a73f5c1948bcf0c64477028321df","abstract_canon_sha256":"9e75c9f19a19908ec0bc15107b2016418e593c43d59b0aeb6e97d75a800f2b17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:32.136541Z","signature_b64":"zOpNbVHWdkZkLT6PBwiJDtnxp8VjUPI+a1dLnOx50kB0KJ82EX0nIoxptYg7CTTfEjOmTkoK3TkGDmyJ4SQKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57adf6021835a479282f575d55d86ea41b6ac5ff836033bac8f016ef5c98de4c","last_reissued_at":"2026-07-05T06:43:32.136112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:32.136112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Atin Sakkeer Hussain, Chenshuo Sun, Shansong Liu, Ying Shan","submitted_at":"2023-08-22T08:43:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11276","kind":"arxiv","version":1},"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/2308.11276/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.11276","created_at":"2026-07-05T06:43:32.136168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11276v1","created_at":"2026-07-05T06:43:32.136168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11276","created_at":"2026-07-05T06:43:32.136168+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6W7MAQYGWSH","created_at":"2026-07-05T06:43:32.136168+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6W7MAQYGWSHSKBP","created_at":"2026-07-05T06:43:32.136168+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6W7MAQY","created_at":"2026-07-05T06:43:32.136168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.13289","citing_title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ","json":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ.json","graph_json":"https://pith.science/api/pith-number/K6W7MAQYGWSHSKBPK5OVLWDOUQ/graph.json","events_json":"https://pith.science/api/pith-number/K6W7MAQYGWSHSKBPK5OVLWDOUQ/events.json","paper":"https://pith.science/paper/K6W7MAQY"},"agent_actions":{"view_html":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ","download_json":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ.json","view_paper":"https://pith.science/paper/K6W7MAQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11276&json=true","fetch_graph":"https://pith.science/api/pith-number/K6W7MAQYGWSHSKBPK5OVLWDOUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/K6W7MAQYGWSHSKBPK5OVLWDOUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ/action/storage_attestation","attest_author":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ/action/author_attestation","sign_citation":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ/action/citation_signature","submit_replication":"https://pith.science/pith/K6W7MAQYGWSHSKBPK5OVLWDOUQ/action/replication_record"}},"created_at":"2026-07-05T06:43:32.136168+00:00","updated_at":"2026-07-05T06:43:32.136168+00:00"}