{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KK2N2M46F6JO3M5ILNDU6XWDWM","short_pith_number":"pith:KK2N2M46","schema_version":"1.0","canonical_sha256":"52b4dd339e2f92edb3a85b474f5ec3b32ba022e31ac0980ad4b63ea7a60eef96","source":{"kind":"arxiv","id":"2211.11216","version":2},"attestation_state":"computed","paper":{"title":"Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Maosong Sun, Shangda Wu","submitted_at":"2022-11-21T07:19:17Z","abstract_excerpt":"Benefiting from large-scale datasets and pre-trained models, the field of generative models has recently gained significant momentum. However, most datasets for symbolic music are very small, which potentially limits the performance of data-driven multimodal models. An intuitive solution to this problem is to leverage pre-trained models from other modalities (e.g., natural language) to improve the performance of symbolic music-related multimodal tasks. In this paper, we carry out the first study of generating complete and semantically consistent symbolic music scores from text descriptions, an"},"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":"2211.11216","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-21T07:19:17Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"dbabc42142473b50dc702bbcc0adf8dbf363656356898dbabfa5ca280beed072","abstract_canon_sha256":"5588ca931cf9226527eff37f53f27148c2fea65e9e62c03296ffb99ed8f0802e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:33.106110Z","signature_b64":"5pqPPyJhHb7UnzzKPb57edbxt05pJ6MKENvhx29xMYKGKiOlp3jbdurgsF7f8UcJJY6fGBf1uodEdFQ7YJ1DDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b4dd339e2f92edb3a85b474f5ec3b32ba022e31ac0980ad4b63ea7a60eef96","last_reissued_at":"2026-07-05T05:30:33.105755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:33.105755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Maosong Sun, Shangda Wu","submitted_at":"2022-11-21T07:19:17Z","abstract_excerpt":"Benefiting from large-scale datasets and pre-trained models, the field of generative models has recently gained significant momentum. However, most datasets for symbolic music are very small, which potentially limits the performance of data-driven multimodal models. An intuitive solution to this problem is to leverage pre-trained models from other modalities (e.g., natural language) to improve the performance of symbolic music-related multimodal tasks. In this paper, we carry out the first study of generating complete and semantically consistent symbolic music scores from text descriptions, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11216","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/2211.11216/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":"2211.11216","created_at":"2026-07-05T05:30:33.105807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11216v2","created_at":"2026-07-05T05:30:33.105807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11216","created_at":"2026-07-05T05:30:33.105807+00:00"},{"alias_kind":"pith_short_12","alias_value":"KK2N2M46F6JO","created_at":"2026-07-05T05:30:33.105807+00:00"},{"alias_kind":"pith_short_16","alias_value":"KK2N2M46F6JO3M5I","created_at":"2026-07-05T05:30:33.105807+00:00"},{"alias_kind":"pith_short_8","alias_value":"KK2N2M46","created_at":"2026-07-05T05:30:33.105807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01022","citing_title":"Workflow-Based Evaluation of Music Generation Systems","ref_index":89,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM","json":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM.json","graph_json":"https://pith.science/api/pith-number/KK2N2M46F6JO3M5ILNDU6XWDWM/graph.json","events_json":"https://pith.science/api/pith-number/KK2N2M46F6JO3M5ILNDU6XWDWM/events.json","paper":"https://pith.science/paper/KK2N2M46"},"agent_actions":{"view_html":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM","download_json":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM.json","view_paper":"https://pith.science/paper/KK2N2M46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11216&json=true","fetch_graph":"https://pith.science/api/pith-number/KK2N2M46F6JO3M5ILNDU6XWDWM/graph.json","fetch_events":"https://pith.science/api/pith-number/KK2N2M46F6JO3M5ILNDU6XWDWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM/action/storage_attestation","attest_author":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM/action/author_attestation","sign_citation":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM/action/citation_signature","submit_replication":"https://pith.science/pith/KK2N2M46F6JO3M5ILNDU6XWDWM/action/replication_record"}},"created_at":"2026-07-05T05:30:33.105807+00:00","updated_at":"2026-07-05T05:30:33.105807+00:00"}