{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LTS6NFJWNH6JCHTG53HWC4ZEAW","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":"4444d7f60b73e0a73f3e90c11aaff3453cc39b806be9385632bf1bd3f7cfd71f","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-24T18:09:27Z","title_canon_sha256":"94049312614446d82c5076c95c56e074b659d12c220a36b0a432fbe5e2a117ba"},"schema_version":"1.0","source":{"id":"2405.15863","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15863","created_at":"2026-07-05T11:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15863v4","created_at":"2026-07-05T11:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15863","created_at":"2026-07-05T11:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"LTS6NFJWNH6J","created_at":"2026-07-05T11:22:30Z"},{"alias_kind":"pith_short_16","alias_value":"LTS6NFJWNH6JCHTG","created_at":"2026-07-05T11:22:30Z"},{"alias_kind":"pith_short_8","alias_value":"LTS6NFJW","created_at":"2026-07-05T11:22:30Z"}],"graph_snapshots":[{"event_id":"sha256:d60a7a5ccb6f9b43fcea12e3e190d9994b5ab1fd0757817846e54e79b7a2e276","target":"graph","created_at":"2026-07-05T11:22:30Z","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/2405.15863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation. Achieving high quality and diversity in this process demands extensive, high-quality data, which are often scarce in available datasets. Most open-source datasets frequently suffer from issues like low-quality waveforms and low text-audio consistency, hindering the advancement of music generation models. To address these challenges, we propose a novel quality-aware training paradigm for generating high-quality, high-musicality music from large-scale, quality-imba","authors_text":"Chang Li, Feng Ma, Jianqing Gao, Jun Du, Lijuan Liu, Ruoyu Wang, Yixuan Sun, Yuan Jiang, Zhenrong Zhang, Zilu Guo","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-24T18:09:27Z","title":"Quality-aware Masked Diffusion Transformer for Enhanced Music Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15863","kind":"arxiv","version":4},"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":"sha256:16772136662cc0d18279955da447f879a9967c6cdd9efc3c1393ccbefd2cd79d","target":"record","created_at":"2026-07-05T11:22:30Z","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":"4444d7f60b73e0a73f3e90c11aaff3453cc39b806be9385632bf1bd3f7cfd71f","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-24T18:09:27Z","title_canon_sha256":"94049312614446d82c5076c95c56e074b659d12c220a36b0a432fbe5e2a117ba"},"schema_version":"1.0","source":{"id":"2405.15863","kind":"arxiv","version":4}},"canonical_sha256":"5ce5e6953669fc911e66eecf61732405b94ac2767687d4f9730726ca1f710ca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ce5e6953669fc911e66eecf61732405b94ac2767687d4f9730726ca1f710ca1","first_computed_at":"2026-07-05T11:22:30.863890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:30.863890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kEHy4d7yScQSL9KdDX13ik7HTVfjAWrojPS8qAxmv7WRI/TIxzpJhN4AfLWO6j1L/2w2EkF9QJiNG+ZIeLCZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:30.864383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15863","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16772136662cc0d18279955da447f879a9967c6cdd9efc3c1393ccbefd2cd79d","sha256:d60a7a5ccb6f9b43fcea12e3e190d9994b5ab1fd0757817846e54e79b7a2e276"],"state_sha256":"8259f343bddbcedf98c76fdb86f9991a69ecf8b311b86d5e32028fd80992a219"}