{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:76LS5QBDKFUCEY4ZEY6AAURAEG","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":"85687c15bd2f6f64049e6da800137dde701ad942246c2edd2f45672490553ebd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T15:31:16Z","title_canon_sha256":"c60854e35711fcc916a12bb9c5c593265cde7206b133936d05cc6e6731994846"},"schema_version":"1.0","source":{"id":"2506.02997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02997","created_at":"2026-07-05T11:15:13Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02997v1","created_at":"2026-07-05T11:15:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02997","created_at":"2026-07-05T11:15:13Z"},{"alias_kind":"pith_short_12","alias_value":"76LS5QBDKFUC","created_at":"2026-07-05T11:15:13Z"},{"alias_kind":"pith_short_16","alias_value":"76LS5QBDKFUCEY4Z","created_at":"2026-07-05T11:15:13Z"},{"alias_kind":"pith_short_8","alias_value":"76LS5QBD","created_at":"2026-07-05T11:15:13Z"}],"graph_snapshots":[{"event_id":"sha256:66cac53a0c4d106ab7632ed94aa1268a809e93bd12840e578098cfb155593064","target":"graph","created_at":"2026-07-05T11:15:13Z","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/2506.02997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized masked-autoencoded style-rich representation as an intermediary. In the first stage, an autoregressive transformer is used for the conditional generation of these style-rich tokens from text and control signals. The second stage generates codec tokens from both text and sampled style-rich tokens. Experiments show that training the first-stage model on exten","authors_text":"Chunlei Zhang, Dong Yu, Hangting Chen, Yongqi Wang, Zhou Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T15:31:16Z","title":"Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02997","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":"sha256:0a9b066b05787d2aac0285405f3f39ec1a314af73bc440c46f78f6f70355061d","target":"record","created_at":"2026-07-05T11:15:13Z","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":"85687c15bd2f6f64049e6da800137dde701ad942246c2edd2f45672490553ebd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T15:31:16Z","title_canon_sha256":"c60854e35711fcc916a12bb9c5c593265cde7206b133936d05cc6e6731994846"},"schema_version":"1.0","source":{"id":"2506.02997","kind":"arxiv","version":1}},"canonical_sha256":"ff972ec0235168226399263c0052202190567820b1abcbe2a54cbb3f98d2217b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff972ec0235168226399263c0052202190567820b1abcbe2a54cbb3f98d2217b","first_computed_at":"2026-07-05T11:15:13.128666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:13.128666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rNhZskCC/wneBNwEpRZN71C/7w5ZORbXpU2yMAkA0ZM1D9DTzmgz1nuhFhtz5r194/gV36eb73/7vjtvfZDmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:13.129091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a9b066b05787d2aac0285405f3f39ec1a314af73bc440c46f78f6f70355061d","sha256:66cac53a0c4d106ab7632ed94aa1268a809e93bd12840e578098cfb155593064"],"state_sha256":"672db123c8ff3b73653c9b2164935269eae4fbc1187eaade48b204a721b50a62"}