{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:76LS5QBDKFUCEY4ZEY6AAURAEG","short_pith_number":"pith:76LS5QBD","canonical_record":{"source":{"id":"2506.02997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T15:31:16Z","cross_cats_sorted":[],"title_canon_sha256":"c60854e35711fcc916a12bb9c5c593265cde7206b133936d05cc6e6731994846","abstract_canon_sha256":"85687c15bd2f6f64049e6da800137dde701ad942246c2edd2f45672490553ebd"},"schema_version":"1.0"},"canonical_sha256":"ff972ec0235168226399263c0052202190567820b1abcbe2a54cbb3f98d2217b","source":{"kind":"arxiv","id":"2506.02997","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:76LS5QBDKFUCEY4ZEY6AAURAEG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T15:31:16Z","cross_cats_sorted":[],"title_canon_sha256":"c60854e35711fcc916a12bb9c5c593265cde7206b133936d05cc6e6731994846","abstract_canon_sha256":"85687c15bd2f6f64049e6da800137dde701ad942246c2edd2f45672490553ebd"},"schema_version":"1.0"},"canonical_sha256":"ff972ec0235168226399263c0052202190567820b1abcbe2a54cbb3f98d2217b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:13.129091Z","signature_b64":"rNhZskCC/wneBNwEpRZN71C/7w5ZORbXpU2yMAkA0ZM1D9DTzmgz1nuhFhtz5r194/gV36eb73/7vjtvfZDmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff972ec0235168226399263c0052202190567820b1abcbe2a54cbb3f98d2217b","last_reissued_at":"2026-07-05T11:15:13.128666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:13.128666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02997","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"APBdTPcODxPA7pYm7o80FE1Z/ExUcpx1cLB/cgdqIjoBmAAG6VsHnBbl4v61wjHfq/7XaCkvcFBhhSWEgZofDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:31:41.785467Z"},"content_sha256":"0a9b066b05787d2aac0285405f3f39ec1a314af73bc440c46f78f6f70355061d","schema_version":"1.0","event_id":"sha256:0a9b066b05787d2aac0285405f3f39ec1a314af73bc440c46f78f6f70355061d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:76LS5QBDKFUCEY4ZEY6AAURAEG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chunlei Zhang, Dong Yu, Hangting Chen, Yongqi Wang, Zhou Zhao","submitted_at":"2025-06-03T15:31:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02997","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/2506.02997/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vrZGNQ5puFMpihnvkvaTATQAj4lH/Z8IP4tHI5ILktUJlMYN5XZmpMe8Dij8EPjbwwVWYVK5Ui3SGAOBsrNEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:31:41.785970Z"},"content_sha256":"66cac53a0c4d106ab7632ed94aa1268a809e93bd12840e578098cfb155593064","schema_version":"1.0","event_id":"sha256:66cac53a0c4d106ab7632ed94aa1268a809e93bd12840e578098cfb155593064"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/bundle.json","state_url":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T02:31:41Z","links":{"resolver":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG","bundle":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/bundle.json","state":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBwAd0GZNzkv62i4kcVnFeIaMrzAVjKLa2UxDBOc92yqvfqLYSks2DEElgiEJTFR6Y7+Jh8ykXJBlXEhXgwNAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:31:41.789294Z","bundle_sha256":"94b7585152a643331782d47846f59a9d168dfefaf9786c77ee2437ea3b6f247f"}}