{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TSMOJEVXKAEXX4V22KU67KV7H3","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":"9102c5a06f2b55e39b1cd4994cb8491825bf323776a94c13994d902e97615dd4","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-12T04:19:49Z","title_canon_sha256":"7e17cd407c2ba226b2e26d249d5beaef5c0b45518490af5c68b7096cab4bc180"},"schema_version":"1.0","source":{"id":"2305.07243","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07243","created_at":"2026-07-05T06:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07243v2","created_at":"2026-07-05T06:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07243","created_at":"2026-07-05T06:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"TSMOJEVXKAEX","created_at":"2026-07-05T06:13:20Z"},{"alias_kind":"pith_short_16","alias_value":"TSMOJEVXKAEXX4V2","created_at":"2026-07-05T06:13:20Z"},{"alias_kind":"pith_short_8","alias_value":"TSMOJEVX","created_at":"2026-07-05T06:13:20Z"}],"graph_snapshots":[{"event_id":"sha256:4ab5a5be777ee7cf520b3af5f4bfe4a11b614897ba34d9815c0c9edfc8230b9f","target":"graph","created_at":"2026-07-05T06:13:20Z","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/2305.07243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, the field of image generation has been revolutionized by the application of autoregressive transformers and DDPMs. These approaches model the process of image generation as a step-wise probabilistic processes and leverage large amounts of compute and data to learn the image distribution. This methodology of improving performance need not be confined to images. This paper describes a way to apply advances in the image generative domain to speech synthesis. The result is TorToise -- an expressive, multi-voice text-to-speech system.\n  All model code and trained weights have been ","authors_text":"James Betker","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-12T04:19:49Z","title":"Better speech synthesis through scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07243","kind":"arxiv","version":2},"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":"sha256:0fe740a30dcb1775385bad9b5770dd819b37cc9a1194dba43ba43f56a0bf034d","target":"record","created_at":"2026-07-05T06:13:20Z","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":"9102c5a06f2b55e39b1cd4994cb8491825bf323776a94c13994d902e97615dd4","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-12T04:19:49Z","title_canon_sha256":"7e17cd407c2ba226b2e26d249d5beaef5c0b45518490af5c68b7096cab4bc180"},"schema_version":"1.0","source":{"id":"2305.07243","kind":"arxiv","version":2}},"canonical_sha256":"9c98e492b750097bf2bad2a9efaabf3ee7e25dac917b4698874a09f60ca1bf95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c98e492b750097bf2bad2a9efaabf3ee7e25dac917b4698874a09f60ca1bf95","first_computed_at":"2026-07-05T06:13:20.976063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:20.976063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"buh/DTK6JHe8G+oDbuYhERBMG0LTf1xZBSZ0hmvnIN4nBw4fgaLEI9jEJoy3jgNQIlCkPlMxAljr0RQG2rsSCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:20.976464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07243","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fe740a30dcb1775385bad9b5770dd819b37cc9a1194dba43ba43f56a0bf034d","sha256:4ab5a5be777ee7cf520b3af5f4bfe4a11b614897ba34d9815c0c9edfc8230b9f"],"state_sha256":"bf45f70b8dbb9fc1e76849173909731813c14d4a7afd27b6e0badf32e8bec785"}