{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LGXTNJ7JOSGRVSRQ2DOJVIWKJC","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":"2454ec888cbe8b8250f17bb10c63ad98bcf6d5f68bccf168d89a6984049d8d9a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T17:35:42Z","title_canon_sha256":"4c23e7ac7cbca2e32698bc5667d09cdcf0bfa42718ca677fbb84c020b8e0c17c"},"schema_version":"1.0","source":{"id":"2608.00011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00011","created_at":"2026-08-04T00:31:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00011v1","created_at":"2026-08-04T00:31:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00011","created_at":"2026-08-04T00:31:37Z"},{"alias_kind":"pith_short_12","alias_value":"LGXTNJ7JOSGR","created_at":"2026-08-04T00:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"LGXTNJ7JOSGRVSRQ","created_at":"2026-08-04T00:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"LGXTNJ7J","created_at":"2026-08-04T00:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:b9ec41a4b648b74fe734329f33230af1585b5df3fb1899f6486b79afaabe547c","target":"graph","created_at":"2026-08-04T00:31:37Z","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/2608.00011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current text-to-speech systems face a trade-off: autoregres- sive codec language models produce highly intelligible speech but require large-scale models and training data and decode tokens sequentially, while non-autoregressive approaches im- prove speed at the cost of linguistic accuracy. We present DLLM-TTS, a framework that formulates TTS as conditional block discrete diffusion over X-Codec2 neural audio codec to- kens. The model decomposes sequences into blocks and applies masked diffusion within each block while processing blocks se- quentially, learning both local acoustic coherence and","authors_text":"Akshat Mandloi, Apoorv Singh, Hamees Sayed, Nityanand Mathur, Sameer Khurana, Sudarshan Kamath, Wasim Madha","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T17:35:42Z","title":"DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00011","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:dbc05a7c064bcee6f34f9b090ae1fa9156b4b57a3b2c98ba8ef6112e7bd7924c","target":"record","created_at":"2026-08-04T00:31:37Z","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":"2454ec888cbe8b8250f17bb10c63ad98bcf6d5f68bccf168d89a6984049d8d9a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T17:35:42Z","title_canon_sha256":"4c23e7ac7cbca2e32698bc5667d09cdcf0bfa42718ca677fbb84c020b8e0c17c"},"schema_version":"1.0","source":{"id":"2608.00011","kind":"arxiv","version":1}},"canonical_sha256":"59af36a7e9748d1aca30d0dc9aa2ca489ce4e8394d73c91c17df3db44d1f6c1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59af36a7e9748d1aca30d0dc9aa2ca489ce4e8394d73c91c17df3db44d1f6c1c","first_computed_at":"2026-08-04T00:31:37.956993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:31:37.956993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AvAdfJ5nFVY0ilU4apY42ABNb6wHVqwJ2w9/vG4JRnCgsJRvOwO0JjL5hQ2HuokdbAT3OAVkl1lwna1Cxx7iCQ==","signature_status":"signed_v1","signed_at":"2026-08-04T00:31:37.958477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbc05a7c064bcee6f34f9b090ae1fa9156b4b57a3b2c98ba8ef6112e7bd7924c","sha256:b9ec41a4b648b74fe734329f33230af1585b5df3fb1899f6486b79afaabe547c"],"state_sha256":"a511c971804238535f8097f6755f1dcc993c0b1d2704a2c208a5bd124bd407ea"}