{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CUBBUHJAOY5KWI6Q46UVZXLN4Y","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":"c462772e79f75b54a6c04930b774c9202b34e1ffa61c169c22ffeef05263c25d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-05T06:45:47Z","title_canon_sha256":"b1fb7da9b85ba71be48f773af75284c031285e590fe90d3422c9c67d7f215e1d"},"schema_version":"1.0","source":{"id":"2607.04140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04140","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04140v1","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04140","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"CUBBUHJAOY5K","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"CUBBUHJAOY5KWI6Q","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"CUBBUHJA","created_at":"2026-07-07T02:18:59Z"}],"graph_snapshots":[{"event_id":"sha256:e6df2e6b2a5930fa12da1a1682a0d6ab1c257730e5890b5055bd6930b3095621","target":"graph","created_at":"2026-07-07T02:18:59Z","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/2607.04140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive (AR) text-to-speech (TTS) models generate discrete speech tokens sequentially, which makes inference slow and can degrade robustness by propagating local errors and hallucinations. This limitation stems from their left-to-right AR commitment: each token must be determined before future speech-token context is available. However, such ordering is not an inherent requirement for TTS, as the full input text is available before synthesis. In this paper, we introduce DELTA-TTS, a lightweight LoRA-based adaptation framework that converts a pretrained AR TTS model into a discrete diffu","authors_text":"Heeseung Kim, Hoseong Ahn, Junwon Moon, Kyuhong Shim, Seungbeom Kim, Sewoong Park, Yejin Lee","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-05T06:45:47Z","title":"DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04140","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":"sha256:8e2b23c1c2728244e013079ceff86363c197a481dcf778dad099f4ccae62cb21","target":"record","created_at":"2026-07-07T02:18:59Z","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":"c462772e79f75b54a6c04930b774c9202b34e1ffa61c169c22ffeef05263c25d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-05T06:45:47Z","title_canon_sha256":"b1fb7da9b85ba71be48f773af75284c031285e590fe90d3422c9c67d7f215e1d"},"schema_version":"1.0","source":{"id":"2607.04140","kind":"arxiv","version":1}},"canonical_sha256":"15021a1d20763aab23d0e7a95cdd6de6313e4b49410e632178697fa126f20ff9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15021a1d20763aab23d0e7a95cdd6de6313e4b49410e632178697fa126f20ff9","first_computed_at":"2026-07-07T02:18:59.326975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:59.326975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZQVfYrUYW9GTdYg9PKUcWBb3vc3BanwcyNUjjGuAECVYu5irLWJ450m9GLp74slbNqBqd0Glxu1MbezaMmOCCg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:59.327778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e2b23c1c2728244e013079ceff86363c197a481dcf778dad099f4ccae62cb21","sha256:e6df2e6b2a5930fa12da1a1682a0d6ab1c257730e5890b5055bd6930b3095621"],"state_sha256":"277f20716ba756949aa4f26ea50711be30536fe34f479245a74fd0245ed9aee9"}