{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7XU5COI3VWD2XVRY4MAY6YTJTM","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":"9a33bf14ec50ac56161a38991fbf5c604d9e0c9e6da4bb90ec7f1ec5d90d3c6a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-16T15:41:44Z","title_canon_sha256":"196c9d9c8f68c398732b6382e828de0dc29d82832f3e02548b3805294313a6fc"},"schema_version":"1.0","source":{"id":"2606.18323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18323","created_at":"2026-06-19T16:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18323v1","created_at":"2026-06-19T16:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18323","created_at":"2026-06-19T16:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"7XU5COI3VWD2","created_at":"2026-06-19T16:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"7XU5COI3VWD2XVRY","created_at":"2026-06-19T16:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"7XU5COI3","created_at":"2026-06-19T16:10:57Z"}],"graph_snapshots":[{"event_id":"sha256:a6dda3cac9e76584819533f3c5635c5f49987c2ef2ab288c4c8ffdd2420d2ecd","target":"graph","created_at":"2026-06-19T16:10:57Z","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/2606.18323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open autoregressive neural-codec text-to-speech (TTS) models sound excellent on typical inputs yet suffer stochastic catastrophic failures: on a meaningful fraction of utterances they emit silence, terminate early, or collapse into repetitive or hallucinated content. We show this failure mode is cheap to remove. Under a single format-robust metric (a catastrophic-failure rate via an ASR round-trip), best-of-N ASR self-verification drives failures to near-zero: no observed failures remain by N=2 on a standard corpus (LibriSpeech) and by N=4 on a hard prompt set. This is not an artifact of one m","authors_text":"Ali Asaria, Deep Gandhi, Tony Salomone","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-16T15:41:44Z","title":"Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18323","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:c5709cb69c810852df4acfd7e47d29b71dce93e4e78a83f26bd521f647b3ec29","target":"record","created_at":"2026-06-19T16:10:57Z","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":"9a33bf14ec50ac56161a38991fbf5c604d9e0c9e6da4bb90ec7f1ec5d90d3c6a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-16T15:41:44Z","title_canon_sha256":"196c9d9c8f68c398732b6382e828de0dc29d82832f3e02548b3805294313a6fc"},"schema_version":"1.0","source":{"id":"2606.18323","kind":"arxiv","version":1}},"canonical_sha256":"fde9d1391bad87abd638e3018f62699b1f90bda7a06ddb6e3af2147e86b9b871","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fde9d1391bad87abd638e3018f62699b1f90bda7a06ddb6e3af2147e86b9b871","first_computed_at":"2026-06-19T16:10:57.927449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:57.927449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x9tK1Ex+UXLOlQbpNpR97U5mOIJTYRkb0temOVte1PngSqMbaLIrfyaSvAvh7Q9612KxfAmmDl6Ra+cSTd0rAg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:57.927796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5709cb69c810852df4acfd7e47d29b71dce93e4e78a83f26bd521f647b3ec29","sha256:a6dda3cac9e76584819533f3c5635c5f49987c2ef2ab288c4c8ffdd2420d2ecd"],"state_sha256":"16879f030d0da39c2314cac899501a06433799a9e2d1d0c577b15161623d88e5"}