{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IPGJGW7MBYCB2AG3LX5Y3IXAXB","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":"58f72e093af4a0204b40fc424e1dfad8bae88e63fe22600e4d270957b24cb69b","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-29T02:25:02Z","title_canon_sha256":"eceb1dc1b7bd0ab125b8583b2928d85a55b7b4324c0ea3536168bdd9c50c7fd0"},"schema_version":"1.0","source":{"id":"2605.30748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30748","created_at":"2026-06-01T01:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30748v1","created_at":"2026-06-01T01:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30748","created_at":"2026-06-01T01:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"IPGJGW7MBYCB","created_at":"2026-06-01T01:03:14Z"},{"alias_kind":"pith_short_16","alias_value":"IPGJGW7MBYCB2AG3","created_at":"2026-06-01T01:03:14Z"},{"alias_kind":"pith_short_8","alias_value":"IPGJGW7M","created_at":"2026-06-01T01:03:14Z"}],"graph_snapshots":[{"event_id":"sha256:b38103cb5d09b17f24898b826f7378e68adadf950556fd8caece44682d0837f0","target":"graph","created_at":"2026-06-01T01:03:14Z","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/2605.30748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Chatterbox-Flash, a zero-shot text-to-speech model obtained by fine-tuning a pretrained autoregressive TTS decoder into a block-diffusion decoder, enabling parallel token generation within each block while retaining block-by-block streaming. We find that naively transferring mainstream block-diffusion decoding to discrete speech tokens degrades quality, as a long-tail token distribution biases parallel position selection toward a few high-frequency tokens. To mitigate this without architectural modification, we introduce two inference-time techniques: prior-calibrated scoring, which","authors_text":"Deokjin Seo, Gangin Park, KiHyun Nam","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-29T02:25:02Z","title":"Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30748","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:b4a809f931dbdd72713a7b8fe3018ef2dcbd554bdfacb626fd09f8817e8e954f","target":"record","created_at":"2026-06-01T01:03:14Z","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":"58f72e093af4a0204b40fc424e1dfad8bae88e63fe22600e4d270957b24cb69b","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-29T02:25:02Z","title_canon_sha256":"eceb1dc1b7bd0ab125b8583b2928d85a55b7b4324c0ea3536168bdd9c50c7fd0"},"schema_version":"1.0","source":{"id":"2605.30748","kind":"arxiv","version":1}},"canonical_sha256":"43cc935bec0e041d00db5dfb8da2e0b85810ca2f343769c4bbba020546f586ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43cc935bec0e041d00db5dfb8da2e0b85810ca2f343769c4bbba020546f586ee","first_computed_at":"2026-06-01T01:03:14.045467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:14.045467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Chr/DIjsTVyiuPyPtqLSdDF6q+27FYmU0Np8ySLJuo6ADJvv3KjdGBMHV12bS9XkxsULPTn0gttat1glwRkBA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:14.046279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4a809f931dbdd72713a7b8fe3018ef2dcbd554bdfacb626fd09f8817e8e954f","sha256:b38103cb5d09b17f24898b826f7378e68adadf950556fd8caece44682d0837f0"],"state_sha256":"866f6148e2cd6a5df94586dad0129f05efb6e1fd68abc4b7e3e4d335e09fe75c"}