{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ADSSIOZNYONMDAL5K5Y3PH2XPT","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":"b252b594419b39cd758c8626cd23cf072ae249dedb742e1d82aa463785af20c2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-04-14T16:03:21Z","title_canon_sha256":"cb31c851b70abb9a4a56c4201b1cdc12b7290381e342f997c1131ed27db706fb"},"schema_version":"1.0","source":{"id":"2504.10352","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10352","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10352v3","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10352","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_12","alias_value":"ADSSIOZNYONM","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_16","alias_value":"ADSSIOZNYONMDAL5","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_8","alias_value":"ADSSIOZN","created_at":"2026-07-05T11:48:48Z"}],"graph_snapshots":[{"event_id":"sha256:ee66e0fd794687a141e7b182c9749d25ab810b77304c93f1ee72128cd56516cf","target":"graph","created_at":"2026-07-05T11:48:48Z","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/2504.10352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent zero-shot text-to-speech (TTS) systems face a common dilemma: autoregressive (AR) models suffer from slow generation and lack duration controllability, while non-autoregressive (NAR) models lack temporal modeling and typically require complex designs. In this paper, we introduce a novel pseudo-autoregressive (PAR) codec language modeling approach that unifies AR and NAR modeling. Combining explicit temporal modeling from AR with parallel generation from NAR, PAR generates dynamic-length spans at fixed time steps. Building on PAR, we propose PALLE, a two-stage TTS system that leverages P","authors_text":"Haibin Wu, Haiyang Sun, Hui Wang, Jianwei Yu, Jinyu Li, Kai Yu, Lingwei Meng, Shujie Liu, Xie Chen, Yan Lu, Yanqing Liu, Yifan Yang, Yuxuan Hu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-04-14T16:03:21Z","title":"Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10352","kind":"arxiv","version":3},"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":"sha256:039311aafa8a59ad7f793cedc96ea6b408f960e0eefedd06f3fe9aae40c4af35","target":"record","created_at":"2026-07-05T11:48:48Z","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":"b252b594419b39cd758c8626cd23cf072ae249dedb742e1d82aa463785af20c2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-04-14T16:03:21Z","title_canon_sha256":"cb31c851b70abb9a4a56c4201b1cdc12b7290381e342f997c1131ed27db706fb"},"schema_version":"1.0","source":{"id":"2504.10352","kind":"arxiv","version":3}},"canonical_sha256":"00e5243b2dc39ac1817d5771b79f577cf8f0c02e165b3046114ee244098ff84e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00e5243b2dc39ac1817d5771b79f577cf8f0c02e165b3046114ee244098ff84e","first_computed_at":"2026-07-05T11:48:48.653178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:48.653178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fkeu0q7igc+mk5ji74cfwbWexyZw1Ru5IEbQgER4w/j5ehhr0V6Q1YSsp8awvHbsy/YUQayJFvi/gxPlrRSJAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:48.653858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.10352","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:039311aafa8a59ad7f793cedc96ea6b408f960e0eefedd06f3fe9aae40c4af35","sha256:ee66e0fd794687a141e7b182c9749d25ab810b77304c93f1ee72128cd56516cf"],"state_sha256":"efb8bb2c3ab2292ddc31707d0f1c3a40cd7fbc34d895238cc7e949f57f3ba5e7"}