{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CQYJC7QRQITL67AEX7QUVDG3YM","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":"531526e5a6382d4bdcb7b54a5ac69d756f8ed9f8fe0a78edf50f522c43f5cae8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T15:40:37Z","title_canon_sha256":"84a4951c5fcfe134942597e53658477d99bf8605aef5efcdaafaa11648c48477"},"schema_version":"1.0","source":{"id":"2606.18072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18072","created_at":"2026-06-19T16:10:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18072v1","created_at":"2026-06-19T16:10:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18072","created_at":"2026-06-19T16:10:47Z"},{"alias_kind":"pith_short_12","alias_value":"CQYJC7QRQITL","created_at":"2026-06-19T16:10:47Z"},{"alias_kind":"pith_short_16","alias_value":"CQYJC7QRQITL67AE","created_at":"2026-06-19T16:10:47Z"},{"alias_kind":"pith_short_8","alias_value":"CQYJC7QR","created_at":"2026-06-19T16:10:47Z"}],"graph_snapshots":[{"event_id":"sha256:db554fb9b0d68039ff5c7aefa25ae487da45336f98dcab23e90b79a9d8dd1736","target":"graph","created_at":"2026-06-19T16:10:47Z","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/2606.18072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural audio codecs are central to modern LLM-based Text-to-Speech (TTS) and multimodal systems. As low-bitrate semantic codecs gain prominence, the Token-to-Waveform (Token2Wav) decoder becomes a bottleneck determining both perceptual quality and system efficiency. Conventional multi-step flow-matching decoders offer superior quality but suffer from high inference latency due to iterative sampling, creating a severe quality-speed trade-off. In this paper, we propose a novel Token2Wav architecture that overcomes this limitation by applying MeanFlow in a highly compressed latent space. By model","authors_text":"Chunyat Wu, Guangyan Zhang, Haolin He, Jingyu Li, Qiuqiang Kong, Yiwen Guo, Zhen Ye, Zheqi Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T15:40:37Z","title":"One-Step Token-to-Waveform Generation with MeanFlow in Latent Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18072","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":"sha256:22ee68a3738624600ebfedffe93175ecc732d25ac91a0e212e390c5558f95756","target":"record","created_at":"2026-06-19T16:10:47Z","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":"531526e5a6382d4bdcb7b54a5ac69d756f8ed9f8fe0a78edf50f522c43f5cae8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T15:40:37Z","title_canon_sha256":"84a4951c5fcfe134942597e53658477d99bf8605aef5efcdaafaa11648c48477"},"schema_version":"1.0","source":{"id":"2606.18072","kind":"arxiv","version":1}},"canonical_sha256":"1430917e118226bf7c04bfe14a8cdbc332928d801c51f9fa65d813d8ed852c05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1430917e118226bf7c04bfe14a8cdbc332928d801c51f9fa65d813d8ed852c05","first_computed_at":"2026-06-19T16:10:47.788429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:47.788429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4gzPEb6WJuzP1kMTJoNBVDkKKWusEquTegdfCE8QKyYARC7ZgKOJijTkjakOpD+mV0tAD5kHaDiHObpZhDf2DA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:47.788778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22ee68a3738624600ebfedffe93175ecc732d25ac91a0e212e390c5558f95756","sha256:db554fb9b0d68039ff5c7aefa25ae487da45336f98dcab23e90b79a9d8dd1736"],"state_sha256":"f9c9d589adca718e0113cc2d62c8c6537a7d2fe60f8fb3f5f6c98b06ac0baeb1"}