{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CQYJC7QRQITL67AEX7QUVDG3YM","short_pith_number":"pith:CQYJC7QR","schema_version":"1.0","canonical_sha256":"1430917e118226bf7c04bfe14a8cdbc332928d801c51f9fa65d813d8ed852c05","source":{"kind":"arxiv","id":"2606.18072","version":1},"attestation_state":"computed","paper":{"title":"One-Step Token-to-Waveform Generation with MeanFlow in Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chunyat Wu, Guangyan Zhang, Haolin He, Jingyu Li, Qiuqiang Kong, Yiwen Guo, Zhen Ye, Zheqi Dai","submitted_at":"2026-06-16T15:40:37Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.18072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T15:40:37Z","cross_cats_sorted":[],"title_canon_sha256":"84a4951c5fcfe134942597e53658477d99bf8605aef5efcdaafaa11648c48477","abstract_canon_sha256":"531526e5a6382d4bdcb7b54a5ac69d756f8ed9f8fe0a78edf50f522c43f5cae8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:47.788778Z","signature_b64":"4gzPEb6WJuzP1kMTJoNBVDkKKWusEquTegdfCE8QKyYARC7ZgKOJijTkjakOpD+mV0tAD5kHaDiHObpZhDf2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1430917e118226bf7c04bfe14a8cdbc332928d801c51f9fa65d813d8ed852c05","last_reissued_at":"2026-06-19T16:10:47.788429Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:47.788429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Step Token-to-Waveform Generation with MeanFlow in Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chunyat Wu, Guangyan Zhang, Haolin He, Jingyu Li, Qiuqiang Kong, Yiwen Guo, Zhen Ye, Zheqi Dai","submitted_at":"2026-06-16T15:40:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18072","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.18072/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.18072","created_at":"2026-06-19T16:10:47.788489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18072v1","created_at":"2026-06-19T16:10:47.788489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18072","created_at":"2026-06-19T16:10:47.788489+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQYJC7QRQITL","created_at":"2026-06-19T16:10:47.788489+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQYJC7QRQITL67AE","created_at":"2026-06-19T16:10:47.788489+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQYJC7QR","created_at":"2026-06-19T16:10:47.788489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM","json":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM.json","graph_json":"https://pith.science/api/pith-number/CQYJC7QRQITL67AEX7QUVDG3YM/graph.json","events_json":"https://pith.science/api/pith-number/CQYJC7QRQITL67AEX7QUVDG3YM/events.json","paper":"https://pith.science/paper/CQYJC7QR"},"agent_actions":{"view_html":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM","download_json":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM.json","view_paper":"https://pith.science/paper/CQYJC7QR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18072&json=true","fetch_graph":"https://pith.science/api/pith-number/CQYJC7QRQITL67AEX7QUVDG3YM/graph.json","fetch_events":"https://pith.science/api/pith-number/CQYJC7QRQITL67AEX7QUVDG3YM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM/action/storage_attestation","attest_author":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM/action/author_attestation","sign_citation":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM/action/citation_signature","submit_replication":"https://pith.science/pith/CQYJC7QRQITL67AEX7QUVDG3YM/action/replication_record"}},"created_at":"2026-06-19T16:10:47.788489+00:00","updated_at":"2026-06-19T16:10:47.788489+00:00"}