{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XXK2GUWA5VTQT3Z7EBINLXVKPD","short_pith_number":"pith:XXK2GUWA","schema_version":"1.0","canonical_sha256":"bdd5a352c0ed6709ef3f2050d5deaa78e0574351b1f4b62407fec3ab246e9f9e","source":{"kind":"arxiv","id":"2504.03289","version":1},"attestation_state":"computed","paper":{"title":"RWKVTTS: Yet another TTS based on RWKV-7","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lin Yueyu, Liu Xiao","submitted_at":"2025-04-04T09:17:20Z","abstract_excerpt":"Human-AI interaction thrives on intuitive and efficient interfaces, among which voice stands out as a particularly natural and accessible modality. Recent advancements in transformer-based text-to-speech (TTS) systems, such as Fish-Speech, CosyVoice, and MegaTTS 3, have delivered remarkable improvements in quality and realism, driving a significant evolution in the TTS domain. In this paper, we introduce RWKV-7 \\cite{peng2025rwkv}, a cutting-edge RNN-based architecture tailored for TTS applications. Unlike traditional transformer models, RWKV-7 leverages the strengths of recurrent neural netwo"},"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":"2504.03289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-04T09:17:20Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"edd36c525888224dc7d4544507d2202cade3698031fbc24af67010ec33cf5804","abstract_canon_sha256":"0964c64af22dff10c457fdad0d3f3ce9d4c35c4b3d43d001693daecaf351c688"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:29.512519Z","signature_b64":"FMEp9ULlDvwEPev76we34M1JTE7rzt+WQ0HXEDEXTEUhgsSuJRVa0JcM6Q4XWur1g2DgB7y3JF1uKb7Q0y2PCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdd5a352c0ed6709ef3f2050d5deaa78e0574351b1f4b62407fec3ab246e9f9e","last_reissued_at":"2026-07-05T10:44:29.512039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:29.512039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RWKVTTS: Yet another TTS based on RWKV-7","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lin Yueyu, Liu Xiao","submitted_at":"2025-04-04T09:17:20Z","abstract_excerpt":"Human-AI interaction thrives on intuitive and efficient interfaces, among which voice stands out as a particularly natural and accessible modality. Recent advancements in transformer-based text-to-speech (TTS) systems, such as Fish-Speech, CosyVoice, and MegaTTS 3, have delivered remarkable improvements in quality and realism, driving a significant evolution in the TTS domain. In this paper, we introduce RWKV-7 \\cite{peng2025rwkv}, a cutting-edge RNN-based architecture tailored for TTS applications. Unlike traditional transformer models, RWKV-7 leverages the strengths of recurrent neural netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03289","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/2504.03289/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":"2504.03289","created_at":"2026-07-05T10:44:29.512101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03289v1","created_at":"2026-07-05T10:44:29.512101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03289","created_at":"2026-07-05T10:44:29.512101+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXK2GUWA5VTQ","created_at":"2026-07-05T10:44:29.512101+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXK2GUWA5VTQT3Z7","created_at":"2026-07-05T10:44:29.512101+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXK2GUWA","created_at":"2026-07-05T10:44:29.512101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02167","citing_title":"AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD","json":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD.json","graph_json":"https://pith.science/api/pith-number/XXK2GUWA5VTQT3Z7EBINLXVKPD/graph.json","events_json":"https://pith.science/api/pith-number/XXK2GUWA5VTQT3Z7EBINLXVKPD/events.json","paper":"https://pith.science/paper/XXK2GUWA"},"agent_actions":{"view_html":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD","download_json":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD.json","view_paper":"https://pith.science/paper/XXK2GUWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03289&json=true","fetch_graph":"https://pith.science/api/pith-number/XXK2GUWA5VTQT3Z7EBINLXVKPD/graph.json","fetch_events":"https://pith.science/api/pith-number/XXK2GUWA5VTQT3Z7EBINLXVKPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD/action/storage_attestation","attest_author":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD/action/author_attestation","sign_citation":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD/action/citation_signature","submit_replication":"https://pith.science/pith/XXK2GUWA5VTQT3Z7EBINLXVKPD/action/replication_record"}},"created_at":"2026-07-05T10:44:29.512101+00:00","updated_at":"2026-07-05T10:44:29.512101+00:00"}