{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EADPR5OK25HZZTIETQRKLACQ7Y","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":"831eeb251eee4a16b06aecee054a4e7bf1cf42f8fc0b743c244e04af2162ebd9","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-03T07:22:06Z","title_canon_sha256":"0f7a03305f1ee6be4080dbc38a073701537d3d7442163afac730f12ed7b33622"},"schema_version":"1.0","source":{"id":"2507.02380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02380","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02380v1","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02380","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"pith_short_12","alias_value":"EADPR5OK25HZ","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"pith_short_16","alias_value":"EADPR5OK25HZZTIE","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"pith_short_8","alias_value":"EADPR5OK","created_at":"2026-07-05T11:31:17Z"}],"graph_snapshots":[{"event_id":"sha256:1ef0e153232a7c340f2a98d4b7cc3f11c638142ad99e41b475f7077cc3dcbb29","target":"graph","created_at":"2026-07-05T11:31:17Z","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/2507.02380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"JoyTTS is an end-to-end spoken chatbot that combines large language models (LLM) with text-to-speech (TTS) technology, featuring voice cloning capabilities. This project is built upon the open-source MiniCPM-o and CosyVoice2 models and trained on 2000 hours of conversational data. We have also provided the complete training code to facilitate further development and optimization by the community. On the testing machine seed-tts-zh, it achieves a SS (speaker similarity) score of 0.73 and a WER (Word Error Rate) of 5.09. The code and models, along with training and inference scripts, are availab","authors_text":"Fangru Zhou, Guoxin Wang, Jun Zhao","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-03T07:22:06Z","title":"JoyTTS: LLM-based Spoken Chatbot With Voice Cloning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02380","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:bfbb7fcc81d0da44ec6f3569b338ba76ca38cf55791eca215fb612c8f6ae3387","target":"record","created_at":"2026-07-05T11:31:17Z","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":"831eeb251eee4a16b06aecee054a4e7bf1cf42f8fc0b743c244e04af2162ebd9","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-03T07:22:06Z","title_canon_sha256":"0f7a03305f1ee6be4080dbc38a073701537d3d7442163afac730f12ed7b33622"},"schema_version":"1.0","source":{"id":"2507.02380","kind":"arxiv","version":1}},"canonical_sha256":"2006f8f5cad74f9ccd049c22a58050fe0f2399ab097dfccfcf769b0ac46a5d3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2006f8f5cad74f9ccd049c22a58050fe0f2399ab097dfccfcf769b0ac46a5d3a","first_computed_at":"2026-07-05T11:31:17.235122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:17.235122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B7TuzXit12xwm11tdk/g7XxTMBotJ/XMLyK72XB5cLEeO6YPhOaL2l0Z/8vow1qKlZUA66MAvpnBuK6QKgi4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:17.235736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfbb7fcc81d0da44ec6f3569b338ba76ca38cf55791eca215fb612c8f6ae3387","sha256:1ef0e153232a7c340f2a98d4b7cc3f11c638142ad99e41b475f7077cc3dcbb29"],"state_sha256":"255cb7652e7fdd49241cb0573379b2caecc186b03d4eb82049fd74b749620b61"}