{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RAO7V3YYIQF5M4RCWHC3JT4EG6","short_pith_number":"pith:RAO7V3YY","schema_version":"1.0","canonical_sha256":"881dfaef18440bd67222b1c5b4cf8437a019db822a24dbf638d8da1c980c18cd","source":{"kind":"arxiv","id":"2606.07080","version":1},"attestation_state":"computed","paper":{"title":"dots.tts Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Changtao Li, Colin Zhang, Da Zheng, Hankun Wang, Junfeng Tian, Kai Yu, Shi Lian, Yufeng Ma","submitted_at":"2026-06-05T09:19:24Z","abstract_excerpt":"We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are threefold. First, we train an AudioVAE with multiple objectives to build a semantically structured and prediction-friendly continuous speech space. Second, we use full-history conditioning in the flow-matching head to preserve long-range consistency and reduce drift during generation. Third, we apply reward-free self-corrective post-training to the flow-matching head "},"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":"2606.07080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T09:19:24Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"7f9d3096d117935d684683d141f3f49f518c90f71d05a19a688dfb59d2abd6bb","abstract_canon_sha256":"5925c73101ab47e6ae0e97b897541228338ed05e9d7365d786a73a9c6bbff806"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:45.052555Z","signature_b64":"pdRSAbEvu+lIbDHPUAQZpHj6mhk7XfMQL5cxZYEMRGQos+0jQ5gZW0CCqQLj0qNd+Fw09bybEKZePs/bxof5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"881dfaef18440bd67222b1c5b4cf8437a019db822a24dbf638d8da1c980c18cd","last_reissued_at":"2026-06-08T01:04:45.052126Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:45.052126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"dots.tts Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Changtao Li, Colin Zhang, Da Zheng, Hankun Wang, Junfeng Tian, Kai Yu, Shi Lian, Yufeng Ma","submitted_at":"2026-06-05T09:19:24Z","abstract_excerpt":"We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are threefold. First, we train an AudioVAE with multiple objectives to build a semantically structured and prediction-friendly continuous speech space. Second, we use full-history conditioning in the flow-matching head to preserve long-range consistency and reduce drift during generation. Third, we apply reward-free self-corrective post-training to the flow-matching head "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07080","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/2606.07080/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":"2606.07080","created_at":"2026-06-08T01:04:45.052178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07080v1","created_at":"2026-06-08T01:04:45.052178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07080","created_at":"2026-06-08T01:04:45.052178+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAO7V3YYIQF5","created_at":"2026-06-08T01:04:45.052178+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAO7V3YYIQF5M4RC","created_at":"2026-06-08T01:04:45.052178+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAO7V3YY","created_at":"2026-06-08T01:04:45.052178+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/RAO7V3YYIQF5M4RCWHC3JT4EG6","json":"https://pith.science/pith/RAO7V3YYIQF5M4RCWHC3JT4EG6.json","graph_json":"https://pith.science/api/pith-number/RAO7V3YYIQF5M4RCWHC3JT4EG6/graph.json","events_json":"https://pith.science/api/pith-number/RAO7V3YYIQF5M4RCWHC3JT4EG6/events.json","paper":"https://pith.science/paper/RAO7V3YY"},"agent_actions":{"view_html":"https://pith.science/pith/RAO7V3YYIQF5M4RCWHC3JT4EG6","download_json":"https://pith.science/pith/RAO7V3YYIQF5M4RCWHC3JT4EG6.json","view_paper":"https://pith.science/paper/RAO7V3YY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07080&json=true","fetch_graph":"https://pith.science/api/pith-number/RAO7V3YYIQF5M4RCWHC3JT4EG6/graph.json","fetch_events":"https://pith.science/api/pith-number/RAO7V3YYIQF5M4RCWHC3JT4EG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAO7V3YYIQF5M4RCWHC3JT4EG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAO7V3YYIQF5M4RCWHC3JT4EG6/action/storage_attestation","attest_author":"https://pith.science/pith/RAO7V3YYIQF5M4RCWHC3JT4EG6/action/author_attestation","sign_citation":"https://pith.science/pith/RAO7V3YYIQF5M4RCWHC3JT4EG6/action/citation_signature","submit_replication":"https://pith.science/pith/RAO7V3YYIQF5M4RCWHC3JT4EG6/action/replication_record"}},"created_at":"2026-06-08T01:04:45.052178+00:00","updated_at":"2026-06-08T01:04:45.052178+00:00"}