{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZI73ZZXFEI2HLXCVFMITQMZM2T","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":"5b227c2324be2a3a70bcafdf8bb313f999d37b2cd4b502d2b8bae2ce1bc40464","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:33:40Z","title_canon_sha256":"29cbb0e0a92f8a186bd6d22eafc280d7123bada383a0770ba5c52d614144e9ec"},"schema_version":"1.0","source":{"id":"2506.21619","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21619","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21619v2","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21619","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"ZI73ZZXFEI2H","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"ZI73ZZXFEI2HLXCV","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"ZI73ZZXF","created_at":"2026-07-05T12:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:73e00089dc00d83288f6d371b20874149b254da6104a35ad239d6ecfbd7e3f41","target":"graph","created_at":"2026-07-05T12:03:49Z","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/2506.21619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing autoregressive large-scale text-to-speech (TTS) models have advantages in speech naturalness, but their token-by-token generation mechanism makes it difficult to precisely control the duration of synthesized speech. This becomes a significant limitation in applications requiring strict audio-visual synchronization, such as video dubbing. This paper introduces IndexTTS2, which proposes a novel, general, and autoregressive model-friendly method for speech duration control. The method supports two generation modes: one explicitly specifies the number of generated tokens to precisely cont","authors_text":"Jinchao Wang, Jingchen Shu, Siyi Zhou, Wei Deng, Xun Zhou, Yi He, Yiquan Zhou","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:33:40Z","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21619","kind":"arxiv","version":2},"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":"sha256:1238fedcc465fff35a5ede7856f28b86004081f8ef4732b9985966a4936a6aa7","target":"record","created_at":"2026-07-05T12:03:49Z","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":"5b227c2324be2a3a70bcafdf8bb313f999d37b2cd4b502d2b8bae2ce1bc40464","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:33:40Z","title_canon_sha256":"29cbb0e0a92f8a186bd6d22eafc280d7123bada383a0770ba5c52d614144e9ec"},"schema_version":"1.0","source":{"id":"2506.21619","kind":"arxiv","version":2}},"canonical_sha256":"ca3fbce6e5223475dc552b1138332cd4d701ac2878d57bf0c27d5cf9b49c9864","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca3fbce6e5223475dc552b1138332cd4d701ac2878d57bf0c27d5cf9b49c9864","first_computed_at":"2026-07-05T12:03:49.475486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:49.475486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ozRWoEwEyBUpUAgynhkaxOlBVcyG3n3qjU4bW070Dgf+hswLS0uTVM6G+Df2iGbmY9pD/X+XUp4WPFYZmd1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:49.476001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21619","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1238fedcc465fff35a5ede7856f28b86004081f8ef4732b9985966a4936a6aa7","sha256:73e00089dc00d83288f6d371b20874149b254da6104a35ad239d6ecfbd7e3f41"],"state_sha256":"112cfda989b7a01c0635f277b91cacd7d821ee7a1cd0d8b3ddc4e30f628a7fe0"}