{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3I23ZJVKXQJHFNMUUWQGS4SHQH","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":"d338c1778c5c7fbfb30fda4cb2f158866ed1f329bb485ae7f26df4e0fcbe501e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-14T12:28:43Z","title_canon_sha256":"b9b78440b859522fd80e07809b4e8ede2cecf81d73728ad38e724b0321889e1a"},"schema_version":"1.0","source":{"id":"2607.12706","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12706","created_at":"2026-07-15T01:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12706v1","created_at":"2026-07-15T01:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12706","created_at":"2026-07-15T01:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"3I23ZJVKXQJH","created_at":"2026-07-15T01:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"3I23ZJVKXQJHFNMU","created_at":"2026-07-15T01:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"3I23ZJVK","created_at":"2026-07-15T01:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:1e3530b80df8fcaf67312427780e5b06b7e5c07cd80992a527a1242248ddd1b5","target":"graph","created_at":"2026-07-15T01:22:13Z","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/2607.12706/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art text-to-speech (TTS) models achieve impressive naturalness and expressiveness, yet fine-grained, disentangled control over speaking styles remains challenging. In professional scenarios such as film dubbing, game voice acting, and video content generation, users often need to modify a specific style category, such as emotion, age, or gender, while preserving all others. Existing style-controllable TTS methods typically rely on either text-described styles or speech-reference style transfer, making it difficult to jointly control explicit semantic attributes and preserve subtle","authors_text":"Chengkai Huang, Haowei Lou, Hye-Young Paik, Junda Wu, Lina Yao, Tong Yu, Wen Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-14T12:28:43Z","title":"AutoSIFT: Automatic Style Sifting for Controllable Speech Generation with Arbitrary Style Infilling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12706","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:fbdca1cea70488dcdbfee570fa849309e4c329c828555ca9d1565cf4446a629f","target":"record","created_at":"2026-07-15T01:22:13Z","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":"d338c1778c5c7fbfb30fda4cb2f158866ed1f329bb485ae7f26df4e0fcbe501e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-14T12:28:43Z","title_canon_sha256":"b9b78440b859522fd80e07809b4e8ede2cecf81d73728ad38e724b0321889e1a"},"schema_version":"1.0","source":{"id":"2607.12706","kind":"arxiv","version":1}},"canonical_sha256":"da35bca6aabc1272b594a5a069724781d47145a45a7f3f0b672a6c20f5399d3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da35bca6aabc1272b594a5a069724781d47145a45a7f3f0b672a6c20f5399d3d","first_computed_at":"2026-07-15T01:22:13.457306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:22:13.457306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VGEJn9qGmT9O4vcYH0yjZf9GWaHVX981k/owXHyIn/8oItubZAShcqiMonOYmroEAmu34+kzaYuoDDcxtSjaAA==","signature_status":"signed_v1","signed_at":"2026-07-15T01:22:13.458155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.12706","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbdca1cea70488dcdbfee570fa849309e4c329c828555ca9d1565cf4446a629f","sha256:1e3530b80df8fcaf67312427780e5b06b7e5c07cd80992a527a1242248ddd1b5"],"state_sha256":"1c4c0a237e900a630d1d5b024f6b7cc6c4d02d2476bf99abd060b2a8684f4ce2"}