{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3R5AFDRKESZXTF3WGXZDICLXO5","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":"62da06ffd83b3b1d9da23854a26ad2eb547264fd2eb4ed9525f1cb54cbd330a1","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-07T16:22:59Z","title_canon_sha256":"a583abed5c46a11b0ac43ac306db686e803a6f2db3ae4dda893384bb474c87f4"},"schema_version":"1.0","source":{"id":"2607.06461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06461","created_at":"2026-07-08T01:19:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06461v1","created_at":"2026-07-08T01:19:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06461","created_at":"2026-07-08T01:19:26Z"},{"alias_kind":"pith_short_12","alias_value":"3R5AFDRKESZX","created_at":"2026-07-08T01:19:26Z"},{"alias_kind":"pith_short_16","alias_value":"3R5AFDRKESZXTF3W","created_at":"2026-07-08T01:19:26Z"},{"alias_kind":"pith_short_8","alias_value":"3R5AFDRK","created_at":"2026-07-08T01:19:26Z"}],"graph_snapshots":[{"event_id":"sha256:c3b240c32759d2399e7f1a59e0ac029180b45548fc97cd8b754b068bd14871bf","target":"graph","created_at":"2026-07-08T01:19:26Z","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/2607.06461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenarios demanding precise stylistic interventions and strict temporal alignment, such as audiobook narration and video dubbing, the inability to explicitly manipulate word-level acoustic attributes remains a critical bottleneck. This limitation is primarily amplified by the severe scarcity of fine-grained annotated datasets and the architectural challenge of integrating mul","authors_text":"Chengbin Jin, Deyi Tuo, Jialong Mai, Jinxin Ji, Sihang Nie, Xiangmin Xu, Xiaofen Xing","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-07T16:22:59Z","title":"WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06461","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:ac53903e3eb34b724ba5423100efbe9c288ea56803c0c8a47f8ee335c3a45630","target":"record","created_at":"2026-07-08T01:19:26Z","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":"62da06ffd83b3b1d9da23854a26ad2eb547264fd2eb4ed9525f1cb54cbd330a1","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-07T16:22:59Z","title_canon_sha256":"a583abed5c46a11b0ac43ac306db686e803a6f2db3ae4dda893384bb474c87f4"},"schema_version":"1.0","source":{"id":"2607.06461","kind":"arxiv","version":1}},"canonical_sha256":"dc7a028e2a24b379977635f23409777773dba374129dfb01ac20ae60983cb8c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc7a028e2a24b379977635f23409777773dba374129dfb01ac20ae60983cb8c1","first_computed_at":"2026-07-08T01:19:26.924359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:26.924359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"13D1LcumecdGeMbLYVzjtd433UUe5C34GFTdBd/9uFjlD8dcdKMKO5oDyxfP2EFDhg2mAVl72VL3UBRO9/QkDw==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:26.924788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac53903e3eb34b724ba5423100efbe9c288ea56803c0c8a47f8ee335c3a45630","sha256:c3b240c32759d2399e7f1a59e0ac029180b45548fc97cd8b754b068bd14871bf"],"state_sha256":"65ce5fd09a1b1f9ed54f4d514b8439f92550dbfc6bc8be9e629b2fee2a0fbb06"}