{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E625IQ2WRF3YNJUOAWHVITCLEU","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":"df2f6e06e8923f90301443b8dd0a280947bde222dbd48a8ddbb45cc741085510","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T13:31:23Z","title_canon_sha256":"01e1fce867da247f85b0e4362cbafa26a3cb8787eef87abcfc1c8812dbc77f50"},"schema_version":"1.0","source":{"id":"2605.17583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17583","created_at":"2026-05-20T00:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17583v1","created_at":"2026-05-20T00:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17583","created_at":"2026-05-20T00:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"E625IQ2WRF3Y","created_at":"2026-05-20T00:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"E625IQ2WRF3YNJUO","created_at":"2026-05-20T00:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"E625IQ2W","created_at":"2026-05-20T00:04:47Z"}],"graph_snapshots":[{"event_id":"sha256:1c6992d3caef69787cd35a6648de311fbf7477ce669bade0f5a30ad7bb2c4deb","target":"graph","created_at":"2026-05-20T00:04:47Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.833805Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.778471Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17583/integrity.json","findings":[],"snapshot_sha256":"1da909e27fcb566e577b5c2f462eb2461b18380e39e3c876d18ab8ad219b462f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the structural mismatch between discrete textual intents and continuous acoustic realizations. Inspired by human cognitive decoupling, we introduce AgentSteerTTS, a multi-agent closed-loop framework designed for intent-faithful expressive control of composite instructions. First, in our framework, an adversarial disentanglement agent mitigates speaker-emotion leakage by learning separable identity and emotion-prosody subspaces with leakage-suppress","authors_text":"Bin Kang, Junjie Wang, Junle Wang, Junzhi Zhao, Shaoguo Wen, Shunlong Wu, Yang Fan, Yulin Li, Zhuotao Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T13:31:23Z","title":"AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17583","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":"sha256:2abd934d623c75e94fd1546156ee2157678c912286402b9cb13e1d3bb182d771","target":"record","created_at":"2026-05-20T00:04:47Z","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":"df2f6e06e8923f90301443b8dd0a280947bde222dbd48a8ddbb45cc741085510","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T13:31:23Z","title_canon_sha256":"01e1fce867da247f85b0e4362cbafa26a3cb8787eef87abcfc1c8812dbc77f50"},"schema_version":"1.0","source":{"id":"2605.17583","kind":"arxiv","version":1}},"canonical_sha256":"27b5d44356897786a68e058f544c4b25285d86a3197e6507d119fab53b21c254","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27b5d44356897786a68e058f544c4b25285d86a3197e6507d119fab53b21c254","first_computed_at":"2026-05-20T00:04:47.236996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:47.236996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VXTm3vEu7jR3NDZufCknrZr82PAPclXeNBYY71l5KE9CnfOvY6ClrvVTQW1Ko7sDwTFaPeaLPGjkWHhRNNs5Ag==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:47.237888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2abd934d623c75e94fd1546156ee2157678c912286402b9cb13e1d3bb182d771","sha256:1c6992d3caef69787cd35a6648de311fbf7477ce669bade0f5a30ad7bb2c4deb"],"state_sha256":"91d024eaf05d0cb53f20bd10db0d7aabed0e77ac1eccb1aa117f8df3308df778"}