{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E625IQ2WRF3YNJUOAWHVITCLEU","short_pith_number":"pith:E625IQ2W","schema_version":"1.0","canonical_sha256":"27b5d44356897786a68e058f544c4b25285d86a3197e6507d119fab53b21c254","source":{"kind":"arxiv","id":"2605.17583","version":1},"attestation_state":"computed","paper":{"title":"AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Kang, Junjie Wang, Junle Wang, Junzhi Zhao, Shaoguo Wen, Shunlong Wu, Yang Fan, Yulin Li, Zhuotao Tian","submitted_at":"2026-05-14T13:31:23Z","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"},"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":"2605.17583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T13:31:23Z","cross_cats_sorted":[],"title_canon_sha256":"01e1fce867da247f85b0e4362cbafa26a3cb8787eef87abcfc1c8812dbc77f50","abstract_canon_sha256":"df2f6e06e8923f90301443b8dd0a280947bde222dbd48a8ddbb45cc741085510"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:47.237888Z","signature_b64":"VXTm3vEu7jR3NDZufCknrZr82PAPclXeNBYY71l5KE9CnfOvY6ClrvVTQW1Ko7sDwTFaPeaLPGjkWHhRNNs5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27b5d44356897786a68e058f544c4b25285d86a3197e6507d119fab53b21c254","last_reissued_at":"2026-05-20T00:04:47.236996Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:47.236996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Kang, Junjie Wang, Junle Wang, Junzhi Zhao, Shaoguo Wen, Shunlong Wu, Yang Fan, Yulin Li, Zhuotao Tian","submitted_at":"2026-05-14T13:31:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17583","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/2605.17583/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"1da909e27fcb566e577b5c2f462eb2461b18380e39e3c876d18ab8ad219b462f"},"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":"2605.17583","created_at":"2026-05-20T00:04:47.237114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17583v1","created_at":"2026-05-20T00:04:47.237114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17583","created_at":"2026-05-20T00:04:47.237114+00:00"},{"alias_kind":"pith_short_12","alias_value":"E625IQ2WRF3Y","created_at":"2026-05-20T00:04:47.237114+00:00"},{"alias_kind":"pith_short_16","alias_value":"E625IQ2WRF3YNJUO","created_at":"2026-05-20T00:04:47.237114+00:00"},{"alias_kind":"pith_short_8","alias_value":"E625IQ2W","created_at":"2026-05-20T00:04:47.237114+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/E625IQ2WRF3YNJUOAWHVITCLEU","json":"https://pith.science/pith/E625IQ2WRF3YNJUOAWHVITCLEU.json","graph_json":"https://pith.science/api/pith-number/E625IQ2WRF3YNJUOAWHVITCLEU/graph.json","events_json":"https://pith.science/api/pith-number/E625IQ2WRF3YNJUOAWHVITCLEU/events.json","paper":"https://pith.science/paper/E625IQ2W"},"agent_actions":{"view_html":"https://pith.science/pith/E625IQ2WRF3YNJUOAWHVITCLEU","download_json":"https://pith.science/pith/E625IQ2WRF3YNJUOAWHVITCLEU.json","view_paper":"https://pith.science/paper/E625IQ2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17583&json=true","fetch_graph":"https://pith.science/api/pith-number/E625IQ2WRF3YNJUOAWHVITCLEU/graph.json","fetch_events":"https://pith.science/api/pith-number/E625IQ2WRF3YNJUOAWHVITCLEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E625IQ2WRF3YNJUOAWHVITCLEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E625IQ2WRF3YNJUOAWHVITCLEU/action/storage_attestation","attest_author":"https://pith.science/pith/E625IQ2WRF3YNJUOAWHVITCLEU/action/author_attestation","sign_citation":"https://pith.science/pith/E625IQ2WRF3YNJUOAWHVITCLEU/action/citation_signature","submit_replication":"https://pith.science/pith/E625IQ2WRF3YNJUOAWHVITCLEU/action/replication_record"}},"created_at":"2026-05-20T00:04:47.237114+00:00","updated_at":"2026-05-20T00:04:47.237114+00:00"}