{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WAJ3BMIU4DFIPJNFMG67NX3ZCF","short_pith_number":"pith:WAJ3BMIU","schema_version":"1.0","canonical_sha256":"b013b0b114e0ca87a5a561bdf6df791141e0fcd4570efa66a0f3d412306efa82","source":{"kind":"arxiv","id":"2605.11866","version":2},"attestation_state":"computed","paper":{"title":"AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AuDirector's self-reflective closed-loop multi-agent framework produces long-form audio stories with greater structural coherence, emotional expressiveness, and acoustic fidelity than existing approaches.","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Baoxiang Li, Chao Zhang, Wen Wu, Xuenan Xu, Yiming Ren, Ziyang Zhang","submitted_at":"2026-05-12T09:46:36Z","abstract_excerpt":"Despite advances in text and visual generation, creating coherent long-form audio narratives remains challenging. Existing frameworks often exhibit limitations such as mismatched character settings with voice performance, insufficient self-correction mechanisms, and limited human interactivity. To address these challenges, we propose AuDirector, a self-reflective closed-loop multi-agent framework. Specifically, it involves an Identity-Aware Pre-production mechanism that transforms narrative texts into character profiles and utterance-level emotional instructions to retrieve suitable voice cand"},"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":true},"canonical_record":{"source":{"id":"2605.11866","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-12T09:46:36Z","cross_cats_sorted":[],"title_canon_sha256":"955a7877f45671733ab8c7192705ed1f7d9d1d28008d6e5fdb7c877164872a3c","abstract_canon_sha256":"cc5ee5b723214b2f8b25fd518c5afbdd52ba547f0575f242f7cb3b80cdac060e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:27.755906Z","signature_b64":"o2fd8dWQ89QW1EnzbcnuaYhufLMDHLihvhW54v76HowhoKjw5SBH+NH7dMrg8MC7nIcyW61zL7TR2+EH3aj8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b013b0b114e0ca87a5a561bdf6df791141e0fcd4570efa66a0f3d412306efa82","last_reissued_at":"2026-05-21T01:04:27.755084Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:27.755084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AuDirector's self-reflective closed-loop multi-agent framework produces long-form audio stories with greater structural coherence, emotional expressiveness, and acoustic fidelity than existing approaches.","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Baoxiang Li, Chao Zhang, Wen Wu, Xuenan Xu, Yiming Ren, Ziyang Zhang","submitted_at":"2026-05-12T09:46:36Z","abstract_excerpt":"Despite advances in text and visual generation, creating coherent long-form audio narratives remains challenging. Existing frameworks often exhibit limitations such as mismatched character settings with voice performance, insufficient self-correction mechanisms, and limited human interactivity. To address these challenges, we propose AuDirector, a self-reflective closed-loop multi-agent framework. Specifically, it involves an Identity-Aware Pre-production mechanism that transforms narrative texts into character profiles and utterance-level emotional instructions to retrieve suitable voice cand"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments demonstrate that AuDirector achieves superior performance compared to state-of-the-art baselines in structural coherence, emotional expressiveness, and acoustic fidelity.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Identity-Aware Pre-production, Collaborative Synthesis and Correction, and Human-Guided Interactive Refinement modules can be integrated into a stable closed-loop system that consistently improves output quality without introducing new inconsistencies or requiring extensive manual tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AuDirector is a self-reflective closed-loop multi-agent framework that generates immersive audio narratives with improved structural coherence, emotional expressiveness, and acoustic fidelity via identity-aware voice adaptation and iterative correction.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AuDirector's self-reflective closed-loop multi-agent framework produces long-form audio stories with greater structural coherence, emotional expressiveness, and acoustic fidelity than existing approaches.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e381da6f9de5d6f5457413ddba178fea5fb691226c924601d33c88bcccb66262"},"source":{"id":"2605.11866","kind":"arxiv","version":2},"verdict":{"id":"78318dd6-62cf-40b8-8f33-bca880a48bea","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T05:01:02.479990Z","strongest_claim":"Experiments demonstrate that AuDirector achieves superior performance compared to state-of-the-art baselines in structural coherence, emotional expressiveness, and acoustic fidelity.","one_line_summary":"AuDirector is a self-reflective closed-loop multi-agent framework that generates immersive audio narratives with improved structural coherence, emotional expressiveness, and acoustic fidelity via identity-aware voice adaptation and iterative correction.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Identity-Aware Pre-production, Collaborative Synthesis and Correction, and Human-Guided Interactive Refinement modules can be integrated into a stable closed-loop system that consistently improves output quality without introducing new inconsistencies or requiring extensive manual tuning.","pith_extraction_headline":"AuDirector's self-reflective closed-loop multi-agent framework produces long-form audio stories with greater structural coherence, emotional expressiveness, and acoustic fidelity than existing approaches."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11866/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-20T18:31:27.274027Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T12:46:25.031635Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-20T03:22:00.394214Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T11:36:33.471188Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9dc6fd9bbb5f701929d8267b873efd802d17d71c0c6fcfa71fa50f5c6cb11218"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8d7dc417e9eeb3ce6e1e2c58164073a4f024006d90e6cc21497ed81c1ac6bf96"},"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":"2605.11866","created_at":"2026-05-21T01:04:27.755201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11866v2","created_at":"2026-05-21T01:04:27.755201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11866","created_at":"2026-05-21T01:04:27.755201+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAJ3BMIU4DFI","created_at":"2026-05-21T01:04:27.755201+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAJ3BMIU4DFIPJNF","created_at":"2026-05-21T01:04:27.755201+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAJ3BMIU","created_at":"2026-05-21T01:04:27.755201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.11866","citing_title":"AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11866","citing_title":"AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF","json":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF.json","graph_json":"https://pith.science/api/pith-number/WAJ3BMIU4DFIPJNFMG67NX3ZCF/graph.json","events_json":"https://pith.science/api/pith-number/WAJ3BMIU4DFIPJNFMG67NX3ZCF/events.json","paper":"https://pith.science/paper/WAJ3BMIU"},"agent_actions":{"view_html":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF","download_json":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF.json","view_paper":"https://pith.science/paper/WAJ3BMIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11866&json=true","fetch_graph":"https://pith.science/api/pith-number/WAJ3BMIU4DFIPJNFMG67NX3ZCF/graph.json","fetch_events":"https://pith.science/api/pith-number/WAJ3BMIU4DFIPJNFMG67NX3ZCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/action/storage_attestation","attest_author":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/action/author_attestation","sign_citation":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/action/citation_signature","submit_replication":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/action/replication_record"}},"created_at":"2026-05-21T01:04:27.755201+00:00","updated_at":"2026-05-21T01:04:27.755201+00:00"}