{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WAJ3BMIU4DFIPJNFMG67NX3ZCF","short_pith_number":"pith:WAJ3BMIU","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"},"canonical_sha256":"b013b0b114e0ca87a5a561bdf6df791141e0fcd4570efa66a0f3d412306efa82","source":{"kind":"arxiv","id":"2605.11866","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11866","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11866v2","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11866","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"WAJ3BMIU4DFI","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"WAJ3BMIU4DFIPJNF","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"WAJ3BMIU","created_at":"2026-05-21T01:04:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WAJ3BMIU4DFIPJNFMG67NX3ZCF","target":"record","payload":{"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"},"canonical_sha256":"b013b0b114e0ca87a5a561bdf6df791141e0fcd4570efa66a0f3d412306efa82","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"},"source_kind":"arxiv","source_id":"2605.11866","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Mzkntf9KqRKgB9Bu1iLuh4dZnEOSpOVBoT4r21XFVv2PnWUq5Vn0hvNsSX1FfUg5Vv5afd35Ts4v0CqPkojCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T08:14:44.707186Z"},"content_sha256":"2b19fce0974371509ab116a6f994025e2ecd1993485c35062320ffb146ea5ea5","schema_version":"1.0","event_id":"sha256:2b19fce0974371509ab116a6f994025e2ecd1993485c35062320ffb146ea5ea5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WAJ3BMIU4DFIPJNFMG67NX3ZCF","target":"graph","payload":{"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"},"verdict_id":"78318dd6-62cf-40b8-8f33-bca880a48bea"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/klth2wudx88V6/RoeFB3KaZuLLh6pzlGrATpuEu/MQHNxOXfSPCZIuph4j3S4pozfI8Gw1JtixS/tZ+SU+GAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T08:14:44.708255Z"},"content_sha256":"21eb3153383ee711b3301b8a13dfb72fbc11fbbaa6f8f1f80634ce0e50a3ee89","schema_version":"1.0","event_id":"sha256:21eb3153383ee711b3301b8a13dfb72fbc11fbbaa6f8f1f80634ce0e50a3ee89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/bundle.json","state_url":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T08:14:44Z","links":{"resolver":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF","bundle":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/bundle.json","state":"https://pith.science/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAJ3BMIU4DFIPJNFMG67NX3ZCF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WAJ3BMIU4DFIPJNFMG67NX3ZCF","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":"cc5ee5b723214b2f8b25fd518c5afbdd52ba547f0575f242f7cb3b80cdac060e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-12T09:46:36Z","title_canon_sha256":"955a7877f45671733ab8c7192705ed1f7d9d1d28008d6e5fdb7c877164872a3c"},"schema_version":"1.0","source":{"id":"2605.11866","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11866","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11866v2","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11866","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"WAJ3BMIU4DFI","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"WAJ3BMIU4DFIPJNF","created_at":"2026-05-21T01:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"WAJ3BMIU","created_at":"2026-05-21T01:04:27Z"}],"graph_snapshots":[{"event_id":"sha256:21eb3153383ee711b3301b8a13dfb72fbc11fbbaa6f8f1f80634ce0e50a3ee89","target":"graph","created_at":"2026-05-21T01:04:27Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments demonstrate that AuDirector achieves superior performance compared to state-of-the-art baselines in structural coherence, emotional expressiveness, and acoustic fidelity."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"e381da6f9de5d6f5457413ddba178fea5fb691226c924601d33c88bcccb66262"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8d7dc417e9eeb3ce6e1e2c58164073a4f024006d90e6cc21497ed81c1ac6bf96"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.11866/integrity.json","findings":[],"snapshot_sha256":"9dc6fd9bbb5f701929d8267b873efd802d17d71c0c6fcfa71fa50f5c6cb11218","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baoxiang Li, Chao Zhang, Wen Wu, Xuenan Xu, Yiming Ren, Ziyang Zhang","cross_cats":[],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-12T09:46:36Z","title":"AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.11866","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T05:01:02.479990Z","id":"78318dd6-62cf-40b8-8f33-bca880a48bea","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"Experiments demonstrate that AuDirector achieves superior performance compared to state-of-the-art baselines in structural coherence, emotional expressiveness, and acoustic fidelity.","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."}},"verdict_id":"78318dd6-62cf-40b8-8f33-bca880a48bea"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2b19fce0974371509ab116a6f994025e2ecd1993485c35062320ffb146ea5ea5","target":"record","created_at":"2026-05-21T01:04:27Z","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":"cc5ee5b723214b2f8b25fd518c5afbdd52ba547f0575f242f7cb3b80cdac060e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-12T09:46:36Z","title_canon_sha256":"955a7877f45671733ab8c7192705ed1f7d9d1d28008d6e5fdb7c877164872a3c"},"schema_version":"1.0","source":{"id":"2605.11866","kind":"arxiv","version":2}},"canonical_sha256":"b013b0b114e0ca87a5a561bdf6df791141e0fcd4570efa66a0f3d412306efa82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b013b0b114e0ca87a5a561bdf6df791141e0fcd4570efa66a0f3d412306efa82","first_computed_at":"2026-05-21T01:04:27.755084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:27.755084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o2fd8dWQ89QW1EnzbcnuaYhufLMDHLihvhW54v76HowhoKjw5SBH+NH7dMrg8MC7nIcyW61zL7TR2+EH3aj8AA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:27.755906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.11866","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b19fce0974371509ab116a6f994025e2ecd1993485c35062320ffb146ea5ea5","sha256:21eb3153383ee711b3301b8a13dfb72fbc11fbbaa6f8f1f80634ce0e50a3ee89"],"state_sha256":"aa70d27a29d3c13de382bd5ecc6441bf90797f4fbbe2887e8cf19179e3516a0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uBnCWjnkP/nY7Rtg//xSqaBz9oTzUZCVU0bG8cqc9wFt1g4MKeKYuPWVvD8TEcHCSqxiC7021ihqQmtZEg8wAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T08:14:44.713070Z","bundle_sha256":"a17a3ecdcccb4f8139592e9bcdc82c46ade83078c252c02862caae29a05c0549"}}