{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MPE2YJ2DYQFHVKFJVTLJRFQYC6","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":"7c40c944d5545e41b5c635aae25dcf05b5c8f9bfb7d585a1b48f409199a16513","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-04-15T09:19:44Z","title_canon_sha256":"39ab39e88d7a3c32e7d3c299d1b2289d7c368eff15728215c3410c4ce3ace75f"},"schema_version":"1.0","source":{"id":"2504.11002","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11002","created_at":"2026-07-05T11:52:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11002v2","created_at":"2026-07-05T11:52:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11002","created_at":"2026-07-05T11:52:20Z"},{"alias_kind":"pith_short_12","alias_value":"MPE2YJ2DYQFH","created_at":"2026-07-05T11:52:20Z"},{"alias_kind":"pith_short_16","alias_value":"MPE2YJ2DYQFHVKFJ","created_at":"2026-07-05T11:52:20Z"},{"alias_kind":"pith_short_8","alias_value":"MPE2YJ2D","created_at":"2026-07-05T11:52:20Z"}],"graph_snapshots":[{"event_id":"sha256:86cff1dcd9692797309ccb20f71f94254282fd48f571c2b7df9ce28f93658c25","target":"graph","created_at":"2026-07-05T11:52:20Z","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/2504.11002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audiobook generation aims to create rich, immersive listening experiences from multimodal inputs, but current approaches face three critical challenges: (1) the lack of synergistic generation of diverse audio types (e.g., speech, sound effects, and music) with precise temporal and semantic alignment; (2) the difficulty in conveying expressive, fine-grained emotions, which often results in machine-like vocal outputs; and (3) the absence of automated evaluation frameworks that align with human preferences for complex and diverse audio. To address these issues, we propose Dopamine Audiobook, a no","authors_text":"Chenxing Li, Dong Yu, Li Liu, Shan Yang, Yan Rong","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-04-15T09:19:44Z","title":"Dopamine Audiobook: A Training-free MLLM Agent for Emotional and Immersive Audiobook Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11002","kind":"arxiv","version":2},"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":"sha256:415db38ec47bead59af751f67ef9789c113435de101d8c5c2992106381299e39","target":"record","created_at":"2026-07-05T11:52:20Z","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":"7c40c944d5545e41b5c635aae25dcf05b5c8f9bfb7d585a1b48f409199a16513","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-04-15T09:19:44Z","title_canon_sha256":"39ab39e88d7a3c32e7d3c299d1b2289d7c368eff15728215c3410c4ce3ace75f"},"schema_version":"1.0","source":{"id":"2504.11002","kind":"arxiv","version":2}},"canonical_sha256":"63c9ac2743c40a7aa8a9acd69896181799e596ca3db59d216759b52480948fc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63c9ac2743c40a7aa8a9acd69896181799e596ca3db59d216759b52480948fc7","first_computed_at":"2026-07-05T11:52:20.032181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:20.032181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YGCFfpuR9/nhH2zm/AVKKm3TuzooCWBOFNQc6mwMzDoD7NtuVvqPYA1D9tdhXolLnnDL9mYlsej9c1yqRMdyAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:20.032664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11002","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:415db38ec47bead59af751f67ef9789c113435de101d8c5c2992106381299e39","sha256:86cff1dcd9692797309ccb20f71f94254282fd48f571c2b7df9ce28f93658c25"],"state_sha256":"eeefb77391858dd8878224e8e098731095b401d1e8bf5af48692c4920bd84a58"}