{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GSENSGWDRW6TGCVQISP2Z4OJJM","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":"63e3ac57768df26a960d56f695f60610579dc81e83453ce4e5bf1921c658dd08","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T06:38:54Z","title_canon_sha256":"ecee93bb28fd335169eeebe857c458eaf96550f4e2c1721eb7b25cd84c7b822a"},"schema_version":"1.0","source":{"id":"2605.28035","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28035","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28035v1","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28035","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"GSENSGWDRW6T","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"GSENSGWDRW6TGCVQ","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"GSENSGWD","created_at":"2026-05-28T01:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:395c246ba1ada545147485bcf900ff6a1ada94222de56d2e7bef67efb5e64349","target":"graph","created_at":"2026-05-28T01:04:56Z","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/2605.28035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, Multi-Talker Audio-Video Generation (MTAVG) models have shown promising performance on fundamental metrics such as lip-sync and audio-visual alignment. However, these metrics remain insufficient for assessing cinematic expressiveness in scene-level generation. In multi-character scenes, generation models must go beyond audio-visual realism to convey coherent character performance and other higher-level cinematic qualities. To fill this gap, we introduce MTAVG-Bench 2.0, a benchmark for diagnosing failure modes of cinematic expressiveness in multi-talker audio-video generation.","authors_text":"Changsen Yuan, Dian Jin, Haitian Li, Heyan Huang, Jiajun Xu, Jingyun Liao, Jinxing Zhou, Liangji Chen, Tian Lan, Xian-Ling Mao, Xuefeng Chen, Xu Liu, Yanghao Zhou, Yiming Cheng, Yousheng Feng, Yu Bai, Yueying Liu, Ziqin Zhou","cross_cats":["cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T06:38:54Z","title":"MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28035","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":"sha256:5283a959bece626ccef93c8d0bfd9194c27cd3945dcc25e8664951278f208903","target":"record","created_at":"2026-05-28T01:04:56Z","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":"63e3ac57768df26a960d56f695f60610579dc81e83453ce4e5bf1921c658dd08","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T06:38:54Z","title_canon_sha256":"ecee93bb28fd335169eeebe857c458eaf96550f4e2c1721eb7b25cd84c7b822a"},"schema_version":"1.0","source":{"id":"2605.28035","kind":"arxiv","version":1}},"canonical_sha256":"3488d91ac38dbd330ab0449facf1c94b1be262d314e46078559ff621840f5c68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3488d91ac38dbd330ab0449facf1c94b1be262d314e46078559ff621840f5c68","first_computed_at":"2026-05-28T01:04:56.672075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:56.672075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6kkldIpHwyu9oqQ527YpljTs/vD2XcPKFAVj7cfb++NWRisdYcaE8mjLLdlNpYMW6Mdjf5/8yUW7abjUTL4pAg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:56.672530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28035","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5283a959bece626ccef93c8d0bfd9194c27cd3945dcc25e8664951278f208903","sha256:395c246ba1ada545147485bcf900ff6a1ada94222de56d2e7bef67efb5e64349"],"state_sha256":"bab8c57ab72b895b1b63552674d1abf9f37caf1ab9af6c80a9c3020e02023db5"}