{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ME2HXIVCC5OD62FPVOMYS4BE6W","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":"886ea67e00d6f9ffc329aeee0f899fcf8d46fca6d654e40d68f57e57c839a326","cross_cats_sorted":["cs.CV","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T16:42:39Z","title_canon_sha256":"680be0d817a1aa0d6b69b6d5751de53b213e28d7e26d39a3a265fce1dab0c35a"},"schema_version":"1.0","source":{"id":"2605.24652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24652","created_at":"2026-05-26T01:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24652v1","created_at":"2026-05-26T01:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24652","created_at":"2026-05-26T01:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"ME2HXIVCC5OD","created_at":"2026-05-26T01:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"ME2HXIVCC5OD62FP","created_at":"2026-05-26T01:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"ME2HXIVC","created_at":"2026-05-26T01:03:51Z"}],"graph_snapshots":[{"event_id":"sha256:97d895477dbfbe25423b1a6d8ec4862ce0169cea7cff7e5bbe80dc8d32ed38a5","target":"graph","created_at":"2026-05-26T01:03:51Z","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/2605.24652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rapid advances in audio-video (AV) generation have enabled high-fidelity synthesis with synchronized sound, particularly for human-related scenarios involving speech and interactions. Yet evaluation for AV generation remains at an early stage, with only a few coarse-grained benchmarks for human-related scenarios and relying on limited preset evaluations with generic multimodal LLMs, leading to inaccurate assessments of model capabilities. To address these issues, we introduce AVBench, a fully automated benchmark tailored for human-centric AV generation. AVBench is built on two key designs for ","authors_text":"Bin Xia, Dingdong Wang, Jialiang Yang, Ruihang Chu, Tianyang Zhong, Wanke Xia, Wenming Yang, Yiting Zhao, Zhun Mou","cross_cats":["cs.CV","cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T16:42:39Z","title":"AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24652","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:bf161fb3e7285a55f578aa5183ffad4821c9d31dcf953621b875d8dc311f64c5","target":"record","created_at":"2026-05-26T01:03:51Z","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":"886ea67e00d6f9ffc329aeee0f899fcf8d46fca6d654e40d68f57e57c839a326","cross_cats_sorted":["cs.CV","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T16:42:39Z","title_canon_sha256":"680be0d817a1aa0d6b69b6d5751de53b213e28d7e26d39a3a265fce1dab0c35a"},"schema_version":"1.0","source":{"id":"2605.24652","kind":"arxiv","version":1}},"canonical_sha256":"61347ba2a2175c3f68afab99897024f581cd5172824529e4111f10a25cf824f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61347ba2a2175c3f68afab99897024f581cd5172824529e4111f10a25cf824f5","first_computed_at":"2026-05-26T01:03:51.358084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:51.358084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hl8eNajpngZUp7QN7UMYjJL0LZ8a8itxtxAaojXl8BaCvM8aA9B8HJMuwiIibbSPZxwa7RRi96OYh5bOVk+oCw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:51.358874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf161fb3e7285a55f578aa5183ffad4821c9d31dcf953621b875d8dc311f64c5","sha256:97d895477dbfbe25423b1a6d8ec4862ce0169cea7cff7e5bbe80dc8d32ed38a5"],"state_sha256":"d36be61ee747440d03ef2c9e0a5db4e24a6254d41f95c8c4390cbdcd80dd08e9"}