{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KUJ4ILXMMWE53ZURTLFLXVAIV4","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":"c3852736b7339a2546323449d4b11aedfc293ce0a76525a670c8d018e5eaf0ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T02:46:12Z","title_canon_sha256":"8e0df7bde9259e5078580442d47b874c8bd1ee8f6fd8e32966c8e913e35a2c71"},"schema_version":"1.0","source":{"id":"2311.14906","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14906","created_at":"2026-07-05T08:43:51Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14906v2","created_at":"2026-07-05T08:43:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14906","created_at":"2026-07-05T08:43:51Z"},{"alias_kind":"pith_short_12","alias_value":"KUJ4ILXMMWE5","created_at":"2026-07-05T08:43:51Z"},{"alias_kind":"pith_short_16","alias_value":"KUJ4ILXMMWE53ZUR","created_at":"2026-07-05T08:43:51Z"},{"alias_kind":"pith_short_8","alias_value":"KUJ4ILXM","created_at":"2026-07-05T08:43:51Z"}],"graph_snapshots":[{"event_id":"sha256:edd85eb18cb7cc601c7b86b0666599fd22cf9ad138abf18849d5f65f7ad9590e","target":"graph","created_at":"2026-07-05T08:43:51Z","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/2311.14906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel and challenging benchmark, AutoEval-Video, to comprehensively evaluate large vision-language models in open-ended video question answering. The comprehensiveness of AutoEval-Video is demonstrated in two aspects: 1) AutoEval-Video constructs open-ended video-questions across 9 skill dimensions, addressing capabilities of perception, comprehension, and generation. 2) AutoEval-Video contains newly collected videos that cover over 40 distinct themes. To efficiently evaluate responses to the open-ended questions, we employ an LLM-based evaluation approach, but instead of merely p","authors_text":"Weiran Huang, Xiuyuan Chen, Yuan Lin, Yuchen Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T02:46:12Z","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14906","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":"sha256:685def30ad1ea12c9f48fdd81793798f8414918802ec02ada97c0180a8e3e752","target":"record","created_at":"2026-07-05T08:43:51Z","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":"c3852736b7339a2546323449d4b11aedfc293ce0a76525a670c8d018e5eaf0ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T02:46:12Z","title_canon_sha256":"8e0df7bde9259e5078580442d47b874c8bd1ee8f6fd8e32966c8e913e35a2c71"},"schema_version":"1.0","source":{"id":"2311.14906","kind":"arxiv","version":2}},"canonical_sha256":"5513c42eec6589dde6919acabbd408af37d1bd8152eab64b721ffcec3e2d009e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5513c42eec6589dde6919acabbd408af37d1bd8152eab64b721ffcec3e2d009e","first_computed_at":"2026-07-05T08:43:51.512450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:51.512450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5lFM4NhB3xhGwACtjqRO7HfrYKhYtlMEGDD09EGqSzDnmrkLxdiGLlJrruxOOA4WqbVhMPH6CjT1v2rDsL5EAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:51.512887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.14906","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:685def30ad1ea12c9f48fdd81793798f8414918802ec02ada97c0180a8e3e752","sha256:edd85eb18cb7cc601c7b86b0666599fd22cf9ad138abf18849d5f65f7ad9590e"],"state_sha256":"51634d66f90bc0c94b8ca1c94acbeaeb46edafbe97b146bc4628eee71c8b7b8b"}