{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DI53RCFJ3D6JGSL5QPPVVQUA4R","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":"43812e0cca168b2a2c1a8a3a5d208464861e0419cd615bcd4f4be19036e1958b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T00:26:26Z","title_canon_sha256":"ecc5cd264774a8fcc1b93e4d8d9bec9612b9368d9bb04af6e7b83403f92c6b70"},"schema_version":"1.0","source":{"id":"2411.09105","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09105","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09105v2","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09105","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_12","alias_value":"DI53RCFJ3D6J","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"DI53RCFJ3D6JGSL5","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"DI53RCFJ","created_at":"2026-07-05T11:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:e709475d5faf7940a7a5313441fe0f3da1e066cc587ebd9f1b637b5fb701511a","target":"graph","created_at":"2026-07-05T11:29:52Z","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/2411.09105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Video-Language Models (LVLMs) have led to promising results in multimodal video understanding. However, it remains unclear whether these models possess the cognitive capabilities required for high-level tasks, particularly those involving symbolic and abstract perception. Existing benchmarks typically rely on real-world, annotated videos, which lack control over video content and inherent difficulty, limiting their diagnostic power. To bridge this gap, we propose VideoCogQA, a scalable and fully controllable benchmark inspired by game-world environments, designed t","authors_text":"Chenglin Li, Feng Tao, Qianglong Chen, Yin Zhang, Zhi Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T00:26:26Z","title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09105","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:ac781ccf51576759d24e0d710c24a2e52db43fdb25fd37d1892ff3eee83fbc1a","target":"record","created_at":"2026-07-05T11:29:52Z","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":"43812e0cca168b2a2c1a8a3a5d208464861e0419cd615bcd4f4be19036e1958b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T00:26:26Z","title_canon_sha256":"ecc5cd264774a8fcc1b93e4d8d9bec9612b9368d9bb04af6e7b83403f92c6b70"},"schema_version":"1.0","source":{"id":"2411.09105","kind":"arxiv","version":2}},"canonical_sha256":"1a3bb888a9d8fc93497d83df5ac280e46caa6c5911095a4316cc73f2279eb688","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a3bb888a9d8fc93497d83df5ac280e46caa6c5911095a4316cc73f2279eb688","first_computed_at":"2026-07-05T11:29:52.148803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:52.148803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jir75pYvK87dpbH3rVS6Jr3Xe1IGEPyErVGuDDB5iuoDO4RrcTDlZSrtUalEA13nmtjSTtDeA9LINRjwmRGVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:52.149283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09105","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac781ccf51576759d24e0d710c24a2e52db43fdb25fd37d1892ff3eee83fbc1a","sha256:e709475d5faf7940a7a5313441fe0f3da1e066cc587ebd9f1b637b5fb701511a"],"state_sha256":"a567b7ba25202b23c53222e61c656fdf32483f2ede9efed3bcd47d27196df777"}