{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DI53RCFJ3D6JGSL5QPPVVQUA4R","short_pith_number":"pith:DI53RCFJ","schema_version":"1.0","canonical_sha256":"1a3bb888a9d8fc93497d83df5ac280e46caa6c5911095a4316cc73f2279eb688","source":{"kind":"arxiv","id":"2411.09105","version":2},"attestation_state":"computed","paper":{"title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenglin Li, Feng Tao, Qianglong Chen, Yin Zhang, Zhi Li","submitted_at":"2024-11-14T00:26:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.09105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T00:26:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecc5cd264774a8fcc1b93e4d8d9bec9612b9368d9bb04af6e7b83403f92c6b70","abstract_canon_sha256":"43812e0cca168b2a2c1a8a3a5d208464861e0419cd615bcd4f4be19036e1958b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:52.149283Z","signature_b64":"jir75pYvK87dpbH3rVS6Jr3Xe1IGEPyErVGuDDB5iuoDO4RrcTDlZSrtUalEA13nmtjSTtDeA9LINRjwmRGVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a3bb888a9d8fc93497d83df5ac280e46caa6c5911095a4316cc73f2279eb688","last_reissued_at":"2026-07-05T11:29:52.148803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:52.148803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenglin Li, Feng Tao, Qianglong Chen, Yin Zhang, Zhi Li","submitted_at":"2024-11-14T00:26:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09105","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.09105/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.09105","created_at":"2026-07-05T11:29:52.148862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09105v2","created_at":"2026-07-05T11:29:52.148862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09105","created_at":"2026-07-05T11:29:52.148862+00:00"},{"alias_kind":"pith_short_12","alias_value":"DI53RCFJ3D6J","created_at":"2026-07-05T11:29:52.148862+00:00"},{"alias_kind":"pith_short_16","alias_value":"DI53RCFJ3D6JGSL5","created_at":"2026-07-05T11:29:52.148862+00:00"},{"alias_kind":"pith_short_8","alias_value":"DI53RCFJ","created_at":"2026-07-05T11:29:52.148862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22570","citing_title":"VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15724","citing_title":"VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19386","citing_title":"Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20358","citing_title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R","json":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R.json","graph_json":"https://pith.science/api/pith-number/DI53RCFJ3D6JGSL5QPPVVQUA4R/graph.json","events_json":"https://pith.science/api/pith-number/DI53RCFJ3D6JGSL5QPPVVQUA4R/events.json","paper":"https://pith.science/paper/DI53RCFJ"},"agent_actions":{"view_html":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R","download_json":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R.json","view_paper":"https://pith.science/paper/DI53RCFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09105&json=true","fetch_graph":"https://pith.science/api/pith-number/DI53RCFJ3D6JGSL5QPPVVQUA4R/graph.json","fetch_events":"https://pith.science/api/pith-number/DI53RCFJ3D6JGSL5QPPVVQUA4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R/action/storage_attestation","attest_author":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R/action/author_attestation","sign_citation":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R/action/citation_signature","submit_replication":"https://pith.science/pith/DI53RCFJ3D6JGSL5QPPVVQUA4R/action/replication_record"}},"created_at":"2026-07-05T11:29:52.148862+00:00","updated_at":"2026-07-05T11:29:52.148862+00:00"}