{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YCKTO57ACJOSYV2C5II5FNCVKL","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":"8930a24c1e57e3b6af8721f047049d228eaf6ed7c52e69b0ab201473d80f3b2e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-03T13:16:36Z","title_canon_sha256":"ce3702a80e6002b7aa4f141b07db198195323413a04f96bffd93cfe879324433"},"schema_version":"1.0","source":{"id":"1910.01442","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.01442","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"1910.01442v2","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01442","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"YCKTO57ACJOS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YCKTO57ACJOSYV2C","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YCKTO57A","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:f73d169ff5ec6e7a962c1eac46e0a6578cec70fac5729e46f6ce829c98b21751","target":"graph","created_at":"2026-05-17T23:38:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"While these models thrive on the perception-based task (descriptive), they perform poorly on the causal tasks (explanatory, predictive and counterfactual), suggesting that a principled approach for causal reasoning should incorporate the capability of both perceiving complex visual and language inputs, and understanding the underlying dynamics and causal relations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the observed poor performance on causal tasks stems primarily from a lack of causal reasoning capability in the models rather than from dataset-specific artifacts, insufficient training regimes, or other unmeasured factors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CLEVRER introduces a diagnostic dataset for evaluating video models on causal reasoning via descriptive, explanatory, predictive, and counterfactual questions about object collision events."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CLEVRER shows video models describe collisions accurately but fail at explaining causes, predicting outcomes, or reasoning about alternatives."}],"snapshot_sha256":"b5f7829645189f18d952c7665ffb2e90fb506f0c57e24d19b7b882434654870d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"224218fc5fecd42a45569f719ea55fe03ed0864d6bf3e154324704c4e094cb87"},"paper":{"abstract_excerpt":"The ability to reason about temporal and causal events from videos lies at the core of human intelligence. Most video reasoning benchmarks, however, focus on pattern recognition from complex visual and language input, instead of on causal structure. We study the complementary problem, exploring the temporal and causal structures behind videos of objects with simple visual appearance. To this end, we introduce the CoLlision Events for Video REpresentation and Reasoning (CLEVRER), a diagnostic video dataset for systematic evaluation of computational models on a wide range of reasoning tasks. Mot","authors_text":"Antonio Torralba, Chuang Gan, Jiajun Wu, Joshua B. Tenenbaum, Kexin Yi, Pushmeet Kohli, Yunzhu Li","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"CLEVRER shows video models describe collisions accurately but fail at explaining causes, predicting outcomes, or reasoning about alternatives.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-03T13:16:36Z","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning"},"references":{"count":300,"internal_anchors":1,"resolved_work":300,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Generating the future with adversarial transformers , author=","work_id":"112a0d34-9bd6-446b-8696-b6cf9afe2da3","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"How, whether, why: Causal judgments as counterfactual contrasts. , author=. CogSci , year=","work_id":"5b775747-0437-4ecd-90de-1521e132ce32","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Learning perceptual causality from video , author=. TIST , volume=. 2016 , publisher=","work_id":"9fbd3536-8506-4495-8079-6d7f5f2dfd62","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Causality , author=. 2009 , publisher=","work_id":"afebe501-3ef8-491b-998d-c996051cc590","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Self-supervised visual planning with temporal skip connections , author=","work_id":"10665674-079e-4805-8183-b65fa8ca5b93","year":null}],"snapshot_sha256":"90f317f639571c8393784cc0df368d9cc0076197e65be67ed463dcfe5a7172b3"},"source":{"id":"1910.01442","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T17:57:07.896393Z","id":"6c7c1758-660c-44aa-adab-2895ab26c526","model_set":{"reader":"grok-4.3"},"one_line_summary":"CLEVRER introduces a diagnostic dataset for evaluating video models on causal reasoning via descriptive, explanatory, predictive, and counterfactual questions about object collision events.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CLEVRER shows video models describe collisions accurately but fail at explaining causes, predicting outcomes, or reasoning about alternatives.","strongest_claim":"While these models thrive on the perception-based task (descriptive), they perform poorly on the causal tasks (explanatory, predictive and counterfactual), suggesting that a principled approach for causal reasoning should incorporate the capability of both perceiving complex visual and language inputs, and understanding the underlying dynamics and causal relations.","weakest_assumption":"That the observed poor performance on causal tasks stems primarily from a lack of causal reasoning capability in the models rather than from dataset-specific artifacts, insufficient training regimes, or other unmeasured factors."}},"verdict_id":"6c7c1758-660c-44aa-adab-2895ab26c526"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ffd871a0569a2fec5e50699249710e56023a16af6fe9fa4d62d82bf20f47d6ed","target":"record","created_at":"2026-05-17T23:38:47Z","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":"8930a24c1e57e3b6af8721f047049d228eaf6ed7c52e69b0ab201473d80f3b2e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-03T13:16:36Z","title_canon_sha256":"ce3702a80e6002b7aa4f141b07db198195323413a04f96bffd93cfe879324433"},"schema_version":"1.0","source":{"id":"1910.01442","kind":"arxiv","version":2}},"canonical_sha256":"c0953777e0125d2c5742ea11d2b45552e8fa51ab923359a76c6f70b0ca81b66d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0953777e0125d2c5742ea11d2b45552e8fa51ab923359a76c6f70b0ca81b66d","first_computed_at":"2026-05-17T23:38:47.042917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.042917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XuDjjcGS5rwulOcgyOshfeWT44CxzmJJ/WbkhqfhujsF8xMXSKCfRTckj69iF07X8QVJy7SGolGaIZ+s2rzqDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.043476Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.01442","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffd871a0569a2fec5e50699249710e56023a16af6fe9fa4d62d82bf20f47d6ed","sha256:f73d169ff5ec6e7a962c1eac46e0a6578cec70fac5729e46f6ce829c98b21751"],"state_sha256":"6c298985913cf8b72be2037f8aff9a3e05ee713dbef03c5e0be97cdf57b78b63"}