{"id":"W7093322906","doi":"10.1145/3746276.3760469","title":"TemporalCook: Benchmarking Temporal and Procedural Reasoning in Multimodal Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Benchmark (surveying); Benchmarking; Question answering; Inference; Task (project management); Language model; Code (set theory); Visual reasoning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001297939,0.0005451043,0.0005848022,0.0007210873,0.0005182128,0.0006074224,0.001049212,0.0002932628,0.00006973107],"category_scores_gemma":[0.0001961775,0.0005635289,0.000114597,0.001789133,0.0001397794,0.001184446,0.001381981,0.001015048,0.00002145469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001935306,"about_ca_system_score_gemma":0.000455152,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01227948,"about_ca_topic_score_gemma":0.001467614,"domain_scores_codex":[0.9958363,0.0002746623,0.0009131354,0.001522552,0.000405166,0.001048153],"domain_scores_gemma":[0.9981586,0.00023234,0.0002679126,0.0009845351,0.0001224589,0.0002341547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007740725,0.000888219,0.4795366,0.0005139163,0.00009317249,0.00008378394,0.01802337,0.01968353,0.0006185885,0.3364863,0.0007911778,0.143204],"study_design_scores_gemma":[0.00154531,0.00005091164,0.08253302,0.0004886911,0.00001662022,0.00001323533,0.0005765039,0.9118672,0.00008094788,0.002060259,0.0002752691,0.0004920128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4779116,0.001323757,0.4958557,0.005263283,0.0002651365,0.001257729,0.00001423172,0.0003385019,0.01777006],"genre_scores_gemma":[0.8802488,0.0000321439,0.1169829,0.001151739,0.00008207088,0.0001163053,0.00002140364,0.00002775348,0.001336938],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8921837,"threshold_uncertainty_score":0.9996816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009377410152993777,"score_gpt":0.2913720655981711,"score_spread":0.2819946554451774,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}