{"id":"W2942197587","doi":"","title":"Evaluating visual \"common sense\" using fine-grained classification and captioning tasks.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; University of Toronto; University of British Columbia","funders":"","keywords":"Closed captioning; Computer science; Natural language processing; Artificial intelligence; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004604947,0.002674349,0.001425614,0.005065761,0.00108794,0.004313113,0.002265587,0.004269321,0.007236435],"category_scores_gemma":[0.0266822,0.0004067157,0.001436257,0.002744702,0.001178101,0.007572825,0.003334421,0.001797312,0.002613255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001171264,"about_ca_system_score_gemma":0.001058421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00727091,"about_ca_topic_score_gemma":0.007215654,"domain_scores_codex":[0.9947807,0.001464584,0.0004400813,0.001921875,0.001001906,0.0003907848],"domain_scores_gemma":[0.9884838,0.005230684,0.001056171,0.002430024,0.002061465,0.0007378882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004418325,0.001280862,0.01995837,0.001905989,0.001166374,0.0007314861,0.0007101825,0.02139922,0.05548893,0.005156048,0.05084297,0.8369413],"study_design_scores_gemma":[0.0007106428,0.003845775,0.06215548,0.0006178354,0.001208972,0.002591964,0.002985986,0.8076524,0.06079332,0.03634918,0.02078287,0.0003056577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6753653,0.01193753,0.2439782,0.001457664,0.002265128,0.001420858,0.01171819,0.01613884,0.03571829],"genre_scores_gemma":[0.9102537,0.0009222656,0.06849702,0.000354776,0.0003456546,0.0002328629,0.01555625,0.0004723583,0.00336518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00727091,"threshold_uncertainty_score":0.02435362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2022041097309364,"score_gpt":0.461630120068778,"score_spread":0.2594260103378415,"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."}}