{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003296066,0.0001299156,0.00010849,0.0002938268,0.0005823011,0.0005064412,0.0002032241,0.00005856448,0.0002951168],"category_scores_gemma":[0.0003374105,0.0001404571,0.00004259978,0.0002251771,0.0001068212,0.000672924,0.0001084075,0.0002512095,0.0001403246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007277438,"about_ca_system_score_gemma":0.00007570521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001039217,"about_ca_topic_score_gemma":0.00003591168,"domain_scores_codex":[0.9984637,0.0001957004,0.0002990785,0.000451038,0.0004224119,0.0001680431],"domain_scores_gemma":[0.9987597,0.0001781721,0.000242425,0.0001826234,0.0005652567,0.00007176887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001012454,0.0003044332,0.01879092,0.00001995427,0.0002007612,0.00002830759,0.009175794,0.004574153,0.3283166,0.3597327,0.0004084077,0.2783467],"study_design_scores_gemma":[0.0003577681,0.0001732071,0.0248696,0.00007051355,0.00001146997,0.00004592958,0.0004584273,0.9665447,0.001665758,0.005371021,0.000261186,0.0001704549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8806478,0.000004774324,0.09833544,0.001786878,0.0004934396,0.0001516135,0.000003314723,0.0001994333,0.01837735],"genre_scores_gemma":[0.9899624,0.000007861821,0.008567022,0.0001489272,0.0003063393,0.00002061565,0.00005792717,0.00001045298,0.0009184496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9619705,"threshold_uncertainty_score":0.5727674,"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."}}