{"id":"W4254490032","doi":"10.31219/osf.io/8b9xs","title":"Evaluating 'Graphical Perception' with CNNs","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Visualization; Perception; Convolutional neural network; Task (project management); Artificial intelligence; Visual perception; Human–computer interaction; Pattern recognition (psychology); Psychology; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004195313,0.0001677199,0.0001676306,0.00013698,0.0001033312,0.00049198,0.001096338,0.0001252443,0.0004681566],"category_scores_gemma":[0.00004604927,0.0001228697,0.00006117175,0.0002838156,0.00008522428,0.0001748523,0.00133716,0.0002341022,0.0002280083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002698998,"about_ca_system_score_gemma":0.0001898942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002175273,"about_ca_topic_score_gemma":0.00001863428,"domain_scores_codex":[0.998441,0.0000776799,0.0002123952,0.0005778338,0.0005133566,0.0001776694],"domain_scores_gemma":[0.9985369,0.00002784351,0.0001102302,0.0009441001,0.0002824635,0.0000984484],"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":[0.00002609774,0.0007074736,0.009022461,0.0004288081,0.0004180903,0.00003963054,0.004070495,0.004963293,0.0003728219,0.7672418,0.1097338,0.1029752],"study_design_scores_gemma":[0.0001589024,0.0001272879,0.002084472,0.00008341506,0.00002094713,0.00000784988,0.00003517575,0.9886317,0.00002041485,0.006344446,0.00219503,0.0002904155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005653355,0.000005434473,0.9833611,0.0008131519,0.0002356972,0.0001198618,0.000006385882,0.0003001741,0.009504798],"genre_scores_gemma":[0.22814,0.00003433287,0.7650101,0.002451285,0.0004256183,0.00002222153,0.0001733572,0.00002528835,0.003717846],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9836683,"threshold_uncertainty_score":0.5125986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09518307370229437,"score_gpt":0.4070941792039013,"score_spread":0.3119111055016069,"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."}}