{"id":"W2893953242","doi":"10.1177/1541931218621082","title":"Usability Analysis of Freeform Marking on Engineering Problem Solving","year":2018,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Usability; Formative assessment; Consistency (knowledge bases); Computer science; Test (biology); Perspective (graphical); Group (periodic table); Sample (material); Mathematics education; Human–computer interaction; Psychology; Artificial intelligence","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":[0.01656246,0.0008567905,0.0008139756,0.003435488,0.000502325,0.0009597099,0.0005578779,0.0004636467,0.001899634],"category_scores_gemma":[0.08945355,0.0002553887,0.00108305,0.00183567,0.0005436536,0.0009940577,0.001049937,0.0003627145,0.0003219475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006128627,"about_ca_system_score_gemma":0.0005510177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009866483,"about_ca_topic_score_gemma":0.001549788,"domain_scores_codex":[0.9767483,0.01399345,0.002020495,0.0008611556,0.005834583,0.0005418704],"domain_scores_gemma":[0.7898307,0.1717063,0.009700163,0.006044636,0.02150415,0.001214004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.009057068,0.002496719,0.2791788,0.003187988,0.0005716123,0.0003746995,0.03654055,0.002899337,0.04630586,0.0005465324,0.002502339,0.6163384],"study_design_scores_gemma":[0.0002542893,0.0152312,0.9356123,0.0004840442,0.0003135904,0.000455546,0.01023249,0.01021984,0.02247418,0.0004480265,0.004060693,0.0002137416],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920219,0.000120083,0.005092132,0.0000264704,0.00002771512,0.0005199731,0.0001482633,0.0001135696,0.0019298],"genre_scores_gemma":[0.9853396,0.0001177503,0.01190819,0.00003662406,0.00004460229,0.0008686705,0.0003468785,0.00005878526,0.001278844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01656246,"threshold_uncertainty_score":0.08759171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01859004852677291,"score_gpt":0.2736410332256983,"score_spread":0.2550509846989253,"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."}}