{"id":"W15861381","doi":"10.21432/t2k670","title":"Field Test Evaluation of Educational Software: A Description of One Approach","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Field (mathematics); Computer science; Test (biology); Quality (philosophy); Software; Product (mathematics); Alphabet; Management science; Data science; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0006364276,0.00004612644,0.0001252455,0.0004635551,0.0002010825,0.00002614144,0.000448298,0.0001225155,0.00001971171],"category_scores_gemma":[0.003036984,0.00004664622,0.00002088785,0.0001332601,0.0002009763,0.0001714689,0.00003102653,0.0002690198,5.40223e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004408177,"about_ca_system_score_gemma":0.001381099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001946854,"about_ca_topic_score_gemma":0.0002541622,"domain_scores_codex":[0.9994493,0.00003027668,0.0002026827,0.00008947335,0.0001327496,0.00009550711],"domain_scores_gemma":[0.9985964,0.0001161469,0.0004916854,0.0001922105,0.0005456382,0.00005790151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001701879,0.00007176829,0.8202371,0.00001940111,0.0000351823,9.214569e-7,0.0001689171,0.00003094907,0.0008505225,0.09247568,0.0002339404,0.08587392],"study_design_scores_gemma":[0.001851621,0.002395735,0.5241767,0.0005936085,0.0002029019,0.0007725002,0.001961582,0.006812693,0.01613604,0.4409135,0.003764671,0.0004184711],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9373442,0.001321137,0.03337272,0.02608313,0.0002766472,0.00008682771,0.000001267552,0.00001110029,0.001503004],"genre_scores_gemma":[0.9658064,0.00001815956,0.03404922,0.000007070247,0.00002183863,0.000003218073,6.770889e-7,0.000002125184,0.00009124533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3484378,"threshold_uncertainty_score":0.3635772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04008810262872196,"score_gpt":0.301355754198165,"score_spread":0.261267651569443,"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."}}