{"id":"W2980427199","doi":"10.1139/cjc-2019-0291","title":"Formative assessments using text messages to develop students’ ability to provide causal reasoning in general chemistry","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Chemistry","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Construct (python library); Class (philosophy); Mathematics education; Psychology; Knowledge survey; Task (project management); Chemistry; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002797867,0.0002154465,0.0003894518,0.0001373037,0.0001010437,0.00009083588,0.0005331232,0.0001697084,0.001080967],"category_scores_gemma":[0.0009893434,0.0002215572,0.00005324512,0.0006241131,0.00004193868,0.0001309774,0.00005139179,0.0009925186,0.00002421139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001129493,"about_ca_system_score_gemma":0.001720615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002863471,"about_ca_topic_score_gemma":0.0002652082,"domain_scores_codex":[0.997968,0.0002800697,0.0006199191,0.0002833449,0.0002920307,0.0005566524],"domain_scores_gemma":[0.9982644,0.000100753,0.0003306268,0.0002855998,0.0004312561,0.0005873997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001328499,0.00006998039,0.7419388,0.0001403667,0.0001459554,0.0002289908,0.01989604,0.00129943,0.2286143,0.00001657131,0.001698537,0.005818256],"study_design_scores_gemma":[0.002986319,0.0002263652,0.8753746,0.001360722,0.00005072336,0.0007036165,0.01594257,0.0001229789,0.07969912,0.00009175543,0.02223733,0.001203882],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879173,0.00004237441,0.001360967,0.0002020694,0.0003630932,0.0001563126,0.00001059905,0.000008020166,0.00993924],"genre_scores_gemma":[0.9820049,1.680393e-7,0.01394693,0.0003294587,0.0002034596,0.000006174888,0.000004928654,0.00002872568,0.003475269],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1489151,"threshold_uncertainty_score":0.9998322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03476161188374043,"score_gpt":0.4011118727772234,"score_spread":0.3663502608934829,"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."}}