{"id":"W4220783775","doi":"10.1016/j.jsp.2022.03.003","title":"Cost analysis and cost-effectiveness of hand-scored and automated approaches to writing screening","year":2022,"lang":"en","type":"article","venue":"Journal of School Psychology","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Usability; Computer science; Curriculum; Raw score; Identification (biology); Machine learning; Visualization; Artificial intelligence; Data mining; Psychology; Raw data; Human–computer interaction","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":[0.004951864,0.00007680638,0.0003340951,0.0005418267,0.0005882207,0.00007891328,0.000155401,0.00005670693,0.00005260213],"category_scores_gemma":[0.0005921494,0.00008009753,0.00007053011,0.0008691557,0.0001792664,0.0001295125,0.00005119999,0.000291683,4.667966e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006163123,"about_ca_system_score_gemma":0.00009264631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001922169,"about_ca_topic_score_gemma":0.00007385553,"domain_scores_codex":[0.9980065,0.0009562093,0.0003892648,0.0001782829,0.0002683263,0.0002014603],"domain_scores_gemma":[0.9987518,0.0004470416,0.0003760067,0.00008753076,0.0001462099,0.0001914656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006781904,0.0003147192,0.9165468,0.00007626108,0.0006930484,0.00002178654,0.01143133,0.001337565,0.00629485,0.001681505,0.001107948,0.05981603],"study_design_scores_gemma":[0.001277642,0.000297702,0.9671218,0.000107333,0.0002873878,0.0000719699,0.02853903,0.0003780176,0.0002262069,0.0004298657,0.00110938,0.0001536183],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928543,0.0003546119,0.003386767,0.001868904,0.0001585984,0.0002353189,0.00000814025,0.00002294344,0.001110414],"genre_scores_gemma":[0.9964436,0.00003875253,0.003160952,0.0001440797,0.0001479742,0.00002144341,0.000003231447,0.000007525216,0.00003245684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05966242,"threshold_uncertainty_score":0.4524177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2381368086824545,"score_gpt":0.4345700443116196,"score_spread":0.1964332356291651,"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."}}