{"id":"W4390393512","doi":"10.1016/j.chbah.2023.100040","title":"A review of assessment for learning with artificial intelligence","year":2023,"lang":"en","type":"review","venue":"Computers in Human Behavior Artificial Humans","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Scopus; Web of science; Artificial intelligence; Field (mathematics); Work (physics); Applications of artificial intelligence; Computer science; Engineering ethics; Engineering; Political science; MEDLINE","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002393689,0.0005248553,0.002159167,0.0005799917,0.0007948834,0.0001822041,0.001105368,0.0002953407,0.0001624956],"category_scores_gemma":[0.00007889474,0.0004935153,0.0006631285,0.001130068,0.0005551526,0.0001427964,0.0001992643,0.0007311286,0.00002888633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000462492,"about_ca_system_score_gemma":0.0006080191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002118814,"about_ca_topic_score_gemma":0.001516118,"domain_scores_codex":[0.9952496,0.0006220039,0.001837728,0.0007952289,0.0007889637,0.0007064466],"domain_scores_gemma":[0.9975499,0.000650292,0.001004381,0.000430978,0.0002388236,0.0001256211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006828664,0.0004982075,0.000135655,0.03489343,0.00008868043,0.0000365129,0.002471736,0.000007772732,0.000001127109,0.07359865,0.0004204908,0.8878409],"study_design_scores_gemma":[0.0001625837,0.0008977276,0.0001023326,0.274951,0.002979424,0.000002553428,0.003743921,0.00003345118,0.00000153026,0.00385229,0.7114352,0.001837995],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001509557,0.9829538,0.005298186,0.00005842577,0.00151182,0.008208286,0.00004395779,0.0003037727,0.0014708],"genre_scores_gemma":[0.0001457849,0.9951825,0.001954404,0.00002557656,0.0006918482,0.001410046,0.0002329419,0.000109809,0.000247105],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8860029,"threshold_uncertainty_score":0.9997516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.272267509277996,"score_gpt":0.506271922895003,"score_spread":0.234004413617007,"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."}}