{"id":"W2510347771","doi":"10.1021/acs.jchemed.6b00028","title":"Score Increase and Partial-Credit Validity When Administering Multiple-Choice Tests Using an Answer-Until-Correct Format","year":2016,"lang":"en","type":"article","venue":"Journal of Chemical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"Brock University","keywords":"Allotment; Test (biology); Post hoc; Multiple choice; Econometrics; Polytomous Rasch model; Statistics; Actuarial science; Computer science; Psychology; Mathematics; Economics; Medicine; Psychometrics; Internal medicine; Item response theory","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":[],"consensus_categories":[],"category_scores_codex":[0.0006335465,0.00009795926,0.0001696871,0.0000681263,0.0001442133,0.0001219906,0.0001884461,0.00008364615,0.0001109156],"category_scores_gemma":[0.001803716,0.00007257398,0.0000592746,0.00008948369,0.0001171281,0.00118008,0.00003705895,0.0001118229,0.000002429535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001890759,"about_ca_system_score_gemma":0.0005067624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002899892,"about_ca_topic_score_gemma":0.00004967707,"domain_scores_codex":[0.9988651,0.00009930995,0.0003330931,0.0001222029,0.0003781334,0.0002022064],"domain_scores_gemma":[0.9985471,0.0004751707,0.0003525951,0.00009644713,0.0002335447,0.0002951126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001358869,0.0005302277,0.7827125,0.00002810384,0.00002672891,0.000002272487,0.00927846,4.392551e-7,0.1793043,0.00006148654,0.002554718,0.02536488],"study_design_scores_gemma":[0.009088639,0.001375422,0.5501052,0.00353913,0.001099006,0.0003833162,0.03487734,0.001099271,0.229942,0.006685682,0.1591856,0.002619418],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972838,0.00005995072,0.0002187513,0.0008303779,0.001086798,0.00009769727,0.000001868481,0.00001302674,0.0004077237],"genre_scores_gemma":[0.9962081,0.00004148002,0.001247721,0.00009419795,0.002327796,0.000002452064,0.000001806672,0.000008649216,0.00006775559],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2326073,"threshold_uncertainty_score":0.2959481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09711035673035426,"score_gpt":0.3936019198884978,"score_spread":0.2964915631581435,"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."}}