{"id":"W2736595548","doi":"","title":"POSTER: A Validity Argument Approach to Collaborative Development of the Colleges Mathematics Assessment Program","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Argument (complex analysis); Test (biology); Mathematics education; Computer science; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008781064,0.0001701611,0.0002614071,0.00004911509,0.0004083374,0.0001084788,0.0007081878,0.00007716592,0.0001497188],"category_scores_gemma":[0.0001064726,0.00009108636,0.00006001339,0.0004071523,0.0002628759,0.0001382684,0.0002574499,0.00006597025,0.00005158593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002436202,"about_ca_system_score_gemma":0.001771953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004830974,"about_ca_topic_score_gemma":0.0002569992,"domain_scores_codex":[0.9978902,0.0002171362,0.0003761626,0.0002794402,0.0008797066,0.0003572922],"domain_scores_gemma":[0.9986292,0.0001816015,0.0002466936,0.0003045613,0.000503567,0.0001344194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001016026,0.00637807,0.1450273,0.0002088107,0.0005123098,0.000002487679,0.2338897,0.000001565931,0.0127717,0.4127656,0.01965495,0.168686],"study_design_scores_gemma":[0.003863414,0.0008479833,0.3721499,0.001792275,0.0002044383,0.000001756538,0.1001458,0.00005130716,0.02399788,0.008331245,0.486701,0.001912997],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5015751,0.00002957166,0.007716364,0.005548357,0.000671582,0.004731094,0.00005545177,0.0001385796,0.4795339],"genre_scores_gemma":[0.9457167,0.00003140379,0.04664149,0.00004937105,0.00005334662,0.0003832296,0.000001373128,0.000009587176,0.007113459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4724204,"threshold_uncertainty_score":0.3714394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08059059746095346,"score_gpt":0.3733509050348911,"score_spread":0.2927603075739377,"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."}}