{"id":"W1785571949","doi":"10.22329/celt.v8i0.4244","title":"Integrated Testlets: A New Form of Expert-Student Collaborative Testing","year":2015,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"Brock University; Trent University","keywords":"Formative assessment; Set (abstract data type); Computer science; Test (biology); Multiple choice; Psychology; Mathematics education","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0009550822,0.0001147991,0.0001823185,0.0001352874,0.0007663732,0.0001156203,0.0001178187,0.00007667212,0.00004209091],"category_scores_gemma":[0.003690504,0.0001040476,0.00002040229,0.000491336,0.00008952324,0.0001345946,0.00002997973,0.0004229959,0.00000456299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001591766,"about_ca_system_score_gemma":0.001476622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004896879,"about_ca_topic_score_gemma":0.0007448356,"domain_scores_codex":[0.9985484,0.000506396,0.0001955624,0.0001906932,0.0003433388,0.0002155626],"domain_scores_gemma":[0.9982574,0.001005651,0.0001596125,0.0000577795,0.0003264787,0.0001930633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001244365,0.0004140138,0.2626678,0.00001495035,0.0001202136,0.000006385065,0.5724607,0.0002132452,0.0009832997,0.07176223,0.01616692,0.07506581],"study_design_scores_gemma":[0.002403577,0.001517967,0.01386459,0.0005658497,0.00005835598,0.000004572015,0.5334024,0.001613046,0.0001355686,0.00804606,0.4377096,0.0006783669],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.692932,0.000304074,0.000276639,0.001369931,0.0002196524,0.0002081618,0.000001906399,0.0001303596,0.3045573],"genre_scores_gemma":[0.9849066,0.00002364735,0.003848092,0.00007502318,0.000230505,0.00001350047,0.00001074047,0.00001204568,0.01087981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4215427,"threshold_uncertainty_score":0.7402649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08347668774675397,"score_gpt":0.4111060133292314,"score_spread":0.3276293255824774,"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."}}