{"id":"W7132987028","doi":"","title":"Test Validation and Complex, Dynamic Systems: The Case of the Pedagogical Content Knowledge for Supporting English Learners Test (PeCKSELT)","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Test (biology); Thematic analysis; Interpretation (philosophy); Item response theory; Test validity; Variety (cybernetics)","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":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.01726599,0.0006008199,0.001233734,0.0005284145,0.001563085,0.0007473372,0.001412145,0.0004449971,0.00009060526],"category_scores_gemma":[0.4701907,0.0003320455,0.0004725112,0.003517183,0.0005321378,0.0001600821,0.0003979616,0.0007497986,0.00001703694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001326209,"about_ca_system_score_gemma":0.000376272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001041618,"about_ca_topic_score_gemma":0.0006169307,"domain_scores_codex":[0.9930873,0.001528789,0.00238786,0.001258312,0.0009550906,0.0007826769],"domain_scores_gemma":[0.7668862,0.2249717,0.004050802,0.001258839,0.002626639,0.0002058232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0005570049,0.001386913,0.1130697,0.005405774,0.0006547728,0.0002087609,0.5322995,0.002392062,0.01315875,0.00425467,0.0150471,0.311565],"study_design_scores_gemma":[0.0009340195,0.0005023218,0.02528455,0.0005982049,0.0003185254,0.0002284334,0.8832712,0.08579254,0.0001697391,0.0004355174,0.001987396,0.0004775114],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821833,0.002009933,0.002422439,0.0006639389,0.006570548,0.00330983,0.000179859,0.0001216636,0.00253848],"genre_scores_gemma":[0.9709359,0.0001951036,0.0008065305,0.00002048697,0.0002681128,0.0001840724,0.00008737812,0.00006735566,0.02743505],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4529247,"threshold_uncertainty_score":0.9999132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6593913137566458,"score_gpt":0.5615762568738744,"score_spread":0.09781505688277148,"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."}}