{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07807352,0.0005692209,0.0006326365,0.004783844,0.006956192,0.01023417,0.002269691,0.004047852,0.001153817],"category_scores_gemma":[0.172479,0.0008695651,0.0007494239,0.004383236,0.03341335,0.01181228,0.01062288,0.005526381,0.0002694108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01027915,"about_ca_system_score_gemma":0.008564191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01223986,"about_ca_topic_score_gemma":0.01273005,"domain_scores_codex":[0.9117675,0.066843,0.003101615,0.004053744,0.01196749,0.00226668],"domain_scores_gemma":[0.6909615,0.273457,0.01024665,0.01263835,0.01098232,0.001714227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0001490299,0.0001620203,0.06827345,0.0005863371,0.00005146399,0.007116092,0.5353421,0.002094883,0.002860608,0.2662369,0.004826469,0.1123008],"study_design_scores_gemma":[0.0001206282,0.0005367277,0.0830752,0.004051344,0.00009853483,0.008234798,0.4088067,0.01849207,0.01628588,0.2475749,0.2122785,0.000444759],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6921819,0.003031058,0.1508274,0.04919147,0.0003145043,0.0007436529,0.0002446789,0.0002211444,0.103244],"genre_scores_gemma":[0.9502811,0.0004568889,0.04529942,0.001378965,0.00005279056,0.0003491297,0.00007434106,0.00009547265,0.002011895],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.07807352,"threshold_uncertainty_score":0.4128972,"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."}}