{"id":"W6942634505","doi":"10.14288/1.0402504","title":"Analyzing Cognitive Demands of a Scientific Reasoning Test Using the Linear Logistic Test Model (LLTM)","year":2021,"lang":"en","type":"article","venue":"Open Collections","topic":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Construct (python library); Cognition; Scientific reasoning; Variance (accounting); Item response theory; Logistic regression; Visual reasoning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01944198,0.001145765,0.000982051,0.002229664,0.0005625391,0.002839929,0.001518679,0.0009825386,0.004076372],"category_scores_gemma":[0.1244039,0.0005544656,0.002250438,0.002332248,0.001148642,0.002269703,0.002134602,0.001913399,0.0006129952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001514038,"about_ca_system_score_gemma":0.001894296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004793627,"about_ca_topic_score_gemma":0.005043304,"domain_scores_codex":[0.9799774,0.01224774,0.001692842,0.001791488,0.003731124,0.0005594037],"domain_scores_gemma":[0.7602285,0.2155366,0.01216448,0.006477922,0.004384088,0.001208389],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002025092,0.001873113,0.916169,0.0002835868,0.0009113311,0.0004318615,0.003037374,0.01120501,0.003788902,0.0017386,0.0008178013,0.05771833],"study_design_scores_gemma":[0.0002785725,0.004111379,0.8338206,0.00009136615,0.0002367942,0.0005066875,0.002744049,0.147574,0.00382142,0.005163032,0.001497935,0.0001542352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9789879,0.00006132989,0.01851991,0.00008322201,0.00001545416,0.0002555756,0.0002600066,0.0001058997,0.00171068],"genre_scores_gemma":[0.9819316,0.0000313046,0.01618889,0.00003836902,0.000009544942,0.0006260356,0.0005269363,0.00003824799,0.000609007],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.980558,"threshold_uncertainty_score":0.1028202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06123721490968349,"score_gpt":0.2913606096955905,"score_spread":0.230123394785907,"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."}}