{"id":"W4405622011","doi":"10.1177/01466216241310600","title":"An Information Manifold Perspective for Analyzing Test Data","year":2024,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital; McGill University","funders":"","keywords":"Item response theory; Mathematics; Measure (data warehouse); Metric (unit); Computer science; Test (biology); Manifold (fluid mechanics); Perspective (graphical); Scale (ratio); Artificial intelligence; Data mining; Statistics; Psychometrics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01793241,0.0002074922,0.0003120292,0.0004719866,0.0002104532,0.0009078548,0.001912627,0.000132749,0.0002446172],"category_scores_gemma":[0.03541715,0.0001327557,0.00009340419,0.001844855,0.0000542852,0.0007007443,0.0001708481,0.0002446277,0.0002875839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001387683,"about_ca_system_score_gemma":0.00003377419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000100996,"about_ca_topic_score_gemma":0.000004066246,"domain_scores_codex":[0.9959873,0.0001120892,0.0007973635,0.001057425,0.001650745,0.0003950602],"domain_scores_gemma":[0.9893472,0.008083365,0.0001927503,0.001651283,0.0005553286,0.0001701278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001348422,0.0003738735,0.002288302,0.00002229313,0.00007631572,0.000004916293,0.0005252307,0.00007151246,0.005281869,0.1320227,0.04878762,0.8104105],"study_design_scores_gemma":[0.001681932,0.001642628,0.123611,0.00008674321,0.0001439363,0.00003515967,0.009089461,0.01582799,0.0005510147,0.6398067,0.2064317,0.001091775],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009968944,0.001017952,0.9131413,0.002160958,0.001715724,0.001266798,0.0001646642,0.0005490098,0.07001472],"genre_scores_gemma":[0.9578236,0.00001782837,0.0411517,0.0005583303,0.0002881813,0.0001013475,0.00002729786,0.00001029997,0.000021454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9478546,"threshold_uncertainty_score":0.9727079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7563916288387372,"score_gpt":0.5558183455944733,"score_spread":0.2005732832442639,"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."}}