{"id":"W7133447372","doi":"","title":"Optimal testing situations for the automated analysis of cognitive components in natural language : a systematic literature review.","year":2025,"lang":"en","type":"preprint","venue":"ORBi UMONS","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Cognition; Natural language; Component (thermodynamics); Systematic review","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":[0.008623844,0.0002533569,0.001547967,0.001999703,0.000152986,0.0002159232,0.001214519,0.0001616117,0.0000156509],"category_scores_gemma":[0.3760363,0.0001462707,0.0005471329,0.0128867,0.00006997264,0.00006532139,0.0006373876,0.0005740628,0.000002239712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005520597,"about_ca_system_score_gemma":0.0001207888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001142127,"about_ca_topic_score_gemma":0.00008158526,"domain_scores_codex":[0.9955506,0.001256693,0.001548352,0.0006131092,0.0007750511,0.0002562271],"domain_scores_gemma":[0.8327456,0.1636712,0.001462324,0.0008981025,0.001181039,0.0000417102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000450674,0.00209714,0.1263741,0.3483494,0.03185564,0.0003992456,0.0709633,0.2363593,0.00197987,0.001061231,0.03347981,0.1466303],"study_design_scores_gemma":[0.0002295678,0.00001881924,0.06664243,0.09946434,0.002919903,0.000004873275,0.002091961,0.8281705,0.000009349585,0.0002493481,0.000005820541,0.000193131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.3266215,0.5517759,0.09002365,0.003256822,0.003813672,0.01441352,0.0060253,0.0007156287,0.003353967],"genre_scores_gemma":[0.9467613,0.002091687,0.04917745,0.0002647896,0.00004567092,0.0006503949,0.000378752,0.00001377345,0.0006161929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6201398,"threshold_uncertainty_score":0.6292196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.309326438312249,"score_gpt":0.4852953835068626,"score_spread":0.1759689451946136,"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."}}