{"id":"W4388821770","doi":"10.3758/s13428-023-02246-7","title":"Model-agnostic unsupervised detection of bots in a Likert-type questionnaire","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Respondent; Computer science; Likert scale; Permutation (music); Calibration; Sensitivity (control systems); Statistical hypothesis testing; Type I and type II errors; Null hypothesis; Outlier; Relation (database); Artificial intelligence; Data mining; Machine learning; Statistics; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01375098,0.0001239039,0.0002760208,0.0009540042,0.0001137249,0.00002682461,0.0002465256,0.0001752571,0.00002329246],"category_scores_gemma":[0.01472084,0.0001211534,0.00006504906,0.002197848,0.0001159644,0.0001128221,0.0001232373,0.000456549,0.00002260823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001211188,"about_ca_system_score_gemma":0.0001352636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004458477,"about_ca_topic_score_gemma":0.0001193161,"domain_scores_codex":[0.9961967,0.00208497,0.0004555577,0.0002864283,0.0005726946,0.0004036649],"domain_scores_gemma":[0.9961357,0.002697511,0.00006631399,0.0004719332,0.0005367212,0.00009189088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002257004,0.0008436152,0.02463545,0.0006968249,0.00002145016,0.00005114413,0.003190486,0.00118575,0.4831457,0.002726511,0.0009191345,0.4823583],"study_design_scores_gemma":[0.0008221921,0.0005605182,0.1207913,0.0008824787,0.00004564901,0.00001489844,0.000411471,0.24547,0.3492488,0.2811815,0.00008424393,0.0004869345],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8080252,0.00006503999,0.190595,0.00005795108,0.00009636611,0.0006010758,0.000005587221,0.0004467889,0.0001069663],"genre_scores_gemma":[0.7767241,0.00006025019,0.222606,0.00000276911,0.00001584345,0.0003116968,0.000006936208,0.00003450845,0.0002378331],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4818713,"threshold_uncertainty_score":0.9935786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6771024707565433,"score_gpt":0.6449932992528221,"score_spread":0.03210917150372117,"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."}}