{"id":"W4297920516","doi":"10.31234/osf.io/nu26z","title":"Model-agnostic unsupervised detection of bots in a Likert-type questionnaire","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Respondent; Computer science; Likert scale; Permutation (music); Calibration; Sensitivity (control systems); Statistical hypothesis testing; Null hypothesis; Type I and type II errors; Relation (database); Outlier; Data mining; Artificial intelligence; Machine learning; Algorithm; Statistics; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02095258,0.0007688697,0.00136297,0.001842029,0.0008045143,0.001541307,0.002732036,0.001693175,0.001697495],"category_scores_gemma":[0.08793039,0.0006376508,0.001233631,0.001479829,0.00173406,0.002514491,0.001982194,0.001944339,0.001004654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008771941,"about_ca_system_score_gemma":0.001132992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001151616,"about_ca_topic_score_gemma":0.001655481,"domain_scores_codex":[0.9857675,0.009568752,0.0005457145,0.002255163,0.001473885,0.0003890213],"domain_scores_gemma":[0.9055822,0.06763903,0.006789991,0.01566044,0.003590643,0.0007377522],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001034182,0.001230698,0.1880148,0.0008561115,0.0005934439,0.000457447,0.002765544,0.1718952,0.01818893,0.07804708,0.008414742,0.5285017],"study_design_scores_gemma":[0.00004817806,0.0001619039,0.01096067,0.00005457463,0.00003437544,0.00026979,0.0002773062,0.9274839,0.005761297,0.05334779,0.001554623,0.00004558133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05937816,0.00005954251,0.9381354,0.0002499,0.00002825386,0.0002157229,0.0001244796,0.001007662,0.000800904],"genre_scores_gemma":[0.6826236,0.0000570102,0.3147635,0.000310804,0.00004284911,0.0004750033,0.0004193691,0.0000963786,0.001211428],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9790474,"threshold_uncertainty_score":0.1108091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1419034585349527,"score_gpt":0.3720307854747307,"score_spread":0.230127326939778,"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."}}