{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104737,0.0002318143,0.0004387807,0.0003719667,0.00005447832,0.00002029937,0.0002666087,0.0002848051,0.0001779953],"category_scores_gemma":[0.002152489,0.0002404373,0.000109541,0.0002846295,0.00003104724,0.0000532036,0.0003698159,0.0006031062,0.000003914332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001997644,"about_ca_system_score_gemma":0.0001846716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001049941,"about_ca_topic_score_gemma":0.0004473258,"domain_scores_codex":[0.9982836,0.000222543,0.0006468897,0.0003581259,0.000319367,0.000169486],"domain_scores_gemma":[0.9984781,0.0004415162,0.0002534957,0.0005920499,0.0001928671,0.00004204542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008907394,0.003541234,0.02691041,0.01306986,0.0004018194,0.00004201005,0.01115793,0.845674,0.01037546,0.03431082,0.004782442,0.04884329],"study_design_scores_gemma":[0.0002365633,0.0001003279,0.001978327,0.0006831168,0.00004834775,0.000003615135,0.00006147748,0.4954806,0.005074184,0.4959493,0.00001752998,0.0003666002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5245341,0.0002091055,0.4715526,0.00009206031,0.0004479266,0.000772105,0.00002404583,0.0008476283,0.001520439],"genre_scores_gemma":[0.9511246,0.00008331781,0.0481962,0.00002801931,0.00002024907,0.000175705,0.00004129554,0.00004357534,0.0002870189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4616385,"threshold_uncertainty_score":0.9804749,"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."}}