{"id":"W4408293278","doi":"10.1037/met0000746","title":"Unsupervised [randomly responding] survey bot detection: In search of high classification accuracy.","year":2025,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Artificial intelligence; Pattern recognition (psychology); Statistical analysis; Computer science; Psychology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0282382,0.001002298,0.001254417,0.001818392,0.001029242,0.001692645,0.002560696,0.002604279,0.001059138],"category_scores_gemma":[0.1434351,0.0005366796,0.0009767291,0.001636901,0.001725669,0.002782115,0.001715782,0.002315441,0.001242813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0012311,"about_ca_system_score_gemma":0.001676624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001886449,"about_ca_topic_score_gemma":0.003230181,"domain_scores_codex":[0.9748639,0.01712822,0.0008850446,0.003924471,0.002742344,0.0004560103],"domain_scores_gemma":[0.8431159,0.09433659,0.01477482,0.03650806,0.0100612,0.001203384],"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":[0.002116479,0.001910973,0.3617477,0.0009219027,0.001117669,0.0003070135,0.001789069,0.1208274,0.009676894,0.02072579,0.02750422,0.451355],"study_design_scores_gemma":[0.0001497708,0.0004983698,0.03438304,0.0001060991,0.00008479419,0.0003547542,0.0003526776,0.9241081,0.006441019,0.02983414,0.003618422,0.00006879763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3367841,0.0005448865,0.6484448,0.001872629,0.0002377211,0.00146688,0.001089843,0.004231828,0.005327243],"genre_scores_gemma":[0.7839919,0.0000988308,0.2114697,0.0009587432,0.00009063465,0.0006120915,0.001193635,0.0001257667,0.001458752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9717618,"threshold_uncertainty_score":0.1493397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1668738952243964,"score_gpt":0.4706631522301324,"score_spread":0.3037892570057359,"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."}}