{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007505352,0.0001241402,0.0002846097,0.0005346213,0.00008613004,0.00007741444,0.0007741742,0.0002092987,0.00003088732],"category_scores_gemma":[0.002873637,0.00010438,0.00007263453,0.003265882,0.00007551221,0.0002046883,0.0001176501,0.0003731363,0.000009267442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005800695,"about_ca_system_score_gemma":0.00002451858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000229029,"about_ca_topic_score_gemma":0.00003461259,"domain_scores_codex":[0.9947683,0.003796409,0.0004406533,0.0005572211,0.0002041848,0.000233196],"domain_scores_gemma":[0.9956017,0.003470008,0.00009288227,0.000649012,0.000133839,0.00005257264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008235098,0.0002812982,0.009599475,0.00002199487,0.00001770275,0.000003523346,0.000210941,0.00005717604,0.1088047,0.01488482,0.0001082713,0.8651866],"study_design_scores_gemma":[0.001099484,0.0002104051,0.940791,0.00002360785,0.000003623976,0.000004111884,0.00001435158,0.01030811,0.03070262,0.01622647,0.0004997707,0.000116499],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2842393,0.00007902093,0.7126823,0.0006322364,0.000834759,0.0001738881,0.000001301843,0.00008223021,0.001274967],"genre_scores_gemma":[0.8751352,0.00003233518,0.124463,0.0001660415,0.00002581696,0.00003315471,0.000001680533,0.000003958695,0.0001387856],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9311914,"threshold_uncertainty_score":0.4256493,"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."}}