{"id":"W3180016080","doi":"10.2196/30730","title":"Strategies for the Identification and Prevention of Survey Fraud: Data Analysis of a Web-Based Survey","year":2021,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Patient-Centered Outcomes Research Institute","keywords":"CAPTCHA; Identification (biology); Data quality; Survey data collection; Social media; Incentive; Computer science; Web application; Internet privacy; Psychology; Computer security; World Wide Web; Statistics; Business; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2206459,0.0009716067,0.00111909,0.01551975,0.001386014,0.002960014,0.001733897,0.001152886,0.001377927],"category_scores_gemma":[0.4119369,0.0007896955,0.00223254,0.01291013,0.001621276,0.002836624,0.002510882,0.001275758,0.0005696592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003033327,"about_ca_system_score_gemma":0.008670758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00580965,"about_ca_topic_score_gemma":0.006330697,"domain_scores_codex":[0.6507979,0.3008018,0.02205458,0.003945136,0.02052799,0.001872669],"domain_scores_gemma":[0.5433157,0.2989362,0.06534205,0.04463223,0.04606234,0.001711446],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000469172,0.0008497884,0.75769,0.003114269,0.001321066,0.0003174852,0.01997806,0.003014884,0.00205615,0.004809446,0.00789388,0.1984859],"study_design_scores_gemma":[0.0002535706,0.002532407,0.8484679,0.004517047,0.001089333,0.00087621,0.02352122,0.06068652,0.009920606,0.007945497,0.03987131,0.0003184263],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7245075,0.001831067,0.2327797,0.005237873,0.0002391829,0.02027478,0.005770065,0.0006880197,0.00867187],"genre_scores_gemma":[0.7607376,0.0005939868,0.2234907,0.0009280336,0.00008330672,0.01031289,0.002783037,0.0001019403,0.0009684346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7793541,"threshold_uncertainty_score":0.9610823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5100129480820306,"score_gpt":0.5479787724618534,"score_spread":0.03796582437982288,"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."}}