{"id":"W4389577817","doi":"10.2196/47091","title":"Assessing and Improving Data Integrity in Web-Based Surveys: Comparison of Fraud Detection Systems in a COVID-19 Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Representativeness heuristic; Computer science; Preprint; Context (archaeology); Transparency (behavior); Data quality; Web application; Data integrity; Data science; Computer security; World Wide Web; Business; Statistics; Geography; Service (business)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2879041,0.00008150433,0.0003146104,0.001069168,0.0004707651,0.0001592866,0.0004382642,0.0001652903,0.00001163753],"category_scores_gemma":[0.04303156,0.00007585446,0.00001490516,0.002661532,0.0004779476,0.0008118174,0.0003251163,0.0009639091,0.000008912517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003343523,"about_ca_system_score_gemma":0.000968197,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05024273,"about_ca_topic_score_gemma":0.1290967,"domain_scores_codex":[0.8421491,0.1551951,0.0006202421,0.0004230076,0.0009854385,0.0006270649],"domain_scores_gemma":[0.9627358,0.03655845,0.0001224344,0.0002950944,0.0001746505,0.0001135668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009953629,0.0004575468,0.8588376,0.0002167892,0.00001205997,0.00001767608,0.1110082,0.00007550514,0.0008105699,0.00002657466,0.000115171,0.02742691],"study_design_scores_gemma":[0.0008141334,0.0001739166,0.7157077,0.00006129503,0.00000111463,1.949836e-7,0.2547354,0.02819836,0.00007532408,0.00004153007,0.0001274946,0.00006356703],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966754,0.0001092572,0.001770739,0.0002043316,0.000140938,0.0009261583,0.00002230123,0.00004117658,0.0001096816],"genre_scores_gemma":[0.9997645,0.00001393794,0.00005171727,0.000005054245,0.00001884459,0.0001138116,0.00001609133,0.000005851973,0.00001019401],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2448725,"threshold_uncertainty_score":0.9650294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7110174167559848,"score_gpt":0.6488890374946584,"score_spread":0.06212837926132642,"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."}}