{"id":"W4283313359","doi":"10.2196/35797","title":"Strategies and Lessons Learned During Cleaning of Data From Research Panel Participants: Cross-sectional Web-Based Health Behavior Survey Study","year":2022,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; University of South Carolina; South Carolina Clinical and Translational Research Institute, Medical University of South Carolina; National Cancer Institute; National Institutes of Health; Moffitt Cancer Center; Medical University of South Carolina","keywords":"Checklist; Data quality; The Internet; Survey data collection; Web application; Quality (philosophy); Psychology; Data science; Computer science; Medical education; World Wide Web; Medicine; Business; Marketing","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","sts"],"consensus_categories":[],"category_scores_codex":[0.2513639,0.0001188146,0.0003230941,0.000558375,0.006030892,0.000312352,0.001162298,0.0000923781,0.0007003007],"category_scores_gemma":[0.007053965,0.0001206838,0.00003340223,0.001579311,0.001818761,0.001070458,0.001529486,0.001734499,0.00001579475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003404983,"about_ca_system_score_gemma":0.003454656,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03897391,"about_ca_topic_score_gemma":0.03044534,"domain_scores_codex":[0.8000233,0.1932966,0.0007530692,0.0008449601,0.003498247,0.001583921],"domain_scores_gemma":[0.9666275,0.03168745,0.0001615141,0.0006196553,0.0006608359,0.0002430711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006172775,0.00117633,0.9275106,0.00003335645,0.00005326358,0.00001969757,0.06270967,0.00005533631,0.000420073,0.0002887393,0.000253665,0.001306551],"study_design_scores_gemma":[0.0009245579,0.0005852593,0.8181618,0.00001075063,0.000001896779,5.190133e-7,0.179549,0.0001848873,0.00004378794,0.0002048035,0.0002462869,0.00008644977],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967023,0.0001419624,0.00002942818,0.0004135715,0.0001274538,0.0009564759,0.001401901,0.00003744914,0.0001894955],"genre_scores_gemma":[0.9989517,0.00004696808,0.000103176,0.000008823059,0.00005085745,0.000433993,0.0002310897,0.000016389,0.0001570402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.24431,"threshold_uncertainty_score":0.9952631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8942829336120554,"score_gpt":0.6843921430569075,"score_spread":0.2098907905551478,"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."}}