{"id":"W2012210612","doi":"10.1016/j.ssresearch.2015.03.006","title":"Should we trust survey data? Assessing response simplification and data fabrication","year":2015,"lang":"en","type":"article","venue":"Social Science Research","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Data quality; Quality (philosophy); Task (project management); Computer science; Survey data collection; Focus (optics); Unit (ring theory); Data science; Psychology; Engineering; Statistics; Operations management; Mathematics education; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch","research_integrity"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch","research_integrity"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.5607435,0.00009246705,0.0001655745,0.0003791333,0.00417152,0.0007712424,0.003460457,0.0002016476,0.00003099751],"category_scores_gemma":[0.3326066,0.00008994372,0.00001086567,0.004061702,0.006253953,0.002687974,0.001673061,0.0004927358,0.00005138198],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003580355,"about_ca_system_score_gemma":0.005867388,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006691021,"about_ca_topic_score_gemma":0.002300398,"domain_scores_codex":[0.9220738,0.07263732,0.0002902448,0.001193834,0.002823183,0.0009816027],"domain_scores_gemma":[0.9729744,0.02372992,0.0001018176,0.001275706,0.001470825,0.0004473931],"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":[0.01325202,0.0004487874,0.3263907,0.00002415547,0.00003615717,0.00002152222,0.1097236,0.000001876442,0.02080493,0.01782753,0.06095706,0.4505116],"study_design_scores_gemma":[0.0002104151,0.00003869509,0.9278252,0.000007042674,0.0000046585,0.000001012158,0.02766011,0.0005961686,0.0001001955,0.002986941,0.04041042,0.0001591999],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651804,0.0004487174,0.002678841,0.01881073,0.000647978,0.0005891546,0.0002184171,0.0001053307,0.01132042],"genre_scores_gemma":[0.9973475,0.0001302154,0.00132453,0.00005817245,0.0003774303,0.00000929588,0.0001131973,0.000009370459,0.0006302282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6014345,"threshold_uncertainty_score":0.9999235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9400145018184716,"score_gpt":0.7066783022504856,"score_spread":0.233336199567986,"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."}}