{"id":"W2792032639","doi":"10.1177/0049124117747302","title":"Optimizing Count Responses in Surveys: A Machine-learning Approach","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Social Science Research Institute, Duke University; University of British Columbia; University of Victoria","keywords":"Censoring (clinical trials); Count data; Poisson distribution; Computer science; Bayesian probability; Multinomial distribution; Machine learning; Statistics; Artificial intelligence; 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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1261021,0.0001904357,0.0004656975,0.0003745437,0.0005024675,0.00008879659,0.0004856974,0.0004130476,0.0002064663],"category_scores_gemma":[0.05589541,0.0001430688,0.00009891347,0.0008085016,0.000969517,0.00008159902,0.0003317444,0.001772408,0.00004022306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000191631,"about_ca_system_score_gemma":0.00009760294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002810711,"about_ca_topic_score_gemma":0.00001158774,"domain_scores_codex":[0.955602,0.04200788,0.0004989511,0.0005541374,0.0005520859,0.0007849384],"domain_scores_gemma":[0.9716456,0.02725698,0.00009520695,0.0003874686,0.0004944387,0.0001202895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002355199,0.003171595,0.1410369,0.000897144,0.0003104213,0.0001102425,0.05720783,0.0002073723,0.0311086,0.2061031,0.004343772,0.5531478],"study_design_scores_gemma":[0.0007691116,0.001309059,0.01869172,0.0001479116,0.00001117462,0.00002038859,0.003937999,0.04373372,0.006092307,0.9214723,0.003159029,0.0006553271],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.19576,0.0003434719,0.7935063,0.0002308245,0.0000624135,0.0004630191,0.000006438911,0.0004840971,0.00914351],"genre_scores_gemma":[0.2974737,0.00006040674,0.7017583,0.00002837145,0.000109146,0.0001304164,0.000007948908,0.00002433994,0.0004073707],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7153691,"threshold_uncertainty_score":0.9520572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6338353326777821,"score_gpt":0.602291176727981,"score_spread":0.03154415594980109,"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."}}