{"id":"W4225143092","doi":"10.1145/3533021","title":"A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Categorical variable; Computer science; Field (mathematics); Machine learning; Data mining; Artificial intelligence; Set (abstract data type); Data field; Software; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004931939,0.001686555,0.001250779,0.004273109,0.001170847,0.001474246,0.003212098,0.001880351,0.004417256],"category_scores_gemma":[0.02738533,0.0007033753,0.001387677,0.003322736,0.001058894,0.004979424,0.001940931,0.002803797,0.003050707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001424576,"about_ca_system_score_gemma":0.003174063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007082495,"about_ca_topic_score_gemma":0.01213031,"domain_scores_codex":[0.9945523,0.001908194,0.0004692055,0.001221026,0.001624417,0.0002248018],"domain_scores_gemma":[0.9812977,0.01181665,0.001564872,0.002591624,0.00232946,0.0003997379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002605755,0.0004191875,0.004663484,0.0002878837,0.00004684005,0.0002211632,0.0005820054,0.03144934,0.004877379,0.004623132,0.01789127,0.9346777],"study_design_scores_gemma":[0.00006709532,0.0001811662,0.001742203,0.00007590486,0.0000227692,0.0004358819,0.0002277738,0.9602975,0.007303168,0.01606034,0.01349663,0.00008952218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009367939,0.0002681941,0.969764,0.0005324262,0.00004230552,0.0002709133,0.0008095577,0.01803589,0.0009087765],"genre_scores_gemma":[0.07354237,0.0001032244,0.9230017,0.0002093728,0.00005083225,0.0002796369,0.00121832,0.0001652905,0.001429158],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007082495,"threshold_uncertainty_score":0.02608293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3306833255399733,"score_gpt":0.4220707860804389,"score_spread":0.09138746054046559,"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."}}