{"id":"W4404373849","doi":"10.1145/3702985","title":"A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms—RCR Report","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"BNP Paribas Cardif","keywords":"Computer science; Categorical variable; Artificial intelligence; Software engineering; Machine learning; Programming language; Data mining","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":[0.02242103,0.001477456,0.001805296,0.004788134,0.002196068,0.005908489,0.00698022,0.002946835,0.01706916],"category_scores_gemma":[0.140169,0.001630775,0.004038628,0.004242109,0.002824157,0.01222138,0.006364879,0.005443709,0.01158934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002727629,"about_ca_system_score_gemma":0.006920797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007447238,"about_ca_topic_score_gemma":0.0066798,"domain_scores_codex":[0.9565956,0.01902982,0.004736571,0.006343305,0.01212328,0.001171371],"domain_scores_gemma":[0.8683937,0.05734735,0.00464709,0.0518722,0.01631513,0.001424474],"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":[0.0009000588,0.0007002763,0.005699503,0.0005554059,0.0001397716,0.0004800076,0.001090308,0.02763703,0.01056862,0.0637809,0.07835115,0.8100971],"study_design_scores_gemma":[0.0002685495,0.0002153891,0.001284901,0.0001767504,0.00005835769,0.000640658,0.0004621777,0.792602,0.02849892,0.1159531,0.05960739,0.0002318323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004772072,0.0001299904,0.9653326,0.001014789,0.0001313939,0.0003544817,0.001605836,0.02545943,0.001199559],"genre_scores_gemma":[0.03248095,0.00005402823,0.9621395,0.0002406643,0.00006647711,0.0003929725,0.002295587,0.001190499,0.001139264],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02242103,"threshold_uncertainty_score":0.1185752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1091989953480633,"score_gpt":0.349668332767168,"score_spread":0.2404693374191046,"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."}}