{"id":"W4388963821","doi":"10.48550/arxiv.2311.13517","title":"Learning-Based Relaxation of Completeness Requirements for Data Entry Forms","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"BNP Paribas Cardif","keywords":"Completeness (order theory); Computer science; Field (mathematics); Lacquer; Data mining; Artificial intelligence; Machine learning; 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":[0.02096196,0.002056442,0.002521083,0.00307017,0.001555567,0.004027259,0.00413319,0.00266048,0.002746243],"category_scores_gemma":[0.1690669,0.001902489,0.002651532,0.002655017,0.002832852,0.01115075,0.005081515,0.006435376,0.001886024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002701018,"about_ca_system_score_gemma":0.009921479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007774979,"about_ca_topic_score_gemma":0.01250143,"domain_scores_codex":[0.9626105,0.01048648,0.005758368,0.008171204,0.01144761,0.001525803],"domain_scores_gemma":[0.83203,0.1096129,0.0155842,0.0222996,0.01875958,0.001713724],"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":[0.002104097,0.001088751,0.05551124,0.002139266,0.0003356391,0.001074909,0.003131137,0.1916786,0.01915391,0.02344006,0.03546989,0.6648725],"study_design_scores_gemma":[0.0001972878,0.0002790524,0.003285477,0.0002098918,0.00009435283,0.0005414748,0.0004883395,0.9422408,0.0185337,0.02064367,0.01340515,0.00008077818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1151856,0.0006735679,0.852972,0.001991876,0.0001232649,0.001093614,0.004606303,0.02073677,0.002616917],"genre_scores_gemma":[0.4155401,0.0003779996,0.5610617,0.001679917,0.0001425785,0.0009055482,0.01573324,0.001420632,0.003138186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02096196,"threshold_uncertainty_score":0.1108587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.649970621585224,"score_gpt":0.3571455270505782,"score_spread":0.2928250945346458,"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."}}