{"id":"W3176788992","doi":"10.1109/icde51399.2021.00116","title":"Automating Entity Matching Model Development","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Pipeline (software); Bottleneck; Benchmark (surveying); Computer science; Process (computing); Artificial intelligence; Machine learning; Matching (statistics); Task (project management); Engineering; Systems engineering; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002858329,0.00006309662,0.0001178849,0.00006143012,0.0001888023,0.0004804615,0.0004065214,0.00002030371,0.001557146],"category_scores_gemma":[0.0006649983,0.00004862341,0.00003973063,0.000281285,0.00001259878,0.0004276791,0.0007050702,0.00005186485,0.001219331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002752498,"about_ca_system_score_gemma":0.0001182939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001837911,"about_ca_topic_score_gemma":0.000264002,"domain_scores_codex":[0.9980448,0.00008702126,0.0004410785,0.0003203154,0.0009492886,0.0001574279],"domain_scores_gemma":[0.9991258,0.0001887138,0.00007443754,0.0004373878,0.0001153888,0.00005827837],"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":[0.00000280352,0.0001757676,0.0009249089,0.00002614278,0.00003916336,0.00003496522,0.004143719,0.008184702,0.0008426566,0.2987134,0.04957125,0.6373405],"study_design_scores_gemma":[0.0005570051,0.000008469001,0.01612961,0.00005259942,0.00001604782,0.00001019884,0.0112352,0.2230251,0.01991358,0.526489,0.201914,0.0006492163],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1445723,0.00001352745,0.7647389,0.000902954,0.0001441192,0.00004113729,0.00000305264,0.00007925746,0.08950475],"genre_scores_gemma":[0.6419401,0.000002459931,0.3038473,0.002023386,0.00001791847,0.000005628254,0.00001451471,0.000004475329,0.05214423],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6366913,"threshold_uncertainty_score":0.9995583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3130788376251375,"score_gpt":0.4498523623238104,"score_spread":0.1367735246986729,"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."}}