{"id":"W4406458491","doi":"10.1109/bigdata62323.2024.10825531","title":"Evaluating Blocking Biases in Entity Matching","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Blocking (statistics); Computer science; Matching (statistics); Computer network; Statistics; 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":[0.0737232,0.00124302,0.001536491,0.00235954,0.002472651,0.003344208,0.002305735,0.002323676,0.0019997],"category_scores_gemma":[0.2481158,0.0005018129,0.0009599339,0.003685399,0.002779903,0.007512685,0.005129999,0.001804867,0.00061299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002756498,"about_ca_system_score_gemma":0.003994353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00490529,"about_ca_topic_score_gemma":0.004061609,"domain_scores_codex":[0.9472908,0.03522411,0.002825172,0.005178986,0.007892674,0.001588199],"domain_scores_gemma":[0.6489184,0.294636,0.01680133,0.02597755,0.01117292,0.002493794],"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":[0.006057251,0.0009370347,0.1308698,0.001461607,0.001571724,0.0003059519,0.003280403,0.3088905,0.01006981,0.1141724,0.008839906,0.4135436],"study_design_scores_gemma":[0.0003652179,0.0009885401,0.01673856,0.0003023797,0.0005219599,0.0005066647,0.001126981,0.8088312,0.02216705,0.1382513,0.01004654,0.0001536479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4832194,0.005272036,0.4986949,0.001509542,0.0004514238,0.0007248933,0.000804143,0.001101198,0.008222488],"genre_scores_gemma":[0.8557535,0.0007116932,0.14082,0.0003962427,0.0001767467,0.0002141342,0.0007467032,0.0001654549,0.001015403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0737232,"threshold_uncertainty_score":0.3898902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6492312296609014,"score_gpt":0.5953427079241184,"score_spread":0.05388852173678305,"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."}}