{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01149344,0.00005917964,0.0001050335,0.00030893,0.00006302329,0.001002147,0.0003978563,0.00001826329,0.001887228],"category_scores_gemma":[0.003037847,0.00004182712,0.00004648795,0.0007405827,0.00001829231,0.0005975924,0.0003573195,0.00008787863,0.001114694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003086164,"about_ca_system_score_gemma":0.00003124947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005871064,"about_ca_topic_score_gemma":0.001187266,"domain_scores_codex":[0.9979011,0.0001984195,0.0004118014,0.0003580917,0.0009576734,0.0001729056],"domain_scores_gemma":[0.9977769,0.001817901,0.00003127656,0.0003128286,0.00002813813,0.00003297003],"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":[0.000005522879,0.00008699322,0.001396875,0.00003746561,0.00001582578,0.00007018458,0.002404613,0.004076412,0.0007341018,0.135069,0.02039029,0.8357127],"study_design_scores_gemma":[0.0003791462,0.00005970822,0.008699613,0.0004605206,0.00002090732,0.000006596027,0.01073867,0.2868971,0.0008685259,0.5688907,0.1226035,0.0003750416],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9346184,0.0002325396,0.0203092,0.001774869,0.0007663849,0.0001322019,0.00000839493,0.0001296421,0.04202842],"genre_scores_gemma":[0.9903486,0.000006824092,0.003317252,0.0004088325,0.00004835291,0.000005254863,0.000003275153,0.000003791314,0.005857815],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8353377,"threshold_uncertainty_score":0.9996631,"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."}}