{"id":"W4289533864","doi":"10.1109/icde53745.2022.00248","title":"Effective Explanations for Entity Resolution Models","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Science for Equity, Empowerment and Development Division","keywords":"Computer science; Counterfactual thinking; Trustworthiness; Probabilistic logic; Classifier (UML); Artificial intelligence; Machine learning; Task (project management); Resolution (logic); Matching (statistics); 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003361032,0.000166178,0.0001993,0.0004955466,0.0002856455,0.0003485628,0.003179132,0.00003400874,0.001674807],"category_scores_gemma":[0.001322653,0.000169744,0.00007779745,0.0003762704,0.00002772827,0.001129453,0.001216416,0.0002799124,0.0001068586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002481511,"about_ca_system_score_gemma":0.00006556305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008819513,"about_ca_topic_score_gemma":0.00006949608,"domain_scores_codex":[0.9966371,0.0001438698,0.0004911528,0.0007691151,0.001714819,0.0002439394],"domain_scores_gemma":[0.9975832,0.0007137189,0.0001897267,0.001188899,0.0002429434,0.00008155942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001094523,0.0001682318,0.00001101049,0.00001133843,0.0001074582,0.000007181256,0.000211348,0.2639377,0.0003387573,0.553701,0.1720688,0.009327682],"study_design_scores_gemma":[0.000349674,0.00008438707,0.0001340884,0.00001001881,0.00001226532,0.000002992866,0.0003405451,0.7333299,0.0000500118,0.01374593,0.2517799,0.0001603329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003465981,0.00003128983,0.9616903,0.004021814,0.005367217,0.00093486,0.01827106,0.0001426315,0.006074857],"genre_scores_gemma":[0.9801638,0.00004547387,0.005270287,0.0005760622,0.0003405281,0.0007260607,0.007735271,0.00002911567,0.005113382],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9766979,"threshold_uncertainty_score":0.9992378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4108617194632559,"score_gpt":0.4345066269760401,"score_spread":0.02364490751278414,"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."}}