{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003852081,0.001227076,0.0008701957,0.003343266,0.0007684335,0.001964685,0.00254395,0.002261728,0.004379044],"category_scores_gemma":[0.0419008,0.0005108441,0.001279252,0.002357248,0.001210413,0.005625619,0.002724182,0.002950134,0.0006127456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001933155,"about_ca_system_score_gemma":0.001430659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003759314,"about_ca_topic_score_gemma":0.006575964,"domain_scores_codex":[0.9961817,0.001514828,0.0003202721,0.0007872448,0.001020352,0.0001756004],"domain_scores_gemma":[0.9759281,0.01749224,0.001909824,0.002466086,0.001835502,0.0003681565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005220195,0.0002442357,0.01563696,0.0007814436,0.0002766215,0.0007241177,0.001241034,0.4515211,0.002413791,0.1934994,0.0181459,0.3149934],"study_design_scores_gemma":[0.00003331454,0.00003026573,0.0006928513,0.00005211551,0.0000397038,0.00009830338,0.00009103324,0.8732877,0.00101802,0.1218195,0.002818647,0.00001858113],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03685259,0.001070139,0.9536837,0.002725499,0.00008990629,0.0001289028,0.001580708,0.002404916,0.001463533],"genre_scores_gemma":[0.6712423,0.0006730957,0.3209539,0.0005646163,0.0002083756,0.0002197986,0.004446743,0.000172535,0.001518681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004379044,"threshold_uncertainty_score":0.02037203,"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."}}