{"id":"W4318187137","doi":"10.1109/bigdata55660.2022.10020293","title":"Entity Matching with AUC-Based Fairness","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Matching (statistics); 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":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.006350874,0.0002867569,0.0003435746,0.0005316997,0.0005833614,0.001351768,0.01682367,0.00004258657,0.006070213],"category_scores_gemma":[0.0008768787,0.0002424697,0.00005007774,0.0007240304,0.000174298,0.001740458,0.0084126,0.0005727002,0.0007007702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000151647,"about_ca_system_score_gemma":0.0005706901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00118039,"about_ca_topic_score_gemma":0.003087913,"domain_scores_codex":[0.9911465,0.0006054767,0.0007664596,0.001907813,0.005200207,0.0003735556],"domain_scores_gemma":[0.9922483,0.0006265891,0.000530135,0.0061527,0.0002854757,0.0001568198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007920436,0.00102725,0.001314471,0.00002488884,0.0002543556,0.0002565026,0.000217452,0.001640319,0.0003933101,0.09533767,0.5560572,0.3426845],"study_design_scores_gemma":[0.001159996,0.0001769364,0.001318211,0.00004421529,0.00003428354,0.00001526433,0.002329668,0.03620015,0.00009883745,0.01239902,0.9457222,0.0005011918],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03767144,0.00005120442,0.58079,0.02968436,0.02680365,0.001251427,0.2732681,0.0003333516,0.05014645],"genre_scores_gemma":[0.9421769,0.00002733572,0.0008851946,0.003000821,0.0005505584,0.00007188579,0.04975439,0.00002443166,0.003508525],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9045054,"threshold_uncertainty_score":0.9996849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6664563814827509,"score_gpt":0.4557380255016488,"score_spread":0.2107183559811021,"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."}}