{"id":"W4401047029","doi":"10.1016/j.jss.2024.112159","title":"EvaluateXAI: A framework to evaluate the reliability and consistency of rule-based XAI techniques for software analytics tasks","year":2024,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Consistency (knowledge bases); Computer science; Analytics; Reliability (semiconductor); Data mining; Software; Reliability engineering; Artificial intelligence; Engineering; Programming language","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":[0.02852772,0.002607464,0.001819243,0.007389131,0.001069722,0.004602469,0.005949168,0.00232836,0.001940264],"category_scores_gemma":[0.08272753,0.001053457,0.00192064,0.003071456,0.001455995,0.005206534,0.003590679,0.0029906,0.000870175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001380378,"about_ca_system_score_gemma":0.003413863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005441378,"about_ca_topic_score_gemma":0.004867177,"domain_scores_codex":[0.9748512,0.007446037,0.002408729,0.002324344,0.01207646,0.0008932458],"domain_scores_gemma":[0.9344715,0.03509163,0.007561355,0.01096515,0.01091453,0.0009958097],"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":[0.003642647,0.00166095,0.08367467,0.002223298,0.002452652,0.000338701,0.0008550838,0.2218179,0.02789341,0.01828221,0.01090874,0.6262497],"study_design_scores_gemma":[0.0002385345,0.001262545,0.01120659,0.0001925792,0.0002691696,0.0002216189,0.000181615,0.9501271,0.01991861,0.01284133,0.003412476,0.0001277014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09570283,0.002434238,0.8631392,0.0003581855,0.0002285949,0.001088608,0.002180319,0.03180124,0.003066797],"genre_scores_gemma":[0.3140871,0.0003973339,0.6803622,0.0001302992,0.00008630934,0.0007898395,0.002284567,0.001020573,0.0008417972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02852772,"threshold_uncertainty_score":0.1508708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03221025691242322,"score_gpt":0.3260664120274342,"score_spread":0.293856155115011,"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."}}