{"id":"W4415682779","doi":"10.18280/mmep.120905","title":"XGRL-TCP: An Explainable Graph-Based Reinforcement Learning Framework for Test Case Prioritization in CI","year":2025,"lang":"","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Prioritization; Reinforcement learning; Key (lock); Action (physics); Matching (statistics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001723035,0.001250626,0.0007640302,0.001097956,0.000394958,0.001016998,0.002787476,0.001271401,0.003777313],"category_scores_gemma":[0.01016296,0.0006284464,0.0009261876,0.0007096836,0.001204117,0.001541252,0.00160437,0.002513034,0.000429338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001992554,"about_ca_system_score_gemma":0.002359332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0131103,"about_ca_topic_score_gemma":0.01568483,"domain_scores_codex":[0.9989537,0.0004009767,0.00004807883,0.0002607023,0.0002292595,0.0001072857],"domain_scores_gemma":[0.9956434,0.003056107,0.0003633374,0.0003357258,0.0004343717,0.0001670836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005790978,0.00005792812,0.001325005,0.00009699432,0.0000458285,0.00007969167,0.00009882807,0.926915,0.001009417,0.01033342,0.001732202,0.05824776],"study_design_scores_gemma":[0.000007251664,0.00001306535,0.00007576952,0.000005819896,0.000005438362,0.000006550371,0.000004716818,0.9927003,0.0002228384,0.006634006,0.0003210081,0.000003345056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01367525,0.0002190068,0.9807265,0.0004441598,0.00003522069,0.0001011321,0.0002116081,0.00312573,0.001461371],"genre_scores_gemma":[0.6705521,0.000243939,0.3240586,0.0004481853,0.00007100274,0.0004558312,0.0007544818,0.0005613665,0.002854489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0131103,"threshold_uncertainty_score":0.02606797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03517078771299631,"score_gpt":0.2717951182795331,"score_spread":0.2366243305665368,"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."}}