{"id":"W4312349853","doi":"10.1145/3524610.3527902","title":"XAI4FL","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Statement (logic); Computer science; Fault (geology); Ranking (information retrieval); Test (biology); Unit testing; Class (philosophy); Software bug; Problem statement; Test case; Software; Programming language; Artificial intelligence; Machine learning; Engineering","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":[0.002317751,0.002069814,0.0007385426,0.002352968,0.001112132,0.002977694,0.004238141,0.001731535,0.192518],"category_scores_gemma":[0.004134164,0.001196589,0.001082891,0.001347396,0.0006342772,0.003561389,0.002585119,0.002238097,0.1061802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201842,"about_ca_system_score_gemma":0.001276185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003336783,"about_ca_topic_score_gemma":0.004502266,"domain_scores_codex":[0.9986738,0.0002063858,0.00009274121,0.0003408547,0.000494822,0.0001914673],"domain_scores_gemma":[0.9978346,0.0004374335,0.000128623,0.0009033604,0.0005745197,0.0001214693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001023416,0.0001544328,0.00217407,0.001142354,0.0001114353,0.000240647,0.0002175676,0.0026207,0.009976429,0.02626067,0.6835879,0.2724904],"study_design_scores_gemma":[0.0002046282,0.0001664958,0.001448464,0.0001510782,0.00004780053,0.0003447663,0.00005025128,0.01667717,0.01844445,0.009812018,0.9525693,0.00008352611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.006203729,0.001401744,0.2103538,0.001325862,0.0008733338,0.0004766324,0.02910925,0.5944045,0.1558513],"genre_scores_gemma":[0.09528849,0.00218257,0.2956871,0.002439212,0.000495248,0.001412747,0.1688887,0.0969927,0.3366133],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.192518,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01376427841441761,"score_gpt":0.2255037897309113,"score_spread":0.2117395113164937,"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."}}