{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001618713,0.00002772,0.00002920044,0.00003783255,0.0001505341,0.00002876657,0.0005227518,0.000004097848,0.0001013639],"category_scores_gemma":[0.00002967942,0.00002602447,0.00001543688,0.000194692,0.000004930442,0.00005704442,0.0004922024,0.00005832075,0.0000187119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001661122,"about_ca_system_score_gemma":0.00001712651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003265839,"about_ca_topic_score_gemma":1.789345e-7,"domain_scores_codex":[0.9996155,0.00002234804,0.00004318552,0.0001138647,0.0001236824,0.00008142441],"domain_scores_gemma":[0.9996245,0.00005943066,0.00001212635,0.0002762045,0.000008787567,0.00001897855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[6.244352e-7,0.0000444313,0.003145774,0.000001304603,0.000002364921,0.00002382652,0.0002320324,0.00005372316,0.00004980924,0.2133031,0.6743675,0.1087755],"study_design_scores_gemma":[0.0001461014,0.0002357407,0.001925741,0.000002205933,0.000001317467,0.0002008315,0.000009229734,0.09937059,0.00094579,0.6928463,0.2040278,0.0002883261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001064419,0.0000264549,0.9461335,0.001104478,0.000168376,0.0000320746,2.441715e-7,0.02467075,0.02679972],"genre_scores_gemma":[0.6223862,2.043958e-7,0.3749448,0.001365742,0.000009683316,0.00002376175,2.894765e-7,0.000002306524,0.001266974],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6213218,"threshold_uncertainty_score":0.1157802,"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."}}