{"id":"W4308718476","doi":"10.3390/make4040047","title":"Actionable Explainable AI (AxAI): A Practical Example with Aggregation Functions for Adaptive Classification and Textual Explanations for Interpretable Machine Learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Kultúrna a Edukacná Grantová Agentúra MŠVVaŠ SR; Ministerstvo školstva, vedy, výskumu a športu Slovenskej republiky; Austrian Science Fund","keywords":"Class (philosophy); Range (aeronautics); Domain (mathematical analysis); Function (biology); Space (punctuation); Artificial intelligence; Computer science; Binary classification; Mathematics; Machine learning; Support vector machine","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":[0.003183546,0.001060319,0.0004962443,0.001048784,0.0008915773,0.002097314,0.001751857,0.002452341,0.007675134],"category_scores_gemma":[0.01202079,0.0003004149,0.001470785,0.001058137,0.00282321,0.003541295,0.002432167,0.003267289,0.001365349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001129666,"about_ca_system_score_gemma":0.0008442562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002075995,"about_ca_topic_score_gemma":0.002586369,"domain_scores_codex":[0.9980003,0.001037678,0.000117482,0.0003439569,0.0004078947,0.00009266489],"domain_scores_gemma":[0.995077,0.003501249,0.0002273216,0.000634141,0.0004573587,0.0001029796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001599046,0.00009369303,0.001086091,0.000363754,0.00005562575,0.0007224128,0.001889327,0.02890288,0.005368422,0.8119368,0.01022907,0.139192],"study_design_scores_gemma":[0.00003317964,0.0000651009,0.000450128,0.00008358977,0.0000385752,0.0004635635,0.0002649835,0.2925049,0.003667119,0.6616231,0.04076117,0.00004479024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003527199,0.0002603848,0.9880344,0.002073708,0.0000842161,0.00006101685,0.0001146638,0.0009671768,0.004877221],"genre_scores_gemma":[0.1399962,0.0002891931,0.8530967,0.0005020984,0.0001294298,0.0002290725,0.0002182103,0.0002979138,0.005241145],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007675134,"threshold_uncertainty_score":0.02567589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04673742173121412,"score_gpt":0.3243509899479155,"score_spread":0.2776135682167014,"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."}}