{"id":"W4205723429","doi":"10.1109/bigdata52589.2021.9671458","title":"Addressing Stability in Classifier Explanations","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Shapley value; Computer science; Classifier (UML); Artificial neural network; Artificial intelligence; Machine learning; Stability (learning theory); Monte Carlo method; Algorithm; Mathematics; Mathematical economics; Game theory; Statistics","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001155885,0.0002762988,0.0002920851,0.0003063022,0.0001838916,0.001131625,0.007809117,0.0001332961,0.0007786925],"category_scores_gemma":[0.001516839,0.0002971909,0.00004245915,0.0008246637,0.0001410442,0.00300679,0.003362519,0.0005382115,0.0005425921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002149723,"about_ca_system_score_gemma":0.001149328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004262499,"about_ca_topic_score_gemma":0.007966057,"domain_scores_codex":[0.9956253,0.0003136418,0.0007055759,0.001806157,0.001067586,0.00048179],"domain_scores_gemma":[0.993264,0.0004169015,0.0002125944,0.005259846,0.0006764132,0.000170257],"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":[0.00006369509,0.001141466,0.002230208,0.00003789562,0.0001236337,0.0008470308,0.0007800292,0.0001792833,0.0172344,0.2187131,0.02798916,0.7306601],"study_design_scores_gemma":[0.0008656759,0.00008719392,0.003538385,0.0006302566,0.00002570233,0.0000781499,0.002186886,0.7704624,0.06048981,0.02222227,0.1381268,0.001286513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02251303,0.0001867976,0.8600842,0.0267735,0.01822612,0.0005577552,0.009804083,0.0002263294,0.06162813],"genre_scores_gemma":[0.9815423,0.0002927878,0.007646638,0.0008462718,0.0009109803,0.00003319663,0.008074423,0.00002031826,0.0006330284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9590293,"threshold_uncertainty_score":0.999948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7275100894644405,"score_gpt":0.4292445498229833,"score_spread":0.2982655396414572,"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."}}