{"id":"W4403447509","doi":"10.1109/vl/hcc60511.2024.00024","title":"Supporting User Critiques of AI Systems via Training Dataset Explanations: Investigating Critique Properties and the Impact of Presentation Style","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Style (visual arts); Presentation (obstetrics); Computer science; Training (meteorology); Artificial intelligence; Natural language processing; Human–computer interaction; Information retrieval; History","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":[0.001353369,0.000111446,0.0002008689,0.0001366753,0.0001065341,0.0003950573,0.0003490293,0.00003769873,0.00001076079],"category_scores_gemma":[0.0006021782,0.00006907084,0.00004839477,0.0003365062,0.0002413312,0.001861031,0.0001325696,0.0001291128,0.000002003468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002492442,"about_ca_system_score_gemma":0.0001680892,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007779019,"about_ca_topic_score_gemma":0.0001010106,"domain_scores_codex":[0.9984888,0.0002537892,0.0005783028,0.0002428234,0.0002322362,0.0002040426],"domain_scores_gemma":[0.9988106,0.0005250623,0.0001244254,0.000283267,0.0002070447,0.00004963515],"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":[0.0000235654,0.00006151829,0.001507471,0.001226417,0.0001878513,0.00002030836,0.1097992,0.007245868,0.0654766,0.7979205,0.008443167,0.008087576],"study_design_scores_gemma":[0.00007511371,0.00008390369,0.00008824711,0.0003528329,0.0000120358,0.00003116889,0.01169852,0.8942344,0.08237569,0.01088844,0.00004878358,0.000110911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2551812,0.001776932,0.7386095,0.002456978,0.000177547,0.0008797465,0.0001335346,0.0002046937,0.0005799037],"genre_scores_gemma":[0.9963818,0.00002233744,0.003346769,0.00008436558,0.0000324858,0.00003871187,0.00003164517,0.000008810139,0.00005313168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8869885,"threshold_uncertainty_score":0.9988283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09466484882499099,"score_gpt":0.3889581525787565,"score_spread":0.2942933037537655,"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."}}