{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03760301,0.001093139,0.0006499967,0.001571598,0.001445656,0.005143321,0.001208988,0.002019484,0.003117012],"category_scores_gemma":[0.2751772,0.0004737243,0.0006213171,0.0006847496,0.001852765,0.005243035,0.003134225,0.002153182,0.0006961978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001381422,"about_ca_system_score_gemma":0.001062694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006657245,"about_ca_topic_score_gemma":0.0009402391,"domain_scores_codex":[0.9563397,0.0360001,0.001767903,0.001361807,0.003747562,0.0007829971],"domain_scores_gemma":[0.5015517,0.4417173,0.02146389,0.01904491,0.01382393,0.002398212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001795701,0.0007632751,0.1409429,0.002431976,0.0002243069,0.001580285,0.6408949,0.002908173,0.0367374,0.005788147,0.005527665,0.1604052],"study_design_scores_gemma":[0.001061868,0.007658784,0.2265093,0.004393965,0.0007872881,0.004464714,0.4516543,0.09071012,0.05163459,0.03862967,0.1211776,0.001317848],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9649125,0.0003048581,0.02787484,0.001259414,0.00006200153,0.0003018238,0.0001471585,0.0005180276,0.004619299],"genre_scores_gemma":[0.9802422,0.0001334989,0.01749757,0.0003496016,0.00004468281,0.0002657569,0.0001274022,0.000146252,0.001193129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03760301,"threshold_uncertainty_score":0.1988661,"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."}}