{"id":"W4386246855","doi":"10.1145/3600211.3604692","title":"Human Uncertainty in Concept-Based AI Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Cambridge Trust; Engineering and Physical Sciences Research Council; Leverhulme Trust; Mozilla Foundation; Gates Cambridge Trust; DeepMind","keywords":"Computer science; Context (archaeology); Task (project management); Artificial intelligence; Multidisciplinary approach; Human-in-the-loop; Data science; Machine learning; MNIST database; Risk analysis (engineering); Psychological intervention; Human–computer interaction; Deep learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003506788,0.00008878377,0.0001253364,0.0002091764,0.00004574893,0.0001557761,0.0009916838,0.00004662584,0.00001412221],"category_scores_gemma":[0.00002824673,0.00007909657,0.00002305098,0.0007637322,0.00003771614,0.0002299696,0.0002386241,0.00009133291,0.0001216827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005369133,"about_ca_system_score_gemma":0.0000514474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001245416,"about_ca_topic_score_gemma":0.00009133137,"domain_scores_codex":[0.9990228,0.00006201679,0.0001859787,0.000301034,0.000186038,0.0002421471],"domain_scores_gemma":[0.9991469,0.00006348438,0.000035199,0.0006792978,0.00003054605,0.00004462384],"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":[0.000001573239,0.00007121312,0.003295316,0.00003384324,0.000007614655,0.0001617776,0.0004657408,0.007233418,0.001060833,0.6041571,0.3737067,0.009804875],"study_design_scores_gemma":[0.0005716287,0.000177477,0.005178045,0.0001384989,0.000001845896,0.000004228245,0.0001122013,0.9680529,0.003263035,0.004502243,0.01758886,0.0004090718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08414108,0.00005842027,0.8548561,0.006178451,0.001085455,0.001154585,0.00006349117,0.01640707,0.03605529],"genre_scores_gemma":[0.9919683,3.993194e-7,0.006729852,0.0004395644,0.00002066851,0.00004828882,0.00002929531,0.000006894429,0.0007567552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9608194,"threshold_uncertainty_score":0.3225465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03164293836165757,"score_gpt":0.3132556931745893,"score_spread":0.2816127548129317,"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."}}