{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01171434,0.001180054,0.001132796,0.001254874,0.001254319,0.003173108,0.002670688,0.002361117,0.002215126],"category_scores_gemma":[0.06479169,0.000844741,0.0008552032,0.001284394,0.003924725,0.00592391,0.003785196,0.003212702,0.0003837609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002781224,"about_ca_system_score_gemma":0.002259567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007731144,"about_ca_topic_score_gemma":0.006009668,"domain_scores_codex":[0.9888609,0.005967024,0.0005549368,0.00219149,0.001998422,0.0004271306],"domain_scores_gemma":[0.9285836,0.05748592,0.004555257,0.005564075,0.002601438,0.001209687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008943295,0.0002729114,0.009981358,0.0007359802,0.0001591892,0.0002436151,0.002163942,0.8095788,0.002809535,0.06501461,0.003907826,0.1042379],"study_design_scores_gemma":[0.00005009527,0.00016924,0.001555614,0.00007179622,0.00002860539,0.0001125308,0.0002690214,0.8843697,0.002175445,0.1053364,0.005806459,0.00005504629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.132628,0.002530415,0.8554245,0.002742345,0.0001323329,0.000302955,0.001149447,0.0008921848,0.004197806],"genre_scores_gemma":[0.8757686,0.0007417546,0.1207309,0.000374975,0.0001032833,0.0002857778,0.0009751305,0.0000892677,0.0009303038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01171434,"threshold_uncertainty_score":0.06195211,"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."}}