{"id":"W4399040267","doi":"10.1109/tts.2024.3378587","title":"Failures in the Loop: Human Leadership in AI-Based Decision-Making","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Technology and Society","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Concordia University","funders":"","keywords":"Human-in-the-loop; Computer science; Loop (graph theory); Psychology; Artificial intelligence; Mathematics","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":[0.0003560447,0.0001286943,0.0001173349,0.000490052,0.0002418823,0.0001795632,0.0002741909,0.0002553413,0.000084126],"category_scores_gemma":[0.00001039054,0.00009658543,0.00007303014,0.001691683,0.0002399901,0.0004076369,0.00000342095,0.0006655991,0.00004462282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002297847,"about_ca_system_score_gemma":0.00001596024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006849648,"about_ca_topic_score_gemma":0.0006537435,"domain_scores_codex":[0.9991937,0.000007920953,0.0001768926,0.0002769435,0.0001204498,0.0002240506],"domain_scores_gemma":[0.9996084,0.0001382369,0.00002297086,0.0002048348,0.00002266683,0.00000288877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001052619,0.0009320173,0.006033943,0.001527701,0.0001074094,0.000181039,0.001467955,0.004546139,0.001746018,0.1552832,0.01048476,0.8175846],"study_design_scores_gemma":[0.004016177,0.000254872,0.01794605,0.01124876,0.000531906,0.00009979006,0.05761373,0.2948439,0.009124976,0.4417452,0.1589743,0.003600307],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3452993,0.001014458,0.6134056,0.03776411,0.0007557036,0.0004848751,0.00001140358,0.0006301308,0.0006343495],"genre_scores_gemma":[0.9964244,0.0000275498,0.0001928556,0.003216929,0.00004883372,0.00004220602,0.00000254912,0.00001104396,0.00003366742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8139843,"threshold_uncertainty_score":0.3938639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07983931117408588,"score_gpt":0.3118630771869079,"score_spread":0.232023766012822,"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."}}