{"id":"W4408546962","doi":"10.1177/15553434251327697","title":"Designing High-Impact Experiments for Human–Autonomy / AI Teaming","year":2025,"lang":"en","type":"article","venue":"Journal of Cognitive Engineering and Decision Making","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Division of Information and Intelligent Systems","keywords":"Autonomy; Computer science; Psychology; Human–computer interaction; Engineering; Political science","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":[0.0004820034,0.0001415439,0.000273423,0.0005717848,0.0001545399,0.0001047349,0.00008256792,0.00007477246,0.0002829338],"category_scores_gemma":[0.0004415764,0.0001245639,0.0001410681,0.0001291261,0.00001441542,0.0002058255,0.00002474664,0.0002422299,0.000006135233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009851583,"about_ca_system_score_gemma":0.00004367212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001803625,"about_ca_topic_score_gemma":1.716102e-7,"domain_scores_codex":[0.9989687,0.00003317197,0.000543205,0.0001422201,0.000138527,0.0001742413],"domain_scores_gemma":[0.9978954,0.001430742,0.0002364411,0.00006985163,0.0003078162,0.0000597241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002660186,0.0005224227,0.006249211,0.0001226951,0.002246626,0.0001497422,0.01253706,0.01599054,0.02217485,0.02905491,0.009481137,0.8988106],"study_design_scores_gemma":[0.05239595,0.00527067,0.6181753,0.04088153,0.00147904,0.001653644,0.0279012,0.1208588,0.02684744,0.05141802,0.04940544,0.003712886],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3139336,0.000291598,0.6837773,0.00002176062,0.000871196,0.0000965295,0.000002936511,0.00002373741,0.0009813887],"genre_scores_gemma":[0.9877867,0.000002951355,0.01160404,0.0001893223,0.0001721451,0.00001338663,0.000001373423,0.00001607098,0.0002140745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8950977,"threshold_uncertainty_score":0.5079568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02800911645837078,"score_gpt":0.430526081579753,"score_spread":0.4025169651213822,"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."}}