{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05627751,0.001170944,0.0008826013,0.001044485,0.003308054,0.003326053,0.002425492,0.002326988,0.009184942],"category_scores_gemma":[0.1405532,0.001095527,0.001098965,0.0009030828,0.004041652,0.004245327,0.003764478,0.003147738,0.001346294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002925268,"about_ca_system_score_gemma":0.003819906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007413324,"about_ca_topic_score_gemma":0.001088418,"domain_scores_codex":[0.95732,0.03274638,0.002589078,0.002035425,0.00376697,0.00154212],"domain_scores_gemma":[0.8234975,0.1379332,0.01094054,0.01321757,0.0104133,0.003997813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.03422135,0.1033606,0.07471352,0.01353107,0.002146565,0.001096022,0.04044326,0.05722174,0.09527619,0.174305,0.01620555,0.3874792],"study_design_scores_gemma":[0.0220689,0.1662101,0.1017719,0.003750765,0.00206859,0.0005621859,0.02056017,0.06965078,0.1193273,0.3531804,0.139911,0.0009379873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.579737,0.0006179256,0.2776049,0.003045118,0.001116781,0.09237967,0.0007820286,0.0007392985,0.04397737],"genre_scores_gemma":[0.5406812,0.0005031272,0.3411174,0.001557488,0.0002385559,0.1120869,0.00042095,0.000155668,0.003238611],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.05627751,"threshold_uncertainty_score":0.2976274,"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."}}