{"id":"W4416184308","doi":"10.1109/acsos-c66519.2025.00041","title":"Self-Evaluation can Help Agents Meet Social Expectations","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reflection (computer programming); Test (biology); Surprise; Product (mathematics); Architecture; Sociotechnical system","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":[0.00697008,0.001204427,0.0005105751,0.0005876967,0.0007229081,0.002792837,0.001556323,0.001597863,0.00372473],"category_scores_gemma":[0.03241968,0.0004321093,0.0005852222,0.0002461352,0.001388163,0.004239225,0.003060872,0.001552044,0.001337683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000980273,"about_ca_system_score_gemma":0.001595228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00175407,"about_ca_topic_score_gemma":0.002175079,"domain_scores_codex":[0.9951225,0.002793967,0.0002255897,0.0006805448,0.000956253,0.0002210799],"domain_scores_gemma":[0.9850706,0.007779544,0.001617028,0.002856043,0.001885155,0.00079172],"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":[0.001412093,0.002486811,0.05874959,0.001105275,0.00042514,0.001113133,0.02703799,0.1511435,0.08352485,0.09049048,0.02026473,0.5622464],"study_design_scores_gemma":[0.000261952,0.001388803,0.01109171,0.0002634401,0.0002751852,0.0003618855,0.004203733,0.7258248,0.0580416,0.1414649,0.05654519,0.0002767263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3054643,0.0002307356,0.6448739,0.003777978,0.0001490966,0.0008665415,0.0001314663,0.01424419,0.03026182],"genre_scores_gemma":[0.8807329,0.00009714955,0.1132427,0.0004390329,0.00002923774,0.0002938953,0.0002061563,0.000508091,0.004451049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00697008,"threshold_uncertainty_score":0.03686172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06218617163229865,"score_gpt":0.3551089753159624,"score_spread":0.2929228036836637,"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."}}