{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001280346,0.0003970717,0.0003657512,0.000554087,0.001758424,0.001020814,0.001485894,0.0002452922,0.0009506011],"category_scores_gemma":[0.0004244613,0.00045338,0.0002277816,0.002911771,0.0001656808,0.001025501,0.0005844688,0.0002402479,0.0006910604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009268608,"about_ca_system_score_gemma":0.001821475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005455452,"about_ca_topic_score_gemma":0.002119891,"domain_scores_codex":[0.9951943,0.0006964542,0.0009216417,0.001082829,0.001220718,0.0008840843],"domain_scores_gemma":[0.997184,0.0002694509,0.000249992,0.0008190113,0.001338876,0.0001387164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001503728,0.0007977358,0.0003676774,0.00009790206,0.0002614318,0.00001629276,0.05912764,0.0009238102,0.0003897748,0.7594786,0.0645569,0.1139671],"study_design_scores_gemma":[0.0003662453,0.0001007189,0.0008922095,0.00005662723,0.0001975651,0.000002381499,0.01425086,0.9023454,0.0238126,0.04822152,0.009179698,0.0005741649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03009675,0.0007404178,0.60498,0.05182305,0.006493181,0.002782134,0.0000194431,0.0008282122,0.3022369],"genre_scores_gemma":[0.9791035,0.00004161205,0.01034813,0.002080299,0.0003110919,0.0002134228,0.00001142236,0.00001914386,0.007871354],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9490068,"threshold_uncertainty_score":0.9999627,"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."}}