{"id":"W4415230017","doi":"10.1609/aies.v8i2.36631","title":"Towards Interactive Evaluations for Interaction Harms in Human-AI Systems","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute on Governance","funders":"","keywords":"Construct (python library); Corporate governance; Cognition; Natural (archaeology); Work (physics); Social relation","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":[0.002143108,0.0001559985,0.0002422743,0.00008290313,0.0004667483,0.0003608371,0.001041342,0.0002104505,0.000003196723],"category_scores_gemma":[0.002245793,0.0001236477,0.0001289445,0.0003612081,0.0001411135,0.0005810451,0.0006612548,0.001618687,5.252459e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001440678,"about_ca_system_score_gemma":0.000268811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001610951,"about_ca_topic_score_gemma":0.000007859472,"domain_scores_codex":[0.9987078,0.00005899355,0.0003267931,0.0003828332,0.0003325891,0.0001910311],"domain_scores_gemma":[0.997817,0.0005695825,0.000279505,0.0002267546,0.001075198,0.00003192483],"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":[0.00002120339,0.00005677268,0.0009274777,0.0002721125,0.00005468254,4.299685e-8,0.01790569,0.0007836305,0.003103814,0.9731326,0.001241037,0.002500995],"study_design_scores_gemma":[0.001089446,0.0001385193,0.003321012,0.001338794,0.00004160022,0.000001766327,0.006892931,0.8249267,0.00315265,0.1580661,0.0007910236,0.0002394439],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.18269,0.0001506842,0.5994371,0.1892761,0.003934054,0.0031394,0.00002062409,0.0002551962,0.02109699],"genre_scores_gemma":[0.9938017,0.00004886639,0.004242477,0.001371183,0.00004219129,0.00008745436,0.000001231691,0.000007365389,0.0003975697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8241431,"threshold_uncertainty_score":0.7032478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08023321290939993,"score_gpt":0.4229158206196218,"score_spread":0.3426826077102219,"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."}}