{"id":"W2995544044","doi":"10.1109/acii.2019.8925498","title":"Evaluating Empathy in Artificial Agents","year":2019,"lang":"en","type":"article","venue":"","topic":"Social Robot Interaction and HRI","field":"Psychology","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Empathy; Variety (cybernetics); Computer science; Set (abstract data type); Artificial intelligence; Human–computer interaction; Cognitive science; Psychology; Social psychology","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":[0.01598435,0.0007526783,0.00066993,0.002125175,0.001080417,0.003301329,0.0008183054,0.001419386,0.002949744],"category_scores_gemma":[0.06771994,0.0001853356,0.0004213999,0.001161364,0.002404516,0.003115983,0.003327319,0.0009998326,0.0003608344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002122413,"about_ca_system_score_gemma":0.001087803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001252336,"about_ca_topic_score_gemma":0.001093852,"domain_scores_codex":[0.9748523,0.01933543,0.001101306,0.001085332,0.003177284,0.0004483127],"domain_scores_gemma":[0.961854,0.0266233,0.00433459,0.00198986,0.004026028,0.001172215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001351376,0.0008950218,0.1020815,0.002196493,0.000768847,0.0002396759,0.01065421,0.101251,0.01070973,0.2068445,0.008362012,0.5546456],"study_design_scores_gemma":[0.0001823153,0.003426769,0.1149155,0.00115656,0.0004154726,0.0005107336,0.009936036,0.5290602,0.01775297,0.2913789,0.03092993,0.0003345926],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6095747,0.003419942,0.31142,0.0035745,0.0002805663,0.001052597,0.0004024269,0.0005728597,0.06970236],"genre_scores_gemma":[0.9459698,0.0002997479,0.05169956,0.0001538302,0.00002675614,0.0003034065,0.0001278278,0.00002881821,0.001390304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01598435,"threshold_uncertainty_score":0.08453429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2529697002904707,"score_gpt":0.5274448690374587,"score_spread":0.274475168746988,"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."}}