{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001903164,0.00004389588,0.00007342255,0.00005690508,0.00001682888,0.00001316793,0.00005293302,0.00005133513,0.08199723],"category_scores_gemma":[0.00003244266,0.00004236073,0.00003348399,0.00009235746,0.00000578462,0.0000376407,0.0000121191,0.00009714547,0.02126139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002750614,"about_ca_system_score_gemma":0.000009968185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003276299,"about_ca_topic_score_gemma":0.0001317272,"domain_scores_codex":[0.9994313,0.0000693511,0.0001442152,0.0001337879,0.00009060245,0.0001307738],"domain_scores_gemma":[0.9997632,0.00005737767,0.00003017257,0.0001098879,0.00001712687,0.00002221548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005234742,0.001099498,0.3415831,0.00001271811,0.0001052865,0.0000390712,0.07610035,0.0002983178,0.009154747,0.1843683,0.05419746,0.3325177],"study_design_scores_gemma":[0.001969107,0.0003594608,0.9283572,0.00002732945,0.00001210746,0.000007878069,0.04121937,0.003645152,0.0006320551,0.005130001,0.01824034,0.0003999816],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6731778,0.000004360426,0.00002262434,0.0001840489,0.001641212,0.0000900645,2.545586e-7,0.00002421869,0.3248554],"genre_scores_gemma":[0.9667534,2.182448e-7,0.00009270112,0.0009635,0.0001038481,0.00001088245,0.000001953188,0.000006566787,0.03206688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5867741,"threshold_uncertainty_score":0.9795007,"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."}}