{"id":"W2579310195","doi":"","title":"Artificial Intelligence Testing","year":2016,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Turing test; Test (biology); Deception; Argument (complex analysis); Subjectivity; Computer science; Artificial intelligence; Turing; Key (lock); Outcome (game theory); Self-deception; Cognitive science; Epistemology; Psychology; Social psychology; Computer security; Mathematics; Philosophy; Mathematical economics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01939884,0.0007144691,0.0008954197,0.002437531,0.001724795,0.005043703,0.002739188,0.002848136,0.01440144],"category_scores_gemma":[0.1041647,0.000297489,0.0008100217,0.001892439,0.006630008,0.006484718,0.00425977,0.002991853,0.004084693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002718931,"about_ca_system_score_gemma":0.003391051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0018773,"about_ca_topic_score_gemma":0.001390122,"domain_scores_codex":[0.9655933,0.01708812,0.001621932,0.00260182,0.01194749,0.001147279],"domain_scores_gemma":[0.9258227,0.04346723,0.003157706,0.01161824,0.01374803,0.002186141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001367212,0.0001777734,0.007965794,0.000282876,0.00006929023,0.0002889371,0.0007624132,0.001741552,0.0006670631,0.7218499,0.04674622,0.2193114],"study_design_scores_gemma":[0.00006682352,0.000312292,0.005158376,0.000600631,0.00003944878,0.0008626754,0.0007174148,0.008229501,0.003937097,0.7109747,0.26903,0.00007100646],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04030113,0.005138338,0.1524162,0.068434,0.002683659,0.0008120341,0.001254615,0.001230313,0.7277296],"genre_scores_gemma":[0.8166773,0.003144763,0.08719481,0.01549117,0.001250946,0.001192419,0.001504885,0.0003899528,0.07315379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9982752,"threshold_uncertainty_score":0.1025921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4743838374723485,"score_gpt":0.5305625539451253,"score_spread":0.05617871647277684,"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."}}