{"id":"W2797143217","doi":"10.1007/s10462-018-9631-5","title":"Artificial intelligence test: a case study of intelligent vehicles","year":2018,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":148,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Test (biology); Computer science; Artificial intelligence; Artificial intelligence, situated approach; Applications of artificial intelligence; Machine learning","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"],"consensus_categories":[],"category_scores_codex":[0.001636027,0.0004695091,0.0008053209,0.0003616368,0.0003621021,0.0001338507,0.001739495,0.000125431,0.0001872636],"category_scores_gemma":[0.001384256,0.0004357572,0.0002354329,0.002559443,0.0004544202,0.00071069,0.0006678277,0.0004022183,0.0005507336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001128707,"about_ca_system_score_gemma":0.0001302326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004172357,"about_ca_topic_score_gemma":0.0006927207,"domain_scores_codex":[0.9950683,0.0003253722,0.002217606,0.001092065,0.0006731171,0.0006235549],"domain_scores_gemma":[0.9956168,0.0006567271,0.000681017,0.001835532,0.0009719619,0.0002379548],"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":[0.00001321379,0.001045048,0.00003419494,0.0002612754,0.00002606052,0.0005043118,0.001463913,0.00002306606,0.0008440076,0.02401266,0.00006411065,0.9717081],"study_design_scores_gemma":[0.00001956662,0.006693718,0.000009973635,0.002414365,0.0001554558,0.003239481,0.005122187,0.02362416,0.7700476,0.1842271,0.003143736,0.001302693],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01505183,0.004355268,0.9768848,0.0004218786,0.0005416215,0.001888639,0.000005024066,0.000604609,0.0002463569],"genre_scores_gemma":[0.9620049,0.004812337,0.0322549,0.0004342282,0.0002327816,0.0002005425,0.000001000502,0.00003717545,0.00002213085],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9704055,"threshold_uncertainty_score":0.9998094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1165053816690335,"score_gpt":0.3882024655908736,"score_spread":0.2716970839218401,"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."}}