{"id":"W2951006205","doi":"10.1016/j.eswa.2019.06.030","title":"A knowledge-based expert system to assess power plant project cost overrun risks","year":2019,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":79,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"Queensland University of Technology","keywords":"Computer science; Cost overrun; Unavailability; Bayesian network; Probabilistic logic; Risk analysis (engineering); Fuzzy logic; Expert system; Domain (mathematical analysis); Artificial intelligence; Reliability engineering; Engineering; Construction engineering; Construction industry","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":[],"category_scores_codex":[0.001667134,0.0003705912,0.0008092466,0.0006510493,0.0004325626,0.0005331107,0.001322601,0.0001699707,0.0001195508],"category_scores_gemma":[0.0001114552,0.0002394559,0.000217007,0.002562196,0.00006595112,0.0002501924,0.000111349,0.0001762179,0.00513283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003197783,"about_ca_system_score_gemma":0.0004627833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001505384,"about_ca_topic_score_gemma":0.0002295426,"domain_scores_codex":[0.995243,0.0004178686,0.001060171,0.001205203,0.001566075,0.0005076934],"domain_scores_gemma":[0.9950046,0.001085254,0.0004410953,0.00239087,0.000731749,0.0003464367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001797125,0.003365037,0.06881349,0.0004363676,0.001292995,0.00007768691,0.0349522,0.04100387,0.01087523,0.130465,0.6699743,0.03694665],"study_design_scores_gemma":[0.0006771011,0.0001322933,0.0009637897,0.0002038252,0.00001903393,0.00003271073,0.01442306,0.01935917,0.0002455574,0.00001168133,0.9634476,0.0004841653],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01700802,0.003528089,0.8682775,0.001683575,0.001195706,0.0131465,0.0004626688,0.0007107049,0.0939872],"genre_scores_gemma":[0.9852998,0.00001549054,0.002448056,0.0002150223,0.0002514468,0.007884659,0.00004778719,0.00004937534,0.003788387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9682918,"threshold_uncertainty_score":0.9956418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1467612197468109,"score_gpt":0.41744998424194,"score_spread":0.270688764495129,"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."}}