{"id":"W3157760823","doi":"10.1016/j.engstruct.2021.112389","title":"Failure mode identification of column base plate connection using data-driven machine learning techniques","year":2021,"lang":"en","type":"article","venue":"Engineering Structures","topic":"Structural Load-Bearing Analysis","field":"Engineering","cited_by":53,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"Canadian Institute of Steel Construction","keywords":"Connection (principal bundle); Failure mode and effects analysis; Naive Bayes classifier; Decision tree; Identification (biology); Mode (computer interface); AdaBoost; Support vector machine; Artificial intelligence; Column (typography); Computer science; Structural engineering; Base (topology); Embedment; Random forest; Engineering; Pattern recognition (psychology); Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001053083,0.0002310972,0.000313771,0.0002191294,0.00007941866,0.00007650836,0.0002712607,0.0001326852,0.0000638129],"category_scores_gemma":[0.0002108307,0.0002610387,0.00007633891,0.0004525891,0.00002178203,0.0002611842,0.0001070714,0.0003670595,0.000001442505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009722695,"about_ca_system_score_gemma":0.00001955551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001675548,"about_ca_topic_score_gemma":0.00002814236,"domain_scores_codex":[0.9987655,0.00003014547,0.0004152149,0.000331441,0.000226333,0.0002313354],"domain_scores_gemma":[0.9991017,0.00005853565,0.00009493159,0.0005898828,0.00009570124,0.00005924098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001409972,0.000001176408,0.000135412,0.0000829154,0.00008523206,0.000005093993,0.00005039185,0.5241704,0.4750556,0.00009879135,0.00002043675,0.0002931184],"study_design_scores_gemma":[0.00006222967,0.000003874613,0.0007978,0.00002838548,0.000061208,0.0000302019,0.00002401481,0.5435655,0.4550182,0.00005292918,0.0002069943,0.0001487203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8732206,0.0005807934,0.1244417,0.00002112077,0.0004073863,0.000123148,0.0001677247,0.00100909,0.00002848252],"genre_scores_gemma":[0.9412181,0.00003441976,0.05815266,0.000003649026,0.0001217723,0.000004114447,0.0003777925,0.00006298272,0.00002446993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0679976,"threshold_uncertainty_score":0.9999842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0123450273631707,"score_gpt":0.2406977867225163,"score_spread":0.2283527593593457,"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."}}