{"id":"W3115146700","doi":"10.1007/s42102-021-00062-1","title":"Comparative Study of Neural Network–Based Models for Fatigue Crack Growth Predictions of Short Cracks","year":2021,"lang":"en","type":"article","venue":"Journal of Peridynamics and Nonlocal Modeling","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extrapolation; Artificial neural network; Structural engineering; Damage tolerance; Nonlinear system; Extreme learning machine; Materials science; Interpolation (computer graphics); Paris' law; Range (aeronautics); Backpropagation; Fracture mechanics; Computer science; Crack closure; Engineering; Machine learning; Artificial intelligence; Mathematics; Composite material; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002868715,0.000162754,0.0005282399,0.0001114771,0.00006681036,0.00002350025,0.0001228569,0.000070574,0.000001202],"category_scores_gemma":[0.00004339778,0.0001577419,0.0001176743,0.0001767979,0.00004696664,0.0002035863,0.00003736295,0.0002775987,8.022246e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005544704,"about_ca_system_score_gemma":0.00006708821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000141099,"about_ca_topic_score_gemma":0.00003491259,"domain_scores_codex":[0.9987143,0.00004214045,0.0007330438,0.0001291171,0.0002099601,0.0001714379],"domain_scores_gemma":[0.9986021,0.0001637182,0.0001558924,0.0001272952,0.0008744545,0.000076543],"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":[0.00006005316,0.0001389371,0.001258185,0.00009573586,0.0001054566,0.000005301448,0.000385203,0.9950191,0.002084472,0.0006767792,0.000008191482,0.0001625205],"study_design_scores_gemma":[0.0004812763,0.0005243698,0.0001726389,0.0001649767,0.0001108939,0.00002921951,0.0006237152,0.9847877,0.0002995642,0.01268275,1.611732e-7,0.000122718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4941989,0.0001151538,0.5053977,0.00000672195,0.00007775056,0.0001121758,0.00001532352,0.00001953373,0.00005667704],"genre_scores_gemma":[0.7885933,0.00002654149,0.2112745,0.000004269695,0.00006880049,0.000006392619,0.000003829898,0.00002205997,3.191263e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2943944,"threshold_uncertainty_score":0.6432528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06232288245124808,"score_gpt":0.304471517103059,"score_spread":0.242148634651811,"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."}}