{"id":"W4410567332","doi":"10.1016/j.tws.2025.113494","title":"Comparison of deep learning techniques for prediction of stress distribution in stiffened panels","year":2025,"lang":"en","type":"article","venue":"Thin-Walled Structures","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Stress (linguistics); Computer science; Structural engineering; Artificial intelligence; Engineering","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":[0.0001575114,0.0001469546,0.0004636705,0.0001640637,0.00005290906,0.00001162328,0.0001623698,0.0002280601,0.0000273568],"category_scores_gemma":[0.0002322241,0.0001274224,0.0001299744,0.0003037652,0.000083239,0.00006797776,0.00002645197,0.000319397,8.663545e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008323908,"about_ca_system_score_gemma":0.00001163424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001394201,"about_ca_topic_score_gemma":0.0001287929,"domain_scores_codex":[0.998949,0.00005717992,0.0005447906,0.0001560281,0.0001385394,0.0001544756],"domain_scores_gemma":[0.9993905,0.0001996343,0.0001020753,0.0001637298,0.0001226793,0.00002139244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004598914,0.0001031781,0.06942712,0.003400489,0.0006727715,7.715369e-7,0.005104341,0.7023093,0.1432484,0.01294225,0.0002181498,0.06211337],"study_design_scores_gemma":[0.0004602324,0.0000928885,0.1313245,0.0001908332,0.0001264893,4.566562e-7,0.001189479,0.2145014,0.6351453,0.01663607,0.0001910993,0.0001412066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9501652,0.0005286522,0.04802816,0.00003845252,0.0002190935,0.0003591519,0.0002436677,0.0001748716,0.0002427349],"genre_scores_gemma":[0.9979897,0.00005366707,0.00160584,0.00000264929,0.00002466551,0.00002127091,0.0002729329,0.000008315217,0.00002100119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4918969,"threshold_uncertainty_score":0.5196133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01347190683848767,"score_gpt":0.2831064777148888,"score_spread":0.2696345708764011,"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."}}