{"id":"W4410312534","doi":"10.1007/s40194-025-02056-9","title":"Deep learning for predicting welding distortions in T-joints","year":2025,"lang":"en","type":"article","venue":"Welding in the World","topic":"Welding Techniques and Residual Stresses","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Materials science; Solid mechanics; Welding; Metallurgy; Artificial intelligence; Composite material; Computer science","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":[0.0005212878,0.0001363037,0.0001664611,0.0003959174,0.0001704336,0.00006308201,0.000274401,0.00006273125,0.0000142144],"category_scores_gemma":[0.0002046538,0.0001151966,0.00006219509,0.0007266874,0.00002431559,0.00007781525,0.00004893091,0.0004396797,0.000001734809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388533,"about_ca_system_score_gemma":0.000007332127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008710611,"about_ca_topic_score_gemma":0.001352981,"domain_scores_codex":[0.9990677,0.00004341325,0.0002963101,0.000170037,0.00009525144,0.0003272848],"domain_scores_gemma":[0.9992715,0.0005001213,0.00003206392,0.0001654286,0.00001185524,0.00001905756],"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":[0.00001658425,0.00004479194,0.08271468,0.0003040242,0.00002921366,0.00001182132,0.00108805,0.9001512,0.0006116384,0.003146659,0.004699038,0.007182302],"study_design_scores_gemma":[0.00249995,0.0001356937,0.121712,0.006849888,0.0001403272,0.00001679437,0.003783791,0.5274655,0.05388166,0.024588,0.2573152,0.001611201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7651717,0.003546642,0.102806,0.00281642,0.001933966,0.001775098,0.000005914255,0.002024926,0.1199193],"genre_scores_gemma":[0.9970984,0.00006159842,0.001905227,0.00005027263,0.00008676064,0.0001841241,0.00000484201,0.00002271643,0.0005860798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3726857,"threshold_uncertainty_score":0.4697582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01058217246657619,"score_gpt":0.2594773318106084,"score_spread":0.2488951593440323,"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."}}