{"id":"W4405360889","doi":"10.1115/ipc2024-133130","title":"Benchmarking of Three Girth Weld Flaw Assessment Models: A Validation Methodology","year":2024,"lang":"en","type":"article","venue":"Volume 3: Operations, Monitoring, and Maintenance; Materials and Joining","topic":"Fatigue and fracture mechanics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dynamic Systems Analysis (Canada)","funders":"","keywords":"Benchmarking; Girth (graph theory); Welding; Computer science; Structural engineering; Engineering; Mechanical engineering; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01094875,0.000893155,0.0006573422,0.001454628,0.0004186161,0.001223547,0.001496657,0.001140388,0.0008012475],"category_scores_gemma":[0.01798157,0.0003513527,0.0008387236,0.0009719788,0.0008725622,0.0007923114,0.00138235,0.001117854,0.0001296287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033931,"about_ca_system_score_gemma":0.001452762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003546861,"about_ca_topic_score_gemma":0.002197698,"domain_scores_codex":[0.9967331,0.001936865,0.0002185784,0.0002920124,0.0006897556,0.0001296626],"domain_scores_gemma":[0.9901378,0.00643716,0.0007741679,0.001224185,0.001323429,0.0001033154],"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":[0.0001032503,0.000196938,0.005474626,0.00009233213,0.00006746092,0.0000622918,0.00008875583,0.967916,0.00338766,0.005859385,0.0001926635,0.01655868],"study_design_scores_gemma":[0.000009650355,0.0002050719,0.00112855,0.00002289725,0.00001151269,0.00001815784,0.00003005456,0.9932296,0.003770093,0.001352781,0.0002088657,0.00001263478],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6557733,0.0001926765,0.3379181,0.0002201663,0.00002102686,0.0005469161,0.0005534741,0.0004213099,0.004353068],"genre_scores_gemma":[0.9324598,0.00005556534,0.06661823,0.00002415611,0.000004276888,0.0002121927,0.0003142561,0.00001676675,0.0002947471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01094875,"threshold_uncertainty_score":0.05790323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04602779978010277,"score_gpt":0.2775412545148278,"score_spread":0.231513454734725,"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."}}