{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006898116,0.0001830224,0.0003132038,0.0001132084,0.0001391942,0.0002624388,0.00005722967,0.0001116886,0.00004969629],"category_scores_gemma":[0.00002691175,0.0001616603,0.00003127694,0.00008707118,0.00003225367,0.0004153576,0.00004797665,0.0001253607,0.000001566221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000327448,"about_ca_system_score_gemma":0.00002790238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001574049,"about_ca_topic_score_gemma":0.00001689226,"domain_scores_codex":[0.9989606,0.00006090499,0.0003963387,0.0002471558,0.0001117237,0.0002232377],"domain_scores_gemma":[0.9996555,0.00006143333,0.00003604572,0.0001365597,0.00005742222,0.00005299962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003737416,0.00003682102,0.002092039,0.002012158,0.0003802806,0.00003196184,0.004996371,0.06941235,0.7510111,0.09446506,0.001074943,0.07444949],"study_design_scores_gemma":[0.0006988285,0.0003314493,0.003272293,0.001661094,0.0002044402,0.00005487334,0.001027721,0.8204261,0.1566668,0.008426865,0.006427919,0.0008015647],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6276677,0.002138123,0.3659706,0.00009410902,0.00337977,0.0002091628,0.00003415793,0.0001595789,0.0003467682],"genre_scores_gemma":[0.9411206,0.002043791,0.05613817,0.00001179313,0.0005038538,0.00004962131,0.00002640103,0.00003257988,0.00007319355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7510138,"threshold_uncertainty_score":0.6592315,"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."}}