{"id":"W3019848710","doi":"10.1016/j.compstruct.2020.112407","title":"Theory-guided machine learning for damage characterization of composites","year":2020,"lang":"en","type":"article","venue":"Composite Structures","topic":"Mechanical Behavior of Composites","field":"Engineering","cited_by":144,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Composite laminates; Materials science; Damage mechanics; Isotropy; Characterization (materials science); Composite material; Composite number; Finite element method; Artificial neural network; Structural engineering; Displacement (psychology); Experimental data; Computer science; Artificial intelligence; 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":[0.00007380368,0.0002310866,0.0003634994,0.00006805188,0.00008633564,0.00004566002,0.0003142341,0.00008889655,0.000124262],"category_scores_gemma":[0.00004001874,0.0002236059,0.0001191317,0.0001633478,0.00004188719,0.0001071764,0.00006621746,0.0002062622,0.000005397846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001583741,"about_ca_system_score_gemma":0.000005682709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001540429,"about_ca_topic_score_gemma":2.467026e-7,"domain_scores_codex":[0.9989697,0.00006362262,0.0003752917,0.0002116237,0.0001644433,0.0002152872],"domain_scores_gemma":[0.9993756,0.0001438269,0.00009368837,0.0001786429,0.00007845341,0.0001297915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000072334,0.000007292697,0.001324535,0.000177119,0.00004797562,0.000001428193,0.0003379288,0.007701834,0.984871,0.004091875,0.00004423659,0.001322466],"study_design_scores_gemma":[0.0005291998,0.0001394079,0.009909152,0.0000260682,0.00007471472,0.000004296177,0.000006448598,0.1243487,0.8624458,0.001277702,0.0009779959,0.0002604932],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8781869,0.000159556,0.1202951,0.00009612564,0.000166285,0.0003607034,0.00009074978,0.0004053883,0.0002391523],"genre_scores_gemma":[0.9914823,0.00001345971,0.00774746,0.000122655,0.0001172786,0.00001324612,0.0004273668,0.00006115325,0.00001509609],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1224252,"threshold_uncertainty_score":0.9118384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01788515313152309,"score_gpt":0.2424997939683372,"score_spread":0.2246146408368141,"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."}}