{"id":"W4366984291","doi":"10.1021/acsami.3c02564","title":"Deep Generative Modeling of Infrared Images Provides Signature of Cracking in Cross-Linked Polyethylene Pipe","year":2023,"lang":"en","type":"article","venue":"ACS Applied Materials & Interfaces","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Light Source (Canada); University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Autoencoder; Pattern recognition (psychology); Infrared; Materials science; Artificial intelligence; Chemical imaging; Degradation (telecommunications); Biological system; Generative model; Polyethylene; Computer science; Representation (politics); Deep learning; Generative grammar; Computer vision; Optics; Physics; Composite material","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002469182,0.0004191127,0.0009317987,0.0003975274,0.000141031,0.0003413588,0.001119264,0.0002539046,0.0007410455],"category_scores_gemma":[0.0005168221,0.0003688105,0.00003229075,0.0005957558,0.0004577824,0.0004956155,0.0007104761,0.0001983559,0.0001120177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005755456,"about_ca_system_score_gemma":0.0001003844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003690981,"about_ca_topic_score_gemma":0.0000262198,"domain_scores_codex":[0.9961913,0.0002883373,0.001452409,0.0007897809,0.0006068948,0.0006712899],"domain_scores_gemma":[0.9980168,0.0002688032,0.0008289897,0.0005872798,0.0002353164,0.00006280647],"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":[0.0002612405,0.00003701489,0.0001258322,0.0003278581,0.00001030084,0.000005089868,0.002384008,0.1318215,0.8644324,0.0004259333,0.00002356894,0.0001452574],"study_design_scores_gemma":[0.0005100182,0.00009163028,0.000564906,0.0002042697,0.00001421162,0.000002440155,0.0005356938,0.00489625,0.9889922,0.003840227,0.000003932664,0.0003442266],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967696,0.0001585759,0.0007381382,0.00009532804,0.0008192511,0.0006159385,0.0001283896,0.0002281237,0.0004466778],"genre_scores_gemma":[0.9936495,0.00005525409,0.005762333,0.00004536296,0.0001485769,0.000122469,0.00003457411,0.00005988278,0.0001220308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1269252,"threshold_uncertainty_score":0.9998764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01665683349033916,"score_gpt":0.291380459429443,"score_spread":0.2747236259391039,"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."}}