{"id":"W3012003849","doi":"10.1016/j.ijhydene.2020.02.136","title":"3D classification of polymer electrolyte membrane fuel cell materials from in-situ X-ray tomographic datasets","year":2020,"lang":"en","type":"article","venue":"International Journal of Hydrogen Energy","topic":"Fuel Cells and Related Materials","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Helmholtz-Zentrum Berlin für Materialien und Energie","keywords":"Porosity; Thermal diffusivity; Materials science; Proton exchange membrane fuel cell; Voxel; Tomography; Work (physics); Fuel cells; Computer science; Chemical engineering; Composite material; Mechanical engineering; Optics; Artificial intelligence","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":[0.0002852477,0.001356158,0.0006107582,0.004403255,0.0003659914,0.00198097,0.0008224557,0.001724771,0.004886829],"category_scores_gemma":[0.0006453966,0.000600581,0.001123429,0.001860459,0.0004236545,0.0007428996,0.0006868685,0.0005713522,0.002488808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004071708,"about_ca_system_score_gemma":0.0005667023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00405247,"about_ca_topic_score_gemma":0.007514289,"domain_scores_codex":[0.9998066,0.00001046471,0.00001670334,0.00004402843,0.00008043766,0.00004186832],"domain_scores_gemma":[0.999773,0.00005557053,0.00003687307,0.00003590505,0.00008240015,0.00001641844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001675629,0.0005875354,0.04416564,0.003469756,0.0004916679,0.001948687,0.0007340959,0.139581,0.3718111,0.003513617,0.0387582,0.393263],"study_design_scores_gemma":[0.0001091997,0.0002040929,0.07698181,0.0003114346,0.0004841811,0.002922463,0.001145536,0.6863098,0.1806486,0.003415952,0.04727504,0.0001918716],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7636062,0.004844915,0.1395736,0.0009488004,0.0002295786,0.0006611845,0.06366222,0.01288674,0.01358673],"genre_scores_gemma":[0.8533165,0.002869417,0.0995938,0.0001793779,0.00006067937,0.0003344971,0.03883554,0.001065693,0.003744456],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004886829,"threshold_uncertainty_score":0.01634812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007828418336668449,"score_gpt":0.2010759720154632,"score_spread":0.1932475536787948,"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."}}