{"id":"W4410050200","doi":"10.1016/j.jallcom.2025.180709","title":"Data-driven explainable machine learning approaches for predicting hydrogen adsorption in porous crystalline materials","year":2025,"lang":"en","type":"article","venue":"Journal of Alloys and Compounds","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Adsorption; Porosity; Materials science; Porous medium; Hydrogen; Computer science; Chemistry; Physical chemistry; Composite material; Organic chemistry","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":[0.00141001,0.0005150199,0.0006482997,0.001222623,0.0003240121,0.0007354821,0.001206413,0.001063792,0.0009244671],"category_scores_gemma":[0.005019644,0.000493914,0.0009327769,0.0007996705,0.0005158478,0.0014651,0.0005875766,0.0009463179,0.0001420788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008940026,"about_ca_system_score_gemma":0.00062285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005501134,"about_ca_topic_score_gemma":0.005644185,"domain_scores_codex":[0.9997823,0.00009363214,0.00001619191,0.00004864888,0.00003445747,0.00002479706],"domain_scores_gemma":[0.9960423,0.003377457,0.0002031877,0.0001355623,0.0001860303,0.00005554218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005775843,0.0000439938,0.002038607,0.00005912153,0.00006926756,0.0000347316,0.00004061062,0.9812831,0.0008136157,0.006533085,0.0003755144,0.00865058],"study_design_scores_gemma":[0.000002000314,0.000002563052,0.00009968506,8.330476e-7,0.000003138589,0.000001510403,0.000002130634,0.9973653,0.00009612115,0.002395092,0.00003033333,0.000001278521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4215921,0.001641557,0.5719744,0.001190858,0.00008411841,0.00009098404,0.00135431,0.0007629055,0.001308735],"genre_scores_gemma":[0.9723126,0.0004870723,0.02514638,0.00004907686,0.00009156208,0.0001165636,0.0007635434,0.00005916594,0.0009740258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005501134,"threshold_uncertainty_score":0.01093823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04883212447386075,"score_gpt":0.2627534371772068,"score_spread":0.213921312703346,"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."}}