{"id":"W4416528705","doi":"10.1016/j.jwpe.2025.109105","title":"Machine learning-based optimization and interpretation of the adsorption capacities of metal-organic frameworks for endocrine-disrupting compounds","year":2025,"lang":"en","type":"article","venue":"Journal of Water Process Engineering","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea","keywords":"Interpretability; Adsorption; Interpretation (philosophy); Convolutional neural network; Variable (mathematics); Process (computing); Sorting; Artificial neural network","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":[0.000230752,0.0001126546,0.0002630696,0.0001091665,0.00004754337,0.00002361776,0.0001550711,0.0001032093,0.00003840032],"category_scores_gemma":[0.0003347577,0.0000759613,0.0001014841,0.0001279058,0.00003936739,0.0001118308,0.00002493524,0.0003591795,4.683113e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002854139,"about_ca_system_score_gemma":0.00002770359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002134021,"about_ca_topic_score_gemma":6.301416e-7,"domain_scores_codex":[0.9991329,0.00001337455,0.0005223666,0.00008828662,0.0001359383,0.0001071119],"domain_scores_gemma":[0.9990868,0.0001806056,0.000355797,0.0001059598,0.0002491334,0.00002167795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002818172,0.00002987558,0.0002999796,0.001063225,0.00008449257,6.774777e-8,0.0005495763,0.59897,0.3983864,0.0001141956,0.00000137075,0.0004726924],"study_design_scores_gemma":[0.0001918012,0.00001293568,0.00001344895,0.0004832081,0.00009116466,0.000004976796,0.0001645931,0.4682663,0.5305467,0.0001349942,0.00004392861,0.0000458848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3899869,0.0004002099,0.6092208,0.0001908668,0.00006862412,0.00007114767,0.000004893817,0.00001247094,0.00004411006],"genre_scores_gemma":[0.9932742,0.00003250479,0.006554201,0.0000101383,0.00003928451,0.00001218319,0.000006319097,0.00001809994,0.0000530612],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6032873,"threshold_uncertainty_score":0.3097612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006068331069915054,"score_gpt":0.2254736881522432,"score_spread":0.2194053570823281,"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."}}