{"id":"W4407429730","doi":"10.1016/j.ijhydene.2025.01.502","title":"Predicting hydrogen production from formic acid dehydrogenation using smart connectionist models","year":2025,"lang":"en","type":"article","venue":"International Journal of Hydrogen Energy","topic":"Carbon dioxide utilization in catalysis","field":"Chemical Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Ministerio del Ambiente, Agua y Transición Ecológica","keywords":"Dehydrogenation; Formic acid; Connectionism; Hydrogen production; Hydrogen; Computer science; Production (economics); Process engineering; Chemistry; Artificial neural network; Organic chemistry; Artificial intelligence; Catalysis; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0003181304,0.0002177675,0.0003048855,0.0006307147,0.00009421641,0.00006748611,0.0004797112,0.0001445077,0.00006155705],"category_scores_gemma":[0.0004062546,0.0002347426,0.0003044196,0.000441088,0.00004703176,0.000921506,0.0001184039,0.0002136634,0.000003116459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008103176,"about_ca_system_score_gemma":0.0001473184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004726368,"about_ca_topic_score_gemma":0.00006807224,"domain_scores_codex":[0.997714,0.00005255069,0.0009793874,0.0002636666,0.000752961,0.0002374338],"domain_scores_gemma":[0.9982271,0.00009315849,0.0005982495,0.0002243415,0.0007484338,0.0001087362],"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":[0.00008543291,0.00009013725,0.003279657,0.000006565979,0.001113457,0.00001235155,0.0001494194,0.5896726,0.401087,0.003132814,0.00007667222,0.001293903],"study_design_scores_gemma":[0.0003815077,0.00000773039,0.0000146775,0.00009777303,0.0001221685,0.0001160892,0.00007413432,0.4366465,0.5588601,0.002575963,0.0009828986,0.0001205254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8750232,0.0009424098,0.1208579,0.0002428624,0.002010051,0.00005131336,0.00002438323,0.0000718505,0.0007760463],"genre_scores_gemma":[0.997258,0.00008987798,0.001219471,0.0001525771,0.0009556242,0.000008765408,0.00008125516,0.00003174185,0.0002026724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.157773,"threshold_uncertainty_score":0.9572527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01416872940615756,"score_gpt":0.2491027533171119,"score_spread":0.2349340239109544,"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."}}