{"id":"W4280533865","doi":"10.1038/s41597-022-01330-5","title":"A benchmark dataset for Hydrogen Combustion","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Division of Chemistry; Natural Sciences and Engineering Research Council of Canada; Office of Science; National Energy Research Scientific Computing Center; China Scholarship Council; U.S. Department of Energy; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Potential energy surface; Combustion; Ab initio; Benchmark (surveying); Hydrogen; Reaction coordinate; Chemistry; Potential energy; Density functional theory; Computer science; Statistical physics; Computational chemistry; Physics; Atomic physics; Physical chemistry","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008551876,0.0001317718,0.0001605139,0.0001254031,0.002042802,0.0006912214,0.004563924,0.00002057582,0.00883648],"category_scores_gemma":[0.0006566431,0.0001290125,0.00002458576,0.0004686436,0.0003402581,0.0006998572,0.004514709,0.000110319,0.0004647668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006059606,"about_ca_system_score_gemma":0.0001648839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006105682,"about_ca_topic_score_gemma":0.00002301262,"domain_scores_codex":[0.9968284,0.0002664008,0.0003109769,0.001283737,0.0008439046,0.0004665401],"domain_scores_gemma":[0.9965069,0.0001418557,0.0001916592,0.003005931,0.0000504394,0.0001031806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000251213,0.00006072615,0.00003994516,0.00001970634,0.000001730724,0.000002754551,0.00007903973,0.003197779,0.408492,0.0004186871,0.5869249,0.0007377176],"study_design_scores_gemma":[0.0002870405,0.00007478442,0.00006623546,0.000004976339,0.00001827536,0.00002418006,0.00009359991,0.05106558,0.01921519,0.001481939,0.9274415,0.0002267531],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.33739,0.0001707567,0.009814845,0.001576076,0.01499577,0.001415768,0.6336077,0.0002769974,0.0007520685],"genre_scores_gemma":[0.453651,0.000001792261,0.05981436,0.0008722416,0.0004000161,0.0004145885,0.4800456,0.00005870385,0.004741705],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3892768,"threshold_uncertainty_score":0.9992564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0528722733954892,"score_gpt":0.3192898238311557,"score_spread":0.2664175504356665,"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."}}