{"id":"W4236847470","doi":"10.26434/chemrxiv-2021-mdjwx","title":"BH9, a New Comprehensive Benchmark Dataset for Barrier Heights and Reaction Energies: Assessment of Density Functional Approximations and Basis Set Incompleteness Potentials","year":2021,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Western Canada Research Grid; Compute Canada","keywords":"Benchmark (surveying); Coupled cluster; Basis set; Set (abstract data type); Density functional theory; Thermochemistry; Basis (linear algebra); Statistical physics; Computational chemistry; Computer science; Chemistry; Molecule; Mathematics; 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":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000840513,0.0003497389,0.0007029548,0.0001313926,0.0003326449,0.0003730796,0.0003056292,0.0002287464,0.0003630425],"category_scores_gemma":[0.0003013427,0.000334915,0.00008408743,0.0001171309,0.000316542,0.0003078862,0.00116214,0.0002236491,0.000001790388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007462619,"about_ca_system_score_gemma":0.0004478772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005035026,"about_ca_topic_score_gemma":0.00004859057,"domain_scores_codex":[0.9973754,0.0002534878,0.0006025643,0.001028476,0.0004567367,0.0002833056],"domain_scores_gemma":[0.9976835,0.0004191629,0.0006396809,0.0006907848,0.0003824023,0.0001844811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004139989,0.00004548482,0.0008056603,0.0009270523,0.0000457371,0.000002902882,0.0002492614,0.002836823,0.992514,0.0003831516,0.002038114,0.0001104405],"study_design_scores_gemma":[0.002865075,0.0002314243,0.2757407,0.001184713,0.0008630991,0.000177079,0.001386098,0.07324532,0.6234274,0.0120688,0.006591134,0.002219195],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9495676,0.0001648995,0.04690469,0.0002411905,0.001036605,0.0005597657,0.001460015,0.00004059314,0.00002466995],"genre_scores_gemma":[0.8927851,0.0000958101,0.09883049,0.000137866,0.0002680949,0.0001324395,0.007672219,0.0000284128,0.0000495448],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3690866,"threshold_uncertainty_score":0.9999103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04536853163544292,"score_gpt":0.3118624025683001,"score_spread":0.2664938709328571,"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."}}