{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002329236,0.001853793,0.001733497,0.002730679,0.001374303,0.001393096,0.005191281,0.002476083,0.00579211],"category_scores_gemma":[0.0056714,0.0005501098,0.002093349,0.00421584,0.0006422367,0.001400065,0.001589088,0.002320855,0.002268866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001259045,"about_ca_system_score_gemma":0.002155748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01663285,"about_ca_topic_score_gemma":0.02047691,"domain_scores_codex":[0.9983435,0.0003834282,0.0001467061,0.0002611593,0.0006981983,0.0001669781],"domain_scores_gemma":[0.996648,0.001457089,0.0002642318,0.0006940025,0.0007387471,0.0001978913],"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":[0.001438098,0.001169508,0.01710217,0.008154332,0.001514266,0.0007448806,0.0001560375,0.5016438,0.0142439,0.02785619,0.3436335,0.08234333],"study_design_scores_gemma":[0.0008621943,0.0007664844,0.01534765,0.0003409139,0.0002508765,0.0005644371,0.0002168204,0.7339479,0.03048333,0.02199609,0.1950184,0.0002048991],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2760541,0.009971636,0.06221452,0.001649961,0.0009254586,0.0009470605,0.5945678,0.01338832,0.04028122],"genre_scores_gemma":[0.2055391,0.00219899,0.06180089,0.0004300599,0.0001269706,0.001094269,0.7231165,0.001742076,0.003951241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01663285,"threshold_uncertainty_score":0.03307205,"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."}}