{"id":"W4414465667","doi":"10.1038/s41597-025-05428-4","title":"Quantum mechanical dataset of 836k neutral closed-shell molecules with up to 5 heavy atoms from C, N, O, F, Si, P, S, Cl, Br","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Structural Genomics Consortium; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Basic Energy Sciences; Office of Science; Canada First Research Excellence Fund; University of Toronto; Argonne National Laboratory; U.S. Department of Energy; European Commission; Compute Canada; Government of Canada; Canadian Institute for Advanced Research; Laboratory Directed Research and Development","keywords":"Conformational isomerism; Quantum Monte Carlo; Molecule; Multipole expansion; Quantum; Quantum chemistry; Quantum chemical; Diffusion Monte Carlo","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":[0.0004323371,0.001648107,0.001241681,0.0007661573,0.0008075043,0.0007669269,0.003194084,0.001902833,0.01321507],"category_scores_gemma":[0.001216948,0.0003570406,0.001164921,0.0020753,0.0005237702,0.0009425401,0.0008539265,0.001485057,0.007217646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005113,"about_ca_system_score_gemma":0.001191766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009336267,"about_ca_topic_score_gemma":0.01584773,"domain_scores_codex":[0.9994949,0.00008558675,0.00002838255,0.0001440335,0.0001749226,0.00007216701],"domain_scores_gemma":[0.999627,0.00009501354,0.0000431087,0.0001134477,0.00007738297,0.00004404446],"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":[0.001035416,0.0009546037,0.01688262,0.005998124,0.0006991313,0.0009236604,0.0001361098,0.1312277,0.02002761,0.02149699,0.7540394,0.04657858],"study_design_scores_gemma":[0.001292599,0.0006663206,0.01637695,0.0003022928,0.0002237139,0.0007367795,0.0003016034,0.2067498,0.02079654,0.02094313,0.7314141,0.000196065],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1395955,0.004625269,0.00544914,0.0009145011,0.0002225097,0.0001840806,0.8284735,0.003409903,0.01712556],"genre_scores_gemma":[0.101088,0.001014091,0.007582097,0.0003393232,0.00004527788,0.0002572305,0.88686,0.000277312,0.002536774],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01321507,"threshold_uncertainty_score":0.04420882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02742171663080592,"score_gpt":0.3067360341635273,"score_spread":0.2793143175327214,"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."}}