{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003710501,0.0003071286,0.0004875046,0.0002441252,0.0004069005,0.0009970909,0.005775071,0.00009366732,0.001203297],"category_scores_gemma":[0.0006759778,0.0002440132,0.000037362,0.001124557,0.0008057234,0.000782752,0.003415945,0.0001946055,0.000888955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004033095,"about_ca_system_score_gemma":0.0003885858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001397181,"about_ca_topic_score_gemma":0.0006775685,"domain_scores_codex":[0.9952037,0.0003673545,0.0007344791,0.002094997,0.0009017385,0.0006977344],"domain_scores_gemma":[0.9941614,0.0002155165,0.0002739197,0.004942647,0.0001514208,0.0002551014],"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":[0.0001863602,0.00009291785,0.0001313144,0.00005270824,0.00001015537,0.00001158644,0.0001081887,0.0002747417,0.8002633,0.006479852,0.192108,0.000280784],"study_design_scores_gemma":[0.0008475785,0.0002136089,0.001349183,0.0003496667,0.00009698975,0.000009719631,0.0002341653,0.02446931,0.8039213,0.005526115,0.1623253,0.0006569778],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8827944,0.0000925796,0.02708125,0.0009063623,0.005946697,0.000535181,0.08230233,0.0001522437,0.0001889821],"genre_scores_gemma":[0.9064083,0.000006266177,0.06248545,0.0009950454,0.0001581273,0.00003069534,0.02830159,0.0000487301,0.00156581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05400075,"threshold_uncertainty_score":0.999889,"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."}}