{"id":"W4391653868","doi":"10.1002/jcc.27295","title":"Novel machine learning insights into the QM7b and QM9 quantum mechanics datasets","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Predictability; Cluster analysis; Computer science; Curse of dimensionality; Inverse; Molecule; Dimension (graph theory); Outlier; Set (abstract data type); Embedding; Statistical physics; Mathematics; Artificial intelligence; Quantum mechanics; Physics; Geometry; Pure mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.0007909561,0.0001553391,0.0001810974,0.00008903191,0.0001771419,0.0003822928,0.0006444137,0.00005098752,0.000009539092],"category_scores_gemma":[0.0002119067,0.0001116323,0.00009605564,0.0003699839,0.00004972354,0.0006199795,0.000319348,0.0005692083,0.000004823921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007261946,"about_ca_system_score_gemma":0.0003555518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005751388,"about_ca_topic_score_gemma":6.581981e-7,"domain_scores_codex":[0.9984187,0.00008932655,0.0004529948,0.0002397498,0.0006688219,0.0001303701],"domain_scores_gemma":[0.9979751,0.001340873,0.0002248528,0.0001501101,0.0002028276,0.0001062936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001956573,0.00006923934,0.00001313518,0.0001365338,0.0001442456,0.0001030168,0.001518346,0.9266235,0.006879251,0.04621031,0.0007483655,0.01753452],"study_design_scores_gemma":[0.0001900326,0.0000289379,0.0001342723,0.00007744951,0.00001569097,0.0007518107,0.00003404066,0.7629442,0.0009010793,0.2239598,0.01085689,0.000105771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06748948,0.004392839,0.9252043,0.002386573,0.0003673949,0.00004010583,0.00001043423,0.00003947508,0.00006935172],"genre_scores_gemma":[0.933208,0.00008085995,0.06610306,0.0002195137,0.0002975052,0.000001658968,0.0000452961,0.00001499574,0.00002906662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8657185,"threshold_uncertainty_score":0.4552234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01709552894626107,"score_gpt":0.2934647125879716,"score_spread":0.2763691836417106,"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."}}