{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002556985,0.0005439348,0.0005869575,0.001857658,0.0007252372,0.001139417,0.001380089,0.001247897,0.001691818],"category_scores_gemma":[0.008192256,0.0001746734,0.000839517,0.002341961,0.0007994313,0.001110594,0.001244715,0.001678779,0.0004400921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001062264,"about_ca_system_score_gemma":0.0009001992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007342517,"about_ca_topic_score_gemma":0.01000712,"domain_scores_codex":[0.9986976,0.0004645278,0.00007251633,0.0002818846,0.0003774771,0.0001059064],"domain_scores_gemma":[0.9968904,0.001661503,0.000299993,0.0005379287,0.0004584278,0.0001518195],"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":[0.001378829,0.002149176,0.1134428,0.001688206,0.0003898935,0.001259796,0.000911049,0.4014851,0.01642739,0.1584708,0.1314968,0.1709],"study_design_scores_gemma":[0.000194685,0.000253478,0.04909197,0.0001024816,0.00003477777,0.0003507045,0.000423106,0.8239067,0.004243636,0.07201219,0.04930888,0.00007740704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7911738,0.003982887,0.08275594,0.009237042,0.0002754338,0.0003314459,0.09534245,0.001830087,0.01507101],"genre_scores_gemma":[0.773329,0.0008092541,0.08656424,0.0009801355,0.000178728,0.0003596431,0.1348252,0.0001767209,0.002777071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007342517,"threshold_uncertainty_score":0.01459956,"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."}}