{"id":"W4403376878","doi":"10.1021/acs.jpca.4c04416","title":"Exploring Nanocluster Potential Energy Surfaces via Deep Reinforcement Learning: Strategies for Global Minimum Search","year":2024,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry A","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Reinforcement learning; Energy (signal processing); Computer science; Artificial intelligence; Nanotechnology; Materials science; Mathematics; Statistics","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":[0.0007073343,0.0006005252,0.0007853889,0.0003345585,0.0002934512,0.0006971975,0.001158905,0.0009383686,0.001356952],"category_scores_gemma":[0.002064181,0.0003682995,0.0004294116,0.0002315623,0.001044106,0.0008394007,0.001204652,0.000999169,0.0001742234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009250217,"about_ca_system_score_gemma":0.0007338113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003078234,"about_ca_topic_score_gemma":0.002933865,"domain_scores_codex":[0.9998566,0.00005560641,0.000006432031,0.00002868899,0.00002812446,0.00002455381],"domain_scores_gemma":[0.9994203,0.0003806736,0.00006098063,0.00003953746,0.00005584121,0.00004269307],"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":[0.00002888633,0.00002793624,0.0005111171,0.00005160261,0.00002329766,0.00004496527,0.00003837305,0.9647722,0.001444919,0.01717413,0.0005001986,0.01538243],"study_design_scores_gemma":[0.000002968183,0.000006908153,0.00001746892,0.000002545057,0.000001450291,0.000002710982,0.000002630878,0.9964316,0.00009316202,0.003335893,0.0001010901,0.000001502513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08461301,0.0008716464,0.9068199,0.0007865797,0.00004896817,0.00005589797,0.00004987083,0.000340735,0.006413442],"genre_scores_gemma":[0.90342,0.0003538624,0.09316505,0.0002797243,0.0000271676,0.0001734296,0.00005781015,0.00006772816,0.002455241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003078234,"threshold_uncertainty_score":0.006711543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02920259285850844,"score_gpt":0.2870761037160783,"score_spread":0.2578735108575698,"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."}}