{"id":"W2906453878","doi":"10.1039/c8sc04516j","title":"How machine learning can assist the interpretation of <i>ab initio</i> molecular dynamics simulations and conceptual understanding of chemistry","year":2018,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; Toronto Public Health; Canadian Institute for Advanced Research","funders":"Vetenskapsrådet; National Science Council; FAS Division of Science, Harvard University; Uppsala Multidisciplinary Center for Advanced Computational Science; Harvard University","keywords":"Interpretation (philosophy); Molecular dynamics; Dynamics (music); Ab initio; Computer science; Chemistry; Computational chemistry; Artificial intelligence; Physics; Organic chemistry","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008288234,0.0001146867,0.0001719809,0.00003563826,0.0002855962,0.0001562716,0.0005875975,0.00004769337,0.00009910087],"category_scores_gemma":[0.00176334,0.00008572144,0.00002582225,0.000479566,0.006677319,0.0002333815,0.0002880073,0.0001376083,0.000001093909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001567569,"about_ca_system_score_gemma":0.0001464367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005668132,"about_ca_topic_score_gemma":0.00001426558,"domain_scores_codex":[0.9985803,0.00006558083,0.0002537044,0.0003395459,0.0005094952,0.0002513817],"domain_scores_gemma":[0.9989611,0.0002484969,0.0002893585,0.0002323048,0.0001852739,0.00008346335],"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":[0.0000106568,0.00000994778,0.001079147,0.00002320095,0.000001255951,3.451501e-7,0.001131392,0.0008664848,0.9948384,0.001953576,0.000002186427,0.00008339818],"study_design_scores_gemma":[0.00009942184,0.00003429175,0.00009169948,0.00004179971,0.000006841281,0.000005555075,0.0008452813,0.2150388,0.7826386,0.001103387,0.00000890546,0.00008538624],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9577186,0.00001761984,0.04020869,0.000838195,0.0000964041,0.0000816956,0.00002914982,0.00002577253,0.0009839373],"genre_scores_gemma":[0.9979874,0.000001327596,0.001864639,0.00007445479,0.00002625155,0.000002285871,0.00000653727,0.000006948571,0.00003018518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2141723,"threshold_uncertainty_score":0.9960259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01587374378488294,"score_gpt":0.2567378238287153,"score_spread":0.2408640800438324,"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."}}