{"id":"W2772285008","doi":"10.1021/acs.jpca.7b10303","title":"Applying Machine Learning to Vibrational Spectroscopy","year":2017,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry A","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Chemistry; Cluster (spacecraft); Dimer; Spectroscopy; Protonation; Spectral line; Infrared spectroscopy; Potential energy surface; Partition (number theory); Electrospray ionization; Hierarchical clustering; Atomic physics; Cluster analysis; Molecular physics; Computational chemistry; Molecule; Ion; Combinatorics; Artificial intelligence; Physics; Organic chemistry; Computer science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001718497,0.0001159986,0.0001775404,0.000010567,0.0004578846,0.00009426831,0.0007718699,0.00003591661,0.001163583],"category_scores_gemma":[0.0001493016,0.00008048092,0.0001224539,0.00004886027,0.0000656817,0.00008781619,0.0001329102,0.0005457985,0.00001254938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005335894,"about_ca_system_score_gemma":0.00003135359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000818332,"about_ca_topic_score_gemma":3.639171e-7,"domain_scores_codex":[0.9992634,0.000007702663,0.0001975755,0.00009474861,0.0002773537,0.0001592154],"domain_scores_gemma":[0.99892,0.00009486182,0.0003994169,0.0004005966,0.00007294067,0.0001122404],"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":[0.00003726536,0.00007276736,0.00008785224,0.00002273177,0.00002275834,0.000002318465,0.00005807021,0.0002929745,0.9980733,0.0006316786,0.0001835446,0.000514731],"study_design_scores_gemma":[0.0001455596,0.00002840786,0.00007061984,0.00003383443,0.00003174068,0.00004342214,0.00003560621,0.002832164,0.9856001,0.003224636,0.007859529,0.00009437393],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8037062,0.00008499138,0.02051667,0.004665149,0.00001892857,0.0001655205,0.00002665639,0.00009722507,0.1707187],"genre_scores_gemma":[0.9966199,0.00001133614,0.001828842,0.00004306397,0.000980216,0.00001847005,0.00000304097,0.00001451545,0.000480646],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1929137,"threshold_uncertainty_score":0.9997495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01300824979334894,"score_gpt":0.2915212313711344,"score_spread":0.2785129815777855,"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."}}