{"id":"W4407638096","doi":"10.1021/acs.jcim.4c02329","title":"A Machine-Learned “Chemical Intuition” to Overcome Spectroscopic Data Scarcity","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Radboud Universiteit; University of Waterloo; Canada Foundation for Innovation; Ontario Research Foundation","keywords":"Intuition; Scarcity; Computer science; Machine learning; Artificial intelligence; Data science; Cognitive science; Psychology; Economics; Microeconomics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002884978,0.00009463046,0.0001867403,0.0001133059,0.00003604113,0.00005214843,0.0002275765,0.00007612817,0.000007962817],"category_scores_gemma":[0.0003394904,0.00008063952,0.00004848588,0.0001039136,0.00002253348,0.00004170798,0.0003488053,0.0001512994,0.000001721258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001973252,"about_ca_system_score_gemma":0.00006063658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005590414,"about_ca_topic_score_gemma":4.727741e-7,"domain_scores_codex":[0.9991999,0.00001133565,0.000432707,0.000104044,0.0001254778,0.0001265911],"domain_scores_gemma":[0.9994401,0.0000100927,0.000114036,0.0001970072,0.0001525044,0.00008624289],"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":[0.000269646,0.00004326881,0.0002971277,0.0000603901,0.0001235377,4.007865e-7,0.0000952711,0.0003164497,0.9871615,0.002145462,0.003478246,0.006008675],"study_design_scores_gemma":[0.003533296,0.000278064,0.0001470588,0.0001862784,0.000177234,0.0000821394,0.0003303891,0.1308313,0.7858392,0.007964079,0.07007955,0.0005514192],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8589221,0.0007596113,0.1378778,0.001239606,0.0001198218,0.0000729618,0.0000174681,0.000004650659,0.0009860095],"genre_scores_gemma":[0.9907061,0.0005643746,0.007300735,0.001238774,0.00009764817,0.000001439448,0.00006507411,0.000003274179,0.00002253245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2013223,"threshold_uncertainty_score":0.3288384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02848981108614175,"score_gpt":0.3123284747111827,"score_spread":0.283838663625041,"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."}}