{"id":"W4405229197","doi":"10.26434/chemrxiv-2024-rzqmh","title":"A Machine-Learned \"Chemical Intuition\" to Overcome Spectroscopic Data Scarcity","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ion; Spectral line; Intuition; Molecule; Curse of dimensionality; Chemistry; Infrared spectroscopy; Spectroscopy; Computer science; Density functional theory; Biological system; Chemical physics; Pattern recognition (psychology); Artificial intelligence; Computational chemistry; Physics; Quantum mechanics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007899672,0.0008367694,0.0006625876,0.00068878,0.0002818126,0.0007693802,0.001545279,0.001120083,0.002757807],"category_scores_gemma":[0.00267174,0.0003991315,0.0008477831,0.0006019343,0.0009998655,0.002363842,0.0008276504,0.002144711,0.0009031339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006492943,"about_ca_system_score_gemma":0.0009316351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001898298,"about_ca_topic_score_gemma":0.002295546,"domain_scores_codex":[0.9997413,0.00006510279,0.00001143755,0.0000991628,0.00006400546,0.00001901628],"domain_scores_gemma":[0.9991246,0.0003915076,0.00009571674,0.000236024,0.0001203155,0.00003178399],"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":[0.000109618,0.0001749209,0.002313489,0.0003314475,0.00008441119,0.0001417323,0.00008711006,0.8763527,0.02424077,0.03421875,0.003148866,0.05879621],"study_design_scores_gemma":[0.00000657515,0.00002665256,0.0002417394,0.000006655823,0.000007122211,0.0000222583,0.0000060234,0.9818268,0.002212002,0.01456222,0.001075342,0.00000642397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06358218,0.0003256629,0.9287884,0.0007689794,0.00008771745,0.00006186391,0.0007494888,0.00165435,0.003981414],"genre_scores_gemma":[0.716117,0.0006333714,0.2762967,0.0006549138,0.0001072338,0.0001834205,0.001908164,0.0002807398,0.003818445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002757807,"threshold_uncertainty_score":0.009225845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03751195749812197,"score_gpt":0.315643826617444,"score_spread":0.278131869119322,"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."}}