{"id":"W2912650435","doi":"10.1038/s41598-019-38482-1","title":"Towards calibration-invariant spectroscopy using deep learning","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Electrochemical Analysis and Applications","field":"Chemistry","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Spectrometer; Computer science; Calibration; Convolutional neural network; Artificial intelligence; Spectroscopy; Invariant (physics); Pattern recognition (psychology); Physics; Optics; Mathematics; Statistics","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":[0.000394808,0.0001107596,0.0001596434,0.00005103196,0.0002814963,0.0002812366,0.0001196712,0.00006583686,0.002742032],"category_scores_gemma":[0.00006864777,0.00009890219,0.0001138559,0.0004078201,0.00006573313,0.0001211138,0.00005574338,0.0001780086,0.00005656282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009721725,"about_ca_system_score_gemma":0.0001460657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004136104,"about_ca_topic_score_gemma":0.00000722179,"domain_scores_codex":[0.9982936,0.000009069864,0.0003544908,0.0006095099,0.0004631643,0.0002701557],"domain_scores_gemma":[0.9989819,0.00001549116,0.0002267662,0.0005855862,0.00009537993,0.00009486263],"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":[0.000001166646,0.00002902211,0.003597205,0.00001672282,0.00001521006,0.00001233349,0.00005194497,0.0005724091,0.9949253,0.0003056707,0.000283395,0.0001896254],"study_design_scores_gemma":[0.00004320679,0.000003390513,0.00001915918,0.00001693818,0.00002812986,0.00005632591,0.00005303607,0.04487083,0.9309401,0.005154029,0.01866977,0.0001450784],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9726679,0.0001006209,0.005787742,0.00008267297,0.0002961888,0.00006091749,9.144883e-7,0.00009408228,0.02090891],"genre_scores_gemma":[0.9908506,0.000002504475,0.002210177,0.00001692541,0.0000978613,0.000008792231,0.00009969902,0.00001405769,0.006699327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0639852,"threshold_uncertainty_score":0.9981696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009677180976195559,"score_gpt":0.2480474662757352,"score_spread":0.2383702852995397,"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."}}