{"id":"W4408059061","doi":"10.1016/j.saa.2025.125975","title":"Leveraging infrared spectroscopy for cocoa content prediction: A dual approach with Kohonen neural network and multivariate modeling","year":2025,"lang":"en","type":"article","venue":"Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Canadian Association of Gastroenterology","keywords":"Chemistry; Multivariate statistics; Self-organizing map; Artificial neural network; Dual (grammatical number); Spectroscopy; Multivariate analysis; Content (measure theory); Chemometrics; Infrared spectroscopy; Biological system; Artificial intelligence; Pattern recognition (psychology); Machine learning; Chromatography; Organic chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002626224,0.000913994,0.001069541,0.0003853859,0.0006935468,0.0004606589,0.0003717884,0.0003282772,0.00006125986],"category_scores_gemma":[0.00008047484,0.0008281894,0.0003055452,0.0009906719,0.0003351042,0.0002221518,0.0002705077,0.0006567951,0.000001239456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002170485,"about_ca_system_score_gemma":0.0001838077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007979599,"about_ca_topic_score_gemma":0.00001152264,"domain_scores_codex":[0.9956506,0.00007371352,0.0007554219,0.001644909,0.00047789,0.001397427],"domain_scores_gemma":[0.9983467,0.00009271555,0.000261877,0.0007754405,0.0001664489,0.0003567908],"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":[0.00110733,0.000242064,0.0009083641,0.0002723953,0.001174387,0.00005122697,0.0001554769,0.0004198671,0.9922886,0.002785194,0.0005670927,0.00002792841],"study_design_scores_gemma":[0.005231452,0.000470184,0.0001394445,0.0001897569,0.001622184,0.0002254159,0.0006264691,0.08898742,0.8977923,0.002710595,0.0009354971,0.001069222],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6134782,0.003792784,0.3707092,0.0009243852,0.0001461944,0.0009508638,0.00009035164,0.0003724123,0.009535572],"genre_scores_gemma":[0.9489667,0.0002986305,0.04840255,0.0007143228,0.0003541475,0.0003002161,0.0002815939,0.0001204418,0.0005614096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3354885,"threshold_uncertainty_score":0.9994169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02102488484790702,"score_gpt":0.2583530798501886,"score_spread":0.2373281950022816,"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."}}