{"id":"W2047174744","doi":"10.1016/s1296-2074(03)00024-4","title":"Near-infrared spectroscopic imaging in art conservation: investigation of drawing constituents","year":2003,"lang":"en","type":"article","venue":"Journal of Cultural Heritage","topic":"Cultural Heritage Materials Analysis","field":"Arts and Humanities","cited_by":93,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Winnipeg; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Remote sensing; Instrumentation (computer programming); Conservation; Principal component analysis; Hyperspectral imaging; Imaging spectroscopy; Spectral resolution; Near-infrared spectroscopy; Computer science; Materials science; Optics; Computer graphics (images); Archaeology; Geology; Artificial intelligence; Environmental science; Physics; Geography; Spectral line","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002070957,0.0001774429,0.000143709,0.0007613744,0.0005016917,0.0005491286,0.0003335311,0.0005201701,0.002705527],"category_scores_gemma":[0.0004504865,0.0002301922,0.0001162794,0.0006275258,0.0003501729,0.0008580151,0.0002191025,0.0004299767,0.0003521216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000964373,"about_ca_system_score_gemma":0.0001327006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005805499,"about_ca_topic_score_gemma":0.001352441,"domain_scores_codex":[0.9999129,0.00001849106,0.000002275384,0.00002163911,0.0000309439,0.0000137988],"domain_scores_gemma":[0.9997781,0.00008912814,0.00002929608,0.00001910003,0.00006459288,0.00001978995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003921423,0.0001391486,0.005261153,0.0001181849,0.0000139533,0.0001441937,0.0002078864,0.0008555836,0.9421897,0.001018567,0.0002522358,0.04940732],"study_design_scores_gemma":[0.00002631003,0.0002462018,0.06379083,0.00003464515,0.0001000278,0.001225422,0.0007825042,0.02155397,0.9066213,0.001218103,0.004372874,0.00002782365],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9496676,0.001392151,0.03435295,0.0001800118,0.00002676283,0.00003136669,0.00009094013,0.00008187348,0.01417632],"genre_scores_gemma":[0.9802575,0.0008670315,0.01570132,0.00004927623,0.00001560489,0.00001347865,0.00004285033,0.0000411826,0.003011724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002705527,"threshold_uncertainty_score":0.009050846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03101469721108078,"score_gpt":0.2465126244801482,"score_spread":0.2154979272690674,"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."}}