{"id":"W4387775258","doi":"10.3390/polym15204147","title":"Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning","year":2023,"lang":"en","type":"article","venue":"Polymers","topic":"Wood and Agarwood Research","field":"Chemistry","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Near-infrared spectroscopy; Ranking (information retrieval); Artificial intelligence; Spectroscopy; Machine learning; Materials science; Feature (linguistics); Boosting (machine learning); Computer science; Analytical Chemistry (journal); Environmental science; Pattern recognition (psychology); Remote sensing; Optics; Chemistry; Geology; Physics; Chromatography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003455501,0.0001743284,0.0003318623,0.00006785908,0.0002179043,0.0000718924,0.0001823686,0.000100183,0.0003376363],"category_scores_gemma":[0.00009754155,0.0001622368,0.00008291593,0.0002218459,0.0001350774,0.00009757941,0.0001118627,0.0003060368,0.00001287394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000329759,"about_ca_system_score_gemma":0.00008633945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007561669,"about_ca_topic_score_gemma":0.00001049432,"domain_scores_codex":[0.998475,0.00008738491,0.000294472,0.0002933605,0.0003394948,0.0005102759],"domain_scores_gemma":[0.9992455,0.0002041795,0.00013022,0.0002438101,0.00003635246,0.0001399671],"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":[0.0002197198,0.00004737513,0.03350993,0.0002645147,0.0001147175,0.0000252516,0.0008053339,0.0005540806,0.9628277,0.00004140888,0.0000239148,0.001566046],"study_design_scores_gemma":[0.004669613,0.0001187247,0.003607265,0.0001512685,0.0000538896,0.00001545586,0.002127482,0.06477448,0.9229027,0.0001564154,0.000886749,0.000535972],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988693,0.0007532791,0.0001635496,0.0001984461,0.00003655447,0.00007989606,0.00004319147,0.0001287346,0.009903321],"genre_scores_gemma":[0.9931749,0.00005059445,0.00009383184,0.00003073475,0.00006878703,0.00000834924,0.00002365745,0.00003649669,0.006512633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06422041,"threshold_uncertainty_score":0.6615824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03527415218095097,"score_gpt":0.3097141567739806,"score_spread":0.2744400045930296,"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."}}