{"id":"W341944981","doi":"10.1023/a:1012763829453","title":"A comparison between diatom-based pH inference models using Artificial Neural Networks (ANN), Weighted Averaging (WA) and Weighted Averaging Partial Least Squares (WA-PLS) regressions","year":2001,"lang":"en","type":"article","venue":"Journal of Paleolimnology","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Jackknife resampling; Mean squared error; Artificial neural network; Statistics; Data set; Bootstrapping (finance); Partial least squares regression; Inference; Computer science; Mathematics; Econometrics; Artificial intelligence","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":[0.003484294,0.0006391798,0.0007154605,0.0004813509,0.0003608774,0.0007810948,0.001112389,0.0006528927,0.0005677281],"category_scores_gemma":[0.007310944,0.0003241999,0.0006282003,0.0005100082,0.0001672273,0.001275053,0.0003516496,0.0006614326,0.0002030687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005395601,"about_ca_system_score_gemma":0.0006867209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009164252,"about_ca_topic_score_gemma":0.009612362,"domain_scores_codex":[0.9994012,0.0003205888,0.00004696524,0.00010903,0.00009432281,0.00002782638],"domain_scores_gemma":[0.9957986,0.00305719,0.000171704,0.0001627881,0.0007672559,0.00004251293],"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":[0.001146048,0.0002834213,0.01646278,0.0001646794,0.0005555435,0.00004418983,0.0001043793,0.7296374,0.004940211,0.001805883,0.000944315,0.2439111],"study_design_scores_gemma":[0.000009215368,0.00004062612,0.001073371,0.000003436498,0.00003605867,0.000006570939,0.000006386916,0.9977565,0.0007014879,0.0002870091,0.0000730479,0.00000623386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5074953,0.0008563843,0.4868906,0.0004955989,0.0001308612,0.00007245778,0.0003037651,0.001029045,0.002725904],"genre_scores_gemma":[0.919593,0.0002891874,0.07834319,0.00009707594,0.0000398701,0.00006505026,0.0002549778,0.00006291529,0.001254714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009164252,"threshold_uncertainty_score":0.01842695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.063200032439049,"score_gpt":0.310823184685635,"score_spread":0.247623152246586,"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."}}