{"id":"W4405400545","doi":"10.1007/s11222-024-10546-x","title":"Optimal subsampling for generalized additive models on large-scale datasets","year":2024,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scale (ratio); Generalized additive model; Mathematics; Computer science; Applied mathematics; Artificial intelligence; Statistics; Geography; Cartography","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":[],"consensus_categories":[],"category_scores_codex":[0.0002721198,0.0001195473,0.0001276601,0.00003359528,0.0002379827,0.0002598538,0.0002029275,0.00003805008,0.000006780572],"category_scores_gemma":[0.00004946993,0.0001118853,0.00002572131,0.00009207596,0.00002258153,0.00008774505,0.0002046958,0.0001074367,0.000003331071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000105401,"about_ca_system_score_gemma":0.00002933468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004787626,"about_ca_topic_score_gemma":0.000001484235,"domain_scores_codex":[0.9990202,0.00001868273,0.0001606665,0.000410709,0.0001028137,0.0002869164],"domain_scores_gemma":[0.9992432,0.0004231585,0.00003735267,0.0001742665,0.00005729179,0.00006470332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009568301,0.00002933731,0.000003612166,0.0001665232,0.00003277836,0.00004091576,0.001184058,0.05559049,0.0001146704,0.8737173,0.02184409,0.04726666],"study_design_scores_gemma":[0.0001733523,0.00004652758,0.00001286653,0.00006445727,0.000008548285,0.0000085119,0.00004619973,0.9287195,0.0001806708,0.04759181,0.02301222,0.0001353938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001926962,0.0001213671,0.9947343,0.0002728875,0.0002377301,0.0001087907,0.001683323,0.0001032298,0.0008113533],"genre_scores_gemma":[0.3103574,0.00001293851,0.6884874,0.0002103292,0.0001567665,0.000008548017,0.0005514655,0.000005243943,0.0002098996],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.873129,"threshold_uncertainty_score":0.4562551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02585760065877823,"score_gpt":0.2810727950670061,"score_spread":0.2552151944082279,"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."}}