{"id":"W4403162617","doi":"10.1093/imaiai/iaae023","title":"Statistical inference for sketching algorithms","year":2024,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Sketch; Inference; Computer science; Algorithm; Set (abstract data type); Data set; Sampling (signal processing); Statistical inference; Mathematics; Statistics; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02545209,0.001486576,0.002900152,0.003928154,0.001188219,0.003737683,0.0036815,0.002619954,0.008806612],"category_scores_gemma":[0.1855145,0.001811524,0.002370524,0.002775711,0.007047286,0.009012167,0.005141574,0.005484671,0.001202025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002044029,"about_ca_system_score_gemma":0.001863984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001775014,"about_ca_topic_score_gemma":0.001431346,"domain_scores_codex":[0.9872937,0.007325861,0.0007205178,0.002344645,0.001911819,0.0004034833],"domain_scores_gemma":[0.8346241,0.1395432,0.005959961,0.01344472,0.005139973,0.001288078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001391708,0.00005764132,0.002450469,0.0002613711,0.0001214153,0.0001054341,0.000221675,0.1897127,0.0009174591,0.7437812,0.002005174,0.06022625],"study_design_scores_gemma":[0.0000425961,0.00004096228,0.0003576773,0.0001010482,0.00001828163,0.00005813863,0.00002593095,0.5270714,0.0006052174,0.4701967,0.001451339,0.00003080085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00357961,0.0001707854,0.9952859,0.000153457,0.00001895295,0.00005040237,0.00007387538,0.0001039081,0.0005631399],"genre_scores_gemma":[0.2190872,0.0009084708,0.7752341,0.0002992744,0.0002337528,0.0006736252,0.0008437618,0.000246358,0.002473488],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02545209,"threshold_uncertainty_score":0.1346051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.019625975934582,"score_gpt":0.3275753939502494,"score_spread":0.3079494180156674,"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."}}