{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007363533,0.00007455929,0.0001127511,0.00009758327,0.00009352503,0.0006111894,0.000396752,0.00003627398,0.000006425302],"category_scores_gemma":[0.0004149286,0.00004283641,0.0000571282,0.0001398481,0.00003661837,0.002643498,0.00009615078,0.0001972931,0.000004110183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001890847,"about_ca_system_score_gemma":0.0002014162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003410111,"about_ca_topic_score_gemma":4.590918e-7,"domain_scores_codex":[0.9992229,0.00004343009,0.0003771897,0.00005372804,0.0001863827,0.0001163376],"domain_scores_gemma":[0.9990845,0.0004045203,0.0001487779,0.0001221883,0.0001740626,0.00006589973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003150248,0.000003002714,0.00002253118,0.00003049931,0.000008606055,7.332691e-7,0.001058995,0.00001589383,0.00003004475,0.3730684,0.0005932025,0.6251649],"study_design_scores_gemma":[0.0003288604,0.0001647689,0.001291524,0.0002722083,0.00001918457,0.0002004535,0.00004961481,0.5618191,0.0005041946,0.3961087,0.03909627,0.0001450375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000931181,0.0001880639,0.9955833,0.00204077,0.0006572054,0.00007892795,0.000007897384,0.00001632401,0.0004963221],"genre_scores_gemma":[0.4537921,0.0000959825,0.5452616,0.0007456988,0.00007012228,0.000003040598,5.779596e-7,0.000002316827,0.0000286404],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6250199,"threshold_uncertainty_score":0.5893714,"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."}}