{"id":"W39904068","doi":"","title":"A simple sketching algorithm for entropy estimation over streaming data.","year":2013,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Rényi entropy; Estimator; Mathematics; Entropy (arrow of time); Maximum entropy probability distribution; Min entropy; Joint entropy; Entropy estimation; Shannon's source coding theorem; Streaming algorithm; Computation; Upper and lower bounds; Entropy rate; Applied mathematics; Algorithm; Principle of maximum entropy; Statistics; Joint quantum entropy; Maximum entropy thermodynamics; Mathematical analysis","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":[0.0002578376,0.0001612653,0.0001397202,0.0001311949,0.0001330752,0.0008885598,0.001163695,0.00005193686,0.0001556188],"category_scores_gemma":[0.0005012244,0.0001574168,0.00001796541,0.00008338628,0.00007857991,0.0009755577,0.0003676044,0.0001163458,0.00006168478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000039534,"about_ca_system_score_gemma":0.00006538631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002842555,"about_ca_topic_score_gemma":0.00003547802,"domain_scores_codex":[0.9986047,0.0000369915,0.0003354569,0.0004909613,0.0003114235,0.0002205226],"domain_scores_gemma":[0.9984549,0.0005224516,0.0001537255,0.0004892339,0.0002982066,0.0000814324],"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":[0.000002874065,0.00003345032,0.000008795458,0.000002495448,0.000008815592,0.000001723862,0.00008325766,0.00001725157,0.0001342856,0.4560744,0.001129074,0.5425036],"study_design_scores_gemma":[0.00001921262,0.00008036389,0.0001026779,0.00002264649,0.000003808596,0.000003031879,0.00007954017,0.6555883,0.0009859368,0.3426429,0.0003571319,0.0001144446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007041552,0.000004114479,0.9964786,0.0006440799,0.0002951734,0.0002945998,0.001096543,0.0001175448,0.0003651971],"genre_scores_gemma":[0.272797,0.00003122575,0.7262564,0.0001533315,0.00007240252,0.00004791821,0.0005889151,0.000008444783,0.00004433798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.655571,"threshold_uncertainty_score":0.8568403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1188387014756424,"score_gpt":0.3807147191308058,"score_spread":0.2618760176551633,"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."}}