{"id":"W2091214390","doi":"10.1109/tkde.2012.220","title":"Bias Correction in a Small Sample from Big Data","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Sample size determination; Computer science; Sampling bias; Big data; Sample (material); Simple random sample; Population size; Sampling (signal processing); Statistics; Reciprocal; Population; Point estimation; Data mining; Mathematics; Telecommunications","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":[0.0002017402,0.0001440873,0.0001715052,0.0001596882,0.00005942028,0.00003768162,0.0003455977,0.00003488257,0.0000842236],"category_scores_gemma":[0.000004628803,0.000151624,0.00002638959,0.0002796486,0.00001050491,0.0003379993,0.00002428931,0.0002190635,0.00001782021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002032066,"about_ca_system_score_gemma":0.00001469365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001771138,"about_ca_topic_score_gemma":0.000915329,"domain_scores_codex":[0.9992189,0.00002390862,0.0001851089,0.0003113101,0.00004351863,0.0002171944],"domain_scores_gemma":[0.9986143,0.0002844278,0.00002676073,0.0009817338,0.00001237402,0.00008040761],"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":[0.00001683013,0.0005624874,0.008457338,0.00001660068,0.0001850858,4.823119e-7,0.0005007351,0.003186948,0.0008408173,0.0001110594,0.002225028,0.9838966],"study_design_scores_gemma":[0.0005716198,0.00003060772,0.005730016,0.0001662203,0.0002216406,0.000001522991,0.000171401,0.9165331,0.004123494,0.0001389943,0.07173528,0.0005760954],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02976199,0.0003158721,0.9678766,0.000007196609,0.0007925911,0.00008691838,0.000843008,0.00009090141,0.0002249026],"genre_scores_gemma":[0.9943161,0.00003706256,0.004241915,0.000004113786,0.0004639294,0.00001668682,0.0008527008,0.00002041213,0.00004707208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9833205,"threshold_uncertainty_score":0.6183048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1054743786026927,"score_gpt":0.291973674795889,"score_spread":0.1864992961931962,"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."}}