{"id":"W2464696916","doi":"10.1093/jssam/smaa042","title":"Estimating the Size and Distribution of Networked Populations with Snowball Sampling","year":2020,"lang":"en","type":"preprint","venue":"Journal of Survey Statistics and Methodology","topic":"Census and Population Estimation","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Snowball sampling; Sample size determination; Inference; Computer science; Population; Sampling (signal processing); Population size; Graph; Sample (material); Selection (genetic algorithm); Statistics; Sampling design; Econometrics; Mathematics; Theoretical computer science; Machine learning; Artificial intelligence; Demography; Telecommunications","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005004114,0.000163995,0.000644176,0.00003918966,0.0001115225,0.00003647056,0.00009735829,0.0001364627,0.000006281246],"category_scores_gemma":[0.01361417,0.0001088845,0.00003963186,0.00009253312,0.0001267859,0.00003410179,0.0001180148,0.0004837913,4.100344e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002298947,"about_ca_system_score_gemma":0.00008219371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002363677,"about_ca_topic_score_gemma":0.000250735,"domain_scores_codex":[0.9972056,0.001428699,0.0008975845,0.0001470271,0.0001985647,0.0001225405],"domain_scores_gemma":[0.9847422,0.01254387,0.001911472,0.0001356716,0.0005900256,0.00007682662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002232655,0.0002744214,0.4043017,0.004063246,0.001558309,0.00004409431,0.006247371,0.1655704,0.000291851,0.2988825,0.007685775,0.1088476],"study_design_scores_gemma":[0.0003210817,0.0001363702,0.5807247,0.0001789923,0.0003053357,0.00007888116,0.00003493851,0.05421696,0.000002989647,0.3638379,0.00004998291,0.000111875],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1593477,0.0001787591,0.838865,0.0004796982,0.0003511659,0.0001500773,0.0006191503,0.000004504617,0.000004016667],"genre_scores_gemma":[0.3385229,0.00005488702,0.6611394,0.00002365512,0.0001102763,0.000001316081,0.0001324576,0.00001202633,0.000003157373],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1791752,"threshold_uncertainty_score":0.9946946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5549742675041466,"score_gpt":0.474974966433552,"score_spread":0.07999930107059461,"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."}}