{"id":"W2795493637","doi":"10.1371/journal.pone.0202223","title":"Automatically assembling a full census of an academic field","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Census; Directory; Workforce; American Community Survey; Field (mathematics); Computer science; Data science; World Wide Web; Population; Sociology; Mathematics; Political science; Demography; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002717389,0.00006332728,0.0001650586,0.00008790304,0.00004981129,0.00004239086,0.0007432817,0.00006608057,0.00002429413],"category_scores_gemma":[0.0003095808,0.0000577808,0.00002916557,0.0003135964,0.00003071447,0.0003007908,0.0001685544,0.0001295182,0.00005541197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006633813,"about_ca_system_score_gemma":0.0000278576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001861383,"about_ca_topic_score_gemma":0.000005932438,"domain_scores_codex":[0.9990943,0.00004007433,0.0002059497,0.0002124122,0.0002850709,0.0001621819],"domain_scores_gemma":[0.9990908,0.000119823,0.00007853311,0.0005208054,0.0001121181,0.00007790123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004524141,0.002635997,0.004056787,0.0002614998,0.0007239962,0.00003037494,0.003488222,0.00001231625,0.8501936,0.02068607,0.002257322,0.1156086],"study_design_scores_gemma":[0.0002083802,0.0006935343,0.001127206,0.0002589473,0.0001007587,0.000003608272,0.00003870677,0.7863923,0.2093151,0.001573937,0.00009233449,0.0001951457],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9433891,0.00002080096,0.05447603,0.0008200978,0.00002612333,0.00003230469,0.000004577724,0.0001349961,0.001096004],"genre_scores_gemma":[0.8108202,0.000004549362,0.188771,0.0002096301,0.0001201418,0.000001920559,0.000003548468,0.000003792083,0.00006522069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.78638,"threshold_uncertainty_score":0.2356233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07600938300478349,"score_gpt":0.2914424414918625,"score_spread":0.2154330584870791,"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."}}