{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.001912402,0.0007976172,0.0009532651,0.01253337,0.001210115,0.002323869,0.0009463094,0.0007929686,0.004311414],"category_scores_gemma":[0.01900209,0.0007851248,0.000825109,0.01008011,0.0003737493,0.002648628,0.002907795,0.0009642288,0.007091911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001186649,"about_ca_system_score_gemma":0.005276539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03369083,"about_ca_topic_score_gemma":0.06048657,"domain_scores_codex":[0.9977434,0.0002949654,0.0003093357,0.0006301128,0.0008522311,0.0001699839],"domain_scores_gemma":[0.9857109,0.003469277,0.001491038,0.002928886,0.005628722,0.0007711095],"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":[0.0002668934,0.0003199864,0.1410624,0.001581695,0.0002472443,0.0006629462,0.003093729,0.008462445,0.02004421,0.00860531,0.2093784,0.6062748],"study_design_scores_gemma":[0.0001395849,0.0001637162,0.2089359,0.000588387,0.0002033282,0.001152974,0.004867161,0.1973032,0.04175848,0.02697991,0.5176479,0.000259483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2106337,0.001822623,0.4571072,0.001587139,0.0005723288,0.002218484,0.2519023,0.04783969,0.02631652],"genre_scores_gemma":[0.183699,0.001036325,0.5520409,0.0002850546,0.000170778,0.001446159,0.251435,0.002358654,0.007527966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9874666,"threshold_uncertainty_score":0.06698948,"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."}}