{"id":"W4399003852","doi":"10.7910/dvn/x27dse","title":"Text data for comparing the language used in Wikipedia, the DiabeticConnect Forum, and Research Articles","year":2019,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Computer science; Information retrieval; World Wide Web; Library science; Data science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004159631,0.0001074206,0.0001668079,0.0001083995,0.0006762483,0.000522941,0.001641876,0.0001207097,0.0008435975],"category_scores_gemma":[0.003316928,0.00007172889,0.00001863005,0.0004558387,0.000447814,0.0004044752,0.000610257,0.000362339,0.002420257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007852279,"about_ca_system_score_gemma":0.0004728507,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.008137085,"about_ca_topic_score_gemma":0.1155453,"domain_scores_codex":[0.9978564,0.000712537,0.0001995603,0.0003629713,0.0004956496,0.0003728676],"domain_scores_gemma":[0.9959572,0.002095533,0.0000958946,0.001684574,0.0001095331,0.00005727901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001552632,0.00003382966,0.0006053792,0.00002433379,0.0000105714,6.897049e-7,0.003973376,0.000001894585,0.000003971877,0.000862054,0.9938256,0.0006428345],"study_design_scores_gemma":[0.0002248302,0.00001174567,0.0002576946,0.00003176403,0.00002184847,1.713757e-7,0.09137844,0.0002445509,0.000003420367,0.0001490958,0.9075866,0.00008979809],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.008374736,0.00002134047,0.000007652556,0.001466481,0.0006310501,0.001356217,0.9878737,0.00001173853,0.0002571342],"genre_scores_gemma":[0.02732312,0.0003359977,0.00004474025,0.0004411415,0.0005847978,0.0001246009,0.9707767,0.00001128039,0.0003576592],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1074082,"threshold_uncertainty_score":0.9984678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1286646354725352,"score_gpt":0.4146913308654475,"score_spread":0.2860266953929123,"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."}}