{"id":"W4398646437","doi":"10.7910/dvn/bki1x3/gkjojn","title":"make_fractionalization_data.R","year":2019,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fractionalization; Geography; Data science; Evolutionary biology; Computer science; Biology; Sociology; Anthropology; Ethnic group","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003570144,0.002700619,0.001903707,0.004629364,0.001013206,0.003828335,0.004753544,0.00246291,0.169611],"category_scores_gemma":[0.02592177,0.001158894,0.001830125,0.006611743,0.0009205592,0.002069282,0.003448622,0.002665577,0.1954313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001528602,"about_ca_system_score_gemma":0.002984341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0106466,"about_ca_topic_score_gemma":0.0156929,"domain_scores_codex":[0.9973936,0.0006650913,0.0003020552,0.0007562041,0.0005128697,0.0003701819],"domain_scores_gemma":[0.9912497,0.003445404,0.0007680535,0.002899835,0.001164754,0.000472219],"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":[0.00005843506,0.00001340341,0.0004513869,0.0005759655,0.00005083307,0.00001421686,0.00001938184,0.000232288,0.00008475107,0.0009969386,0.9956792,0.001823198],"study_design_scores_gemma":[0.0004467857,0.00001792549,0.001631891,0.0003903929,0.00005743997,0.00005081349,0.00003641495,0.0005205693,0.0005143966,0.005672153,0.9906167,0.0000445364],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.0001140748,0.00007427033,0.0003904675,0.0001150753,0.00003596582,0.00001670583,0.9965091,0.001888185,0.0008561116],"genre_scores_gemma":[0.001001576,0.0001140507,0.00151956,0.0002162656,0.00002094894,0.0003065715,0.994188,0.00139371,0.001239368],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.169611,"threshold_uncertainty_score":0.5674054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1993302669156104,"score_gpt":0.4158677941980098,"score_spread":0.2165375272823994,"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."}}