{"id":"W6910593052","doi":"10.48448/hw0j-c575","title":"Methodological improvements in uncertain classification of individual-level demographic measurements: Improving reliability of inferences from citizen-science and field data","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reliability (semiconductor); Field (mathematics); Sample (material); Identification (biology); Variety (cybernetics); Population; Inference","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2568567,0.001288117,0.001098779,0.004341132,0.00209576,0.006741965,0.004781594,0.00224529,0.003094774],"category_scores_gemma":[0.5679766,0.001206488,0.00158722,0.005234234,0.003580968,0.0038874,0.007840699,0.003719209,0.001452162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002528425,"about_ca_system_score_gemma":0.004929363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009478677,"about_ca_topic_score_gemma":0.01761519,"domain_scores_codex":[0.7053518,0.2367594,0.01518235,0.01717942,0.02437017,0.001156779],"domain_scores_gemma":[0.4214054,0.3702225,0.03770748,0.09716132,0.07184651,0.001656603],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008666415,0.0004250346,0.2216292,0.002945557,0.002037524,0.0004195507,0.01500102,0.03238041,0.01165181,0.05462801,0.02406247,0.6339527],"study_design_scores_gemma":[0.0005177398,0.001015854,0.1934027,0.003826705,0.001464444,0.001096171,0.006053231,0.4333509,0.04653437,0.1961028,0.1157843,0.0008506853],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01777605,0.0003022146,0.9762175,0.0016342,0.000241524,0.000554061,0.0004949527,0.0007073273,0.002072082],"genre_scores_gemma":[0.158223,0.0001578179,0.8377588,0.0008518524,0.0001979439,0.001367289,0.0004420062,0.0003570904,0.0006441778],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7431433,"threshold_uncertainty_score":0.916428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.47205296216095,"score_gpt":0.4204237462777127,"score_spread":0.05162921588323732,"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."}}