{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.02267485,0.0004289857,0.0009065742,0.002150698,0.0001654221,0.0001825171,0.004406292,0.000374791,0.0003002062],"category_scores_gemma":[0.02451205,0.0003665156,0.00004706036,0.005777814,0.005912231,0.0007198466,0.002743821,0.0005452041,0.000002582312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002517528,"about_ca_system_score_gemma":0.003339562,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01258992,"about_ca_topic_score_gemma":0.00629034,"domain_scores_codex":[0.9913155,0.0006410906,0.001255811,0.002312454,0.003799323,0.0006758665],"domain_scores_gemma":[0.9933894,0.001153115,0.001641047,0.002453457,0.001147493,0.0002154516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0000484503,0.0005833608,0.1927564,0.0003426757,0.00006468771,0.000002708695,0.0003495034,0.00001275798,0.7121368,0.0003835399,0.001037343,0.09228176],"study_design_scores_gemma":[0.003437671,0.0009584923,0.8672314,0.003048114,0.000437815,0.000005004615,0.004177452,0.03584829,0.07115766,0.01072349,0.000845718,0.002128838],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8765715,0.004406114,0.04773433,0.001029181,0.00253146,0.00688713,0.01269302,0.000495207,0.04765205],"genre_scores_gemma":[0.8269162,0.0001337758,0.1720584,0.0001034644,0.00005432366,0.00003144992,0.0004361104,0.00009452744,0.0001717397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6744751,"threshold_uncertainty_score":0.9998787,"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."}}