{"id":"W4388931364","doi":"10.3389/fgene.2023.1269255","title":"Improving predictive ability in sparse testing designs in soybean populations","year":2023,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Soybean genetics and cultivation","field":"Agricultural and Biological Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Plant Biotechnology Institute","funders":"University of Florida","keywords":"Set (abstract data type); Sample size determination; Inbred strain; Biology; Biotechnology; Computer science; Statistics; Mathematics; Genetics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003738145,0.0001001248,0.000129476,0.00006510148,0.00005458862,0.00002569195,0.0001445854,0.00009477376,0.000007410049],"category_scores_gemma":[0.0002159054,0.00005633532,0.00002485664,0.00137432,0.0000365778,0.00004434495,0.00004570251,0.0001283846,0.000003688973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009373669,"about_ca_system_score_gemma":0.00001325879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003522595,"about_ca_topic_score_gemma":0.002117643,"domain_scores_codex":[0.9989092,0.00008576138,0.0002953262,0.0002814103,0.0001342641,0.0002940368],"domain_scores_gemma":[0.9997206,0.00008185081,0.00006087132,0.00006021403,0.00003412825,0.00004235685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000724703,0.00003927953,0.9225776,0.000003637337,9.674419e-7,0.000003095641,0.0004046762,0.00608623,0.01914054,0.000005068578,0.0001292675,0.05160236],"study_design_scores_gemma":[0.0001363632,0.00006785709,0.8858964,0.00001888688,0.00000193855,2.200077e-7,0.001452513,0.1090897,0.0004140599,0.002778567,0.00003728658,0.0001062632],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9987094,0.0001097537,0.0002968182,0.0001469257,0.0002638692,0.0003190027,0.00001582574,0.00004020441,0.00009822717],"genre_scores_gemma":[0.9918388,0.00002229743,0.007944009,0.00002353219,0.00006810313,0.00003184614,0.00004930998,0.000001608286,0.00002046665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1030034,"threshold_uncertainty_score":0.2297288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07934033798128533,"score_gpt":0.2532546341516896,"score_spread":0.1739142961704043,"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."}}