{"id":"W4213450832","doi":"10.12688/f1000research.109080.1","title":"Recommendations for the formatting of Variant Call Format (VCF) files to make plant genotyping data FAIR","year":2022,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Research Data Management Practices","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Horizon 2020 Framework Programme; German Network for Bioinformatics Infrastructure; Bundesministerium für Bildung und Forschung; European Commission","keywords":"Disk formatting; Metadata; Computer science; Information retrieval; World Wide Web; Annotation; Interoperability; Data element; Artificial intelligence","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.1164609,0.002052844,0.001699972,0.01113188,0.002684931,0.009575552,0.007398909,0.009647724,0.05488723],"category_scores_gemma":[0.3507473,0.002762147,0.003049417,0.008889028,0.00394959,0.0120231,0.006246972,0.009602429,0.05848852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003910436,"about_ca_system_score_gemma":0.01231067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009272997,"about_ca_topic_score_gemma":0.006391248,"domain_scores_codex":[0.9241129,0.03644256,0.01738652,0.003287475,0.01646074,0.002309784],"domain_scores_gemma":[0.6324204,0.1694556,0.02515808,0.05515953,0.109734,0.008072491],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004787547,0.0003257738,0.002729346,0.002756856,0.00008382552,0.0007055039,0.003215076,0.002630857,0.005296871,0.0237951,0.7096069,0.2483751],"study_design_scores_gemma":[0.0001743726,0.0001148763,0.001775829,0.004304077,0.00006352058,0.000520515,0.0007001343,0.001456109,0.004286426,0.01306793,0.9732996,0.0002367019],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005686414,0.005106845,0.7209152,0.06306334,0.01431104,0.01453419,0.03915216,0.0587435,0.07848734],"genre_scores_gemma":[0.01095163,0.004020189,0.8529903,0.02192017,0.002224595,0.01394198,0.03611183,0.02034995,0.03748936],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9926011,"threshold_uncertainty_score":0.6159115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4089725583043259,"score_gpt":0.4605710201384414,"score_spread":0.05159846183411543,"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."}}