{"id":"W3170119884","doi":"10.1101/2021.06.14.21258917","title":"Gender Balance and Readability of COVID-19 Scientific Publishing: A Quantitative Analysis of 90,000 Preprint Manuscripts","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Academic Publishing and Open Access","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Preprint; Publishing; Gender balance; Readability; Harm; Construct (python library); Pandemic; Quality (philosophy); Coronavirus disease 2019 (COVID-19); Psychology; Public relations; Political science; Sociology; Medicine; Social psychology; Law; Computer science; Disease; Infectious disease (medical specialty); Gender studies","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","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03808894,0.0004007879,0.001920007,0.002139087,0.0002433357,0.005990084,0.005672934,0.0006408499,0.0008424292],"category_scores_gemma":[0.1105813,0.0003206709,0.0006066565,0.006165715,0.001484767,0.002715937,0.006058141,0.001400488,0.00000417406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001713095,"about_ca_system_score_gemma":0.001669785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002503811,"about_ca_topic_score_gemma":0.000747604,"domain_scores_codex":[0.987932,0.00207923,0.002533592,0.002902953,0.004091795,0.0004603928],"domain_scores_gemma":[0.98605,0.004191874,0.002784953,0.003566323,0.002827864,0.0005790592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007037853,0.0001571579,0.9737666,0.0002888902,0.0007652025,0.00001257106,0.01113706,0.00529847,0.0005894743,0.001434523,0.004926202,0.001553528],"study_design_scores_gemma":[0.0001984531,0.00002551747,0.9076391,0.0001195184,0.0007180315,0.00000456128,0.008906174,0.02824131,0.001856293,0.0477792,0.003978249,0.0005335613],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9737017,0.001620435,0.01780158,0.002137468,0.00106518,0.0004639679,0.0006412482,0.00004346626,0.002524962],"genre_scores_gemma":[0.9953408,0.00007011916,0.003408652,0.0002281079,0.00003114859,0.00003867783,0.0001468763,0.00001653825,0.0007191412],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07249233,"threshold_uncertainty_score":0.9999245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2640110442343268,"score_gpt":0.4394690292971488,"score_spread":0.175457985062822,"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."}}