{"id":"W2597363143","doi":"10.1101/108555","title":"Unmet Needs for Analyzing Biological Big Data: A Survey of 704 NSF Principal Investigators","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Principal (computer security); Workflow; Data science; Data archive; Big data; Data management; Computer science; Publication; Biological data; Political science; Bioinformatics; Data mining; Database; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003550848,0.0006027688,0.0008668117,0.0003489708,0.0002368656,0.0002158333,0.002851367,0.001310428,0.00000622809],"category_scores_gemma":[0.008003336,0.0005413977,0.0002338301,0.0003148759,0.0009762894,0.00001466044,0.003740016,0.0005815426,0.00001003336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006192783,"about_ca_system_score_gemma":0.001895556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002262071,"about_ca_topic_score_gemma":0.00004719138,"domain_scores_codex":[0.9962167,0.0002687003,0.0009998357,0.001120649,0.0005357317,0.0008583992],"domain_scores_gemma":[0.9935717,0.0001280511,0.0008532582,0.003672686,0.001164648,0.0006096598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00028866,0.0003070393,0.1249901,0.001337814,0.0007507669,0.000008127507,0.00001333462,0.00002964549,0.8691503,0.00006189629,0.002919855,0.000142556],"study_design_scores_gemma":[0.001722136,0.000803891,0.3248757,0.0004399983,0.0002057871,5.739803e-8,0.000009203623,0.001301828,0.615025,0.000009427129,0.0539448,0.001662141],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9810494,0.001400614,0.009845964,0.0001652102,0.001431015,0.00103671,0.00501245,0.00004846654,0.00001022227],"genre_scores_gemma":[0.9891391,0.001935083,0.007475413,0.0001298665,0.001005298,0.0000997663,0.0001132646,0.00008339945,0.0000188533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2541253,"threshold_uncertainty_score":0.9999861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1014270074696426,"score_gpt":0.3087143420382056,"score_spread":0.207287334568563,"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."}}