{"id":"W2952156265","doi":"10.1371/journal.pcbi.1005755","title":"Unmet needs for analyzing biological big data: A survey of 704 NSF principal investigators","year":2017,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":157,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Principal (computer security); Workflow; Data science; Data management; Big data; Data archive; Computer science; Publication; Work (physics); Political science; Engineering; Data mining; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0009767395,0.0001659903,0.0003057924,0.0001242876,0.0002219833,0.00004106741,0.001098623,0.0002869655,0.000007332206],"category_scores_gemma":[0.004965262,0.0001322466,0.00007551587,0.00009333187,0.000966427,0.000007158865,0.0008848974,0.0001085386,0.000007936964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001087273,"about_ca_system_score_gemma":0.0003302235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008614257,"about_ca_topic_score_gemma":0.00009241722,"domain_scores_codex":[0.9984993,0.0001475873,0.0004670936,0.0003705109,0.0001682726,0.0003472555],"domain_scores_gemma":[0.9981368,0.0002716734,0.0002950334,0.0006796051,0.000437827,0.0001790263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005775872,0.0004718872,0.8238714,0.0002126469,0.0008339283,0.000001761887,0.00009728922,0.0002856208,0.1317409,0.001635889,0.002966782,0.0373043],"study_design_scores_gemma":[0.00354681,0.003332059,0.8822469,0.00006507845,0.00008409945,0.00001474627,0.00008415381,0.03103336,0.04346661,0.007361069,0.0278202,0.0009448864],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.969198,0.0001869131,0.02796583,0.0004262826,0.0002988014,0.0003188436,0.001465123,0.000009791483,0.0001304282],"genre_scores_gemma":[0.982989,0.0001275681,0.009130311,0.0002059044,0.0003258113,0.00001718674,0.007144246,0.00001149318,0.00004845174],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08827426,"threshold_uncertainty_score":0.5944241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2060724053949253,"score_gpt":0.3698108616315151,"score_spread":0.1637384562365898,"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."}}