{"id":"W2971408387","doi":"10.1186/s12911-019-0867-z","title":"A privacy-preserving distributed filtering framework for NLP artifacts","year":2019,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; University of Manitoba; National Institutes of Health; Cancer Prevention and Research Institute of Texas","keywords":"Health informatics; Computer science; Artificial intelligence; Natural language processing; Protected health information; Information retrieval; Machine learning; Medicine; Public health; Health policy","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.01341751,0.0009566023,0.001441436,0.002751916,0.003029295,0.005234857,0.003774673,0.003115675,0.00338702],"category_scores_gemma":[0.01516491,0.0007976632,0.002979334,0.002195277,0.002951013,0.00873905,0.006789929,0.003593627,0.001531104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002430676,"about_ca_system_score_gemma":0.004161748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002920989,"about_ca_topic_score_gemma":0.002594605,"domain_scores_codex":[0.9883736,0.003507399,0.001147256,0.002117749,0.004175751,0.0006782436],"domain_scores_gemma":[0.9834547,0.005878846,0.001312539,0.006557236,0.002287212,0.0005094454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006508849,0.0004706737,0.002181629,0.0004478698,0.0002576753,0.001094462,0.001929624,0.1116061,0.02212351,0.4886307,0.008019288,0.3625877],"study_design_scores_gemma":[0.00007066538,0.0001304169,0.0004566555,0.0000653657,0.00009952433,0.000574077,0.0002789754,0.7037386,0.01629095,0.2595068,0.01870733,0.00008071433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001715747,0.00004623991,0.9969332,0.0001636058,0.00001255197,0.00009572491,0.00004729905,0.0005969388,0.000388676],"genre_scores_gemma":[0.1344468,0.0001691697,0.8603066,0.0002684424,0.00008679391,0.000393082,0.0004748407,0.0002115099,0.003642784],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01341751,"threshold_uncertainty_score":0.07095945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03084129199997003,"score_gpt":0.3188505267025306,"score_spread":0.2880092347025606,"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."}}