{"id":"W2166648275","doi":"10.2196/medinform.4959","title":"NHash: Randomized N-Gram Hashing for Distributed Generation of Validatable Unique Study Identifiers in Multicenter Research","year":2015,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke; National Heart, Lung, and Blood Institute","keywords":"Identifier; Computer science; Hash function; Unique identifier; n-gram; Cryptography; Universal hashing; Theoretical computer science; Hash table; Data mining; Computer security; Computer network; Artificial intelligence; Double hashing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01188073,0.0008285961,0.0009135398,0.00122869,0.001265685,0.001345632,0.002536882,0.001187175,0.008436088],"category_scores_gemma":[0.03860968,0.0006672413,0.0008139419,0.001313522,0.001840809,0.002698658,0.005504002,0.001122079,0.004071686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054563,"about_ca_system_score_gemma":0.00303753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006604015,"about_ca_topic_score_gemma":0.0008861916,"domain_scores_codex":[0.9886323,0.00632994,0.0009019132,0.001361874,0.0023068,0.0004671845],"domain_scores_gemma":[0.9752253,0.009261378,0.003188506,0.009191133,0.002179941,0.0009537417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006663168,0.0005170885,0.009282849,0.001313965,0.0002926173,0.001349865,0.002610948,0.03153176,0.06257721,0.07198426,0.02678402,0.7850922],"study_design_scores_gemma":[0.002971551,0.004141154,0.006202728,0.0004229437,0.0002548321,0.002772497,0.001345146,0.5620266,0.1621384,0.1558986,0.1013382,0.0004874372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01992037,0.0003005948,0.9687275,0.0003839094,0.0002652925,0.001431745,0.0005771688,0.00669698,0.001696426],"genre_scores_gemma":[0.2049924,0.0001435155,0.7883766,0.0003060484,0.0001293343,0.0020453,0.0008745719,0.0004320153,0.002700166],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01188073,"threshold_uncertainty_score":0.06283206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1453992460823107,"score_gpt":0.4347469399101895,"score_spread":0.2893476938278788,"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."}}