{"id":"W2031989156","doi":"10.2481/dsj.2.25","title":"Data integration and knowledge discovery in biomedical databases. Reliable information from unreliable sources","year":2003,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Scope (computer science); Computer science; Data science; Usability; Metadata; Transparency (behavior); Open data; Reuse; Implementation; World Wide Web; Data discovery; Data publishing; Publishing; Software engineering; Political science; Engineering","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","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009279463,0.0001363507,0.0002102831,0.0004363615,0.001773008,0.0002811909,0.001959139,0.0001049144,0.0002932659],"category_scores_gemma":[0.008379996,0.0001061065,0.000008638024,0.001120645,0.0005607523,0.02142639,0.001526225,0.001204732,0.0002505665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002568796,"about_ca_system_score_gemma":0.0034468,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006725489,"about_ca_topic_score_gemma":0.007182514,"domain_scores_codex":[0.9968604,0.0003112753,0.00105772,0.0004868684,0.0006409665,0.0006427743],"domain_scores_gemma":[0.9967422,0.0006503429,0.0004001916,0.001601444,0.0002583877,0.0003474572],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001655665,0.0004155617,0.6449422,0.0002440427,0.00001861051,0.00003016296,0.0207428,0.00006320696,0.00203891,0.01804375,0.2351105,0.07818463],"study_design_scores_gemma":[0.00054743,0.00008433536,0.01476497,0.00153197,0.00002356034,0.00004109928,0.0609754,0.1445456,0.0003451213,0.00424817,0.772508,0.0003842963],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9100146,0.002224475,0.05944523,0.003495337,0.008950341,0.001187014,0.009279273,0.00008636026,0.005317365],"genre_scores_gemma":[0.9623731,0.002681874,0.02550796,0.00125341,0.000813539,0.00001865948,0.007174637,0.0000220284,0.0001548111],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6301773,"threshold_uncertainty_score":0.9999728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2754938637313639,"score_gpt":0.5016500590355036,"score_spread":0.2261561953041397,"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."}}