{"id":"W4242907897","doi":"10.1038/npre.2010.4270.1","title":"Formulating MEDLINE queries for article retrieval based on PubMed exemplars","year":2010,"lang":"en","type":"preprint","venue":"Nature Precedings","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health","keywords":"Computer science; Information retrieval; Search engine indexing; Set (abstract data type); Bigram; Task (project management); Result set; Process (computing); Function (biology); Recall; Natural language processing","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007045816,0.0003499761,0.0003449138,0.00008359225,0.0001549716,0.00007886735,0.0004465186,0.003211185,0.00001215225],"category_scores_gemma":[0.004458155,0.000300558,0.000247376,0.00008552194,0.0001627761,0.000002860379,0.000359916,0.001847015,0.000001402141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000390995,"about_ca_system_score_gemma":0.0001357116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004918504,"about_ca_topic_score_gemma":0.00002523626,"domain_scores_codex":[0.998067,0.00003214817,0.0003237838,0.0007559714,0.0002995956,0.0005215204],"domain_scores_gemma":[0.9987203,0.0001570562,0.0002366908,0.0005165745,0.0002051404,0.0001641932],"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":[0.006684257,0.0006265268,0.004156652,0.001391238,0.0004660661,0.00001258319,0.0005086596,0.0007089508,0.7724109,0.0007679627,0.04483414,0.167432],"study_design_scores_gemma":[0.001907481,0.0007889348,0.002432502,0.0002354966,0.000115707,0.000008131452,0.00005495546,0.009371836,0.8674164,0.003083682,0.1136953,0.0008895345],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9839031,0.0007538581,0.005862743,0.004955242,0.002452318,0.00098408,0.0002009977,0.0001470891,0.0007405798],"genre_scores_gemma":[0.9651184,0.00002793292,0.03129186,0.001162475,0.001260811,0.000192037,0.0005643081,0.00005413004,0.0003280556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1665425,"threshold_uncertainty_score":0.9999446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01489261622583352,"score_gpt":0.2964808509958263,"score_spread":0.2815882347699928,"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."}}