{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003857875,0.001933609,0.002310852,0.01191699,0.00133394,0.004467459,0.001861797,0.002504275,0.01306076],"category_scores_gemma":[0.03171526,0.00109722,0.002226376,0.006463361,0.0007560877,0.006328223,0.002942056,0.001150114,0.005352737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001796974,"about_ca_system_score_gemma":0.001889092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003519271,"about_ca_topic_score_gemma":0.006063511,"domain_scores_codex":[0.9954383,0.001053684,0.001245815,0.0006767887,0.00135257,0.0002329037],"domain_scores_gemma":[0.9804709,0.01434471,0.001169289,0.0009894549,0.002482206,0.0005434055],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003416893,0.0007931826,0.0190904,0.0103764,0.0006519877,0.004547473,0.004273445,0.01825484,0.09683853,0.04542061,0.1346799,0.6616564],"study_design_scores_gemma":[0.001509124,0.001199999,0.01479644,0.001432851,0.0009401076,0.005262696,0.004953168,0.4964884,0.1219151,0.08690128,0.2640835,0.0005173482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1266392,0.003213281,0.7069574,0.005950784,0.0003993278,0.003926329,0.04752898,0.09200779,0.01337687],"genre_scores_gemma":[0.1277224,0.00108872,0.8328336,0.0005834536,0.0001784164,0.0009615814,0.03266838,0.001780655,0.002182704],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9961421,"threshold_uncertainty_score":0.04369253,"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."}}