{"id":"W2070983861","doi":"10.1145/1835449.1835673","title":"A survival modeling approach to biomedical search result diversification using wikipedia","year":2010,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Novelty; Ranking (information retrieval); Computer science; Diversification (marketing strategy); Relevance (law); Information retrieval; Probabilistic logic; Data science; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004433076,0.0001058022,0.0001077703,0.00006534727,0.000103992,0.00002569561,0.0002561637,0.0002709873,0.00001484893],"category_scores_gemma":[0.0002610623,0.00008732112,0.00004796033,0.0001570422,0.0001397347,0.000002001722,0.0001908139,0.0001881378,0.000016596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007482034,"about_ca_system_score_gemma":0.00008185965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001408074,"about_ca_topic_score_gemma":0.0000178685,"domain_scores_codex":[0.9989045,0.00003920839,0.0001600662,0.0003821554,0.0002397121,0.0002743056],"domain_scores_gemma":[0.9993647,0.00001309697,0.00001843249,0.000307613,0.00008520483,0.0002109448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000078653,0.0001418269,0.0006065234,0.00001198438,0.00002570451,0.000001147424,0.0001761385,0.0003460045,0.9841513,0.0003077097,0.001229847,0.01292314],"study_design_scores_gemma":[0.002939679,0.0009000186,0.002785001,0.0000313755,0.00008523173,0.00009090039,0.005105115,0.7901562,0.09254116,0.0002321189,0.1035747,0.001558525],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7513763,0.00002038436,0.2451185,0.000278449,0.0002647027,0.00008648964,0.000008951085,0.00003091852,0.002815327],"genre_scores_gemma":[0.9161697,0.000007647736,0.08286266,0.0001280024,0.0004155131,0.0000052368,0.00009643493,0.00001094202,0.0003038444],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8916101,"threshold_uncertainty_score":0.3560852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07376606669905197,"score_gpt":0.3213171003480381,"score_spread":0.2475510336489861,"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."}}