{"id":"W1886498467","doi":"10.1186/1471-2164-13-s3-s2","title":"A LDA-based approach to promoting ranking diversity for genomics information retrieval","year":2012,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Latent Dirichlet allocation; Information retrieval; Computer science; Relevance (law); Ranking (information retrieval); Topic model; Redundancy (engineering); Genomics; Learning to rank; Data science; Biology; Genome","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":[],"consensus_categories":[],"category_scores_codex":[0.002764123,0.0007982544,0.001363033,0.003385364,0.001285433,0.001480279,0.001556649,0.001175533,0.001512587],"category_scores_gemma":[0.006130696,0.0005471144,0.001834378,0.002596863,0.001101645,0.001881688,0.00154775,0.001340673,0.001326799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001538774,"about_ca_system_score_gemma":0.001628124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006921712,"about_ca_topic_score_gemma":0.009825127,"domain_scores_codex":[0.9970638,0.001286611,0.0001668712,0.0003688487,0.0008818083,0.0002320317],"domain_scores_gemma":[0.9969335,0.001477197,0.0002314111,0.0004092676,0.0007854435,0.0001631786],"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":[0.0005421173,0.0005001694,0.005966749,0.0003558091,0.0003216194,0.0002660614,0.0005353895,0.2495964,0.03197993,0.02356907,0.01186255,0.6745042],"study_design_scores_gemma":[0.00003887224,0.0001124155,0.000842969,0.00001115508,0.00004965354,0.0001241194,0.00005020521,0.9819456,0.004076343,0.01024416,0.002455527,0.00004897262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02034472,0.0009826715,0.9748381,0.0004817923,0.00007804848,0.000148907,0.0001536875,0.001285686,0.001686285],"genre_scores_gemma":[0.5505374,0.0009248143,0.4399824,0.0004037792,0.0004828633,0.0004571429,0.0008242878,0.0002531848,0.006134134],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006921712,"threshold_uncertainty_score":0.01461822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0541025256968388,"score_gpt":0.2550488328437936,"score_spread":0.2009463071469548,"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."}}