{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001274092,0.0001421717,0.0001508153,0.0001974987,0.0005585825,0.0002597111,0.0007343087,0.00008748868,0.00000240647],"category_scores_gemma":[0.0001457607,0.000143177,0.0001063212,0.0003513785,0.00001852021,0.001794426,0.000609035,0.0001149151,0.00008811076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003408483,"about_ca_system_score_gemma":0.0002158755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009858015,"about_ca_topic_score_gemma":9.709671e-7,"domain_scores_codex":[0.998637,0.00003469405,0.0003448175,0.0001481045,0.0003170056,0.000518397],"domain_scores_gemma":[0.998983,0.00007524877,0.0001617294,0.0003362101,0.0002131483,0.0002306227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00292877,0.002124965,0.07979822,0.003269834,0.0001952525,0.000001779919,0.3866355,0.07999074,0.02180501,0.1599201,0.005524627,0.2578053],"study_design_scores_gemma":[0.002640174,0.000289086,0.01060962,0.00001886972,0.00003988017,0.00001312183,0.0006479168,0.9047681,0.03428008,0.0002590523,0.04558297,0.0008511131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3138027,0.000006927973,0.6846145,0.00005176041,0.0002343275,0.0007668874,0.00001723462,0.00008167847,0.0004240191],"genre_scores_gemma":[0.6497023,9.254173e-7,0.3495201,0.0005547622,0.0001143956,0.00002067344,0.00004751808,0.000007292231,0.00003206608],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8247774,"threshold_uncertainty_score":0.5838588,"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."}}