{"id":"W2158255858","doi":"10.5555/1937055.1937105","title":"Towards a collection-based results diversification","year":2010,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Information retrieval; Computer science; Cosine similarity; Diversification (marketing strategy); Relevance (law); Data mining; Document retrieval; Artificial intelligence; Cluster analysis","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":[0.0002495692,0.00004179575,0.00003588252,0.00009410806,0.0001565223,0.0001217933,0.0003335634,0.0000383291,0.00008655311],"category_scores_gemma":[0.0000861817,0.00003358164,0.00002760808,0.0004250599,0.00002071084,0.0003637944,0.00004173347,0.0001061808,0.0002372283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001648581,"about_ca_system_score_gemma":0.0001411367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000956865,"about_ca_topic_score_gemma":0.00002378262,"domain_scores_codex":[0.9994214,0.00001126683,0.0001213752,0.0001091264,0.0002319129,0.0001049252],"domain_scores_gemma":[0.9994376,0.00003028464,0.00003449212,0.0002612665,0.0001737059,0.00006267156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002099684,0.0004497565,0.003022449,0.00002382927,0.00001522739,0.00001113446,0.00390444,0.0001495062,0.03148112,0.5572257,0.07027826,0.3332286],"study_design_scores_gemma":[0.002166014,0.0002269686,0.1110796,0.000004179266,0.000004821323,0.0000084433,0.00006951683,0.6448795,0.1378987,0.0009159211,0.102391,0.0003553189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06763221,7.030447e-7,0.8294801,0.007489668,0.0008747605,0.0002394666,0.000007005282,0.0004095839,0.09386658],"genre_scores_gemma":[0.9539935,4.018346e-7,0.04306976,0.0003491728,0.00002034547,0.000007210453,0.000007715605,0.000001265201,0.002550629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8863613,"threshold_uncertainty_score":0.304917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02275603600988979,"score_gpt":0.2648521647651605,"score_spread":0.2420961287552708,"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."}}