{"id":"W2792179143","doi":"10.1109/tkde.2018.2810873","title":"Supervised Search Result Diversification via Subtopic Attention","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Chinese Academy of Sciences; National Natural Science Foundation of China; Natural Science Foundation of Beijing Municipality; Microsoft Research","keywords":"Computer science; Pooling; Diversification (marketing strategy); Machine learning; Artificial intelligence; Ranking (information retrieval); Relevance (law); Information retrieval; Data mining","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":[0.000246517,0.00008968916,0.0000726778,0.0001879178,0.0002199325,0.0001067867,0.0004956466,0.00004896921,0.00002227047],"category_scores_gemma":[0.000003836094,0.00008672344,0.0000216247,0.0003598131,0.00003060425,0.001094341,0.00001712408,0.0001393189,0.0002307817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003001441,"about_ca_system_score_gemma":0.000024905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001714901,"about_ca_topic_score_gemma":0.000007464142,"domain_scores_codex":[0.9992467,0.00001954388,0.0001489359,0.000252209,0.0001546881,0.0001779302],"domain_scores_gemma":[0.9991461,0.00003987726,0.00001330434,0.000588296,0.0001228762,0.00008953694],"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":[0.00007606999,0.0003736595,0.000149191,0.0001944747,0.00006849388,0.000006722385,0.004233565,0.0009047017,0.04996723,0.002053736,0.0008316812,0.9411405],"study_design_scores_gemma":[0.0004138451,0.000122622,0.003745187,0.00002701881,0.00001147235,0.000008697156,0.00002767148,0.9720718,0.01961758,0.000006008313,0.003786098,0.0001619712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03771352,0.00002579887,0.9612956,0.00009199412,0.0004426136,0.0001113782,0.00003491794,0.0001350101,0.0001491838],"genre_scores_gemma":[0.9937066,0.00004215591,0.005858019,0.0000164316,0.00006774066,0.000006111684,0.0000318353,0.000005580934,0.0002655444],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9711671,"threshold_uncertainty_score":0.3536479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04992458604131879,"score_gpt":0.2878324295515918,"score_spread":0.237907843510273,"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."}}