{"id":"W2069318033","doi":"10.1109/icde.2010.5447820","title":"Efficient identification of coupled entities in document collections","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Identification (biology); Information retrieval; Core (optical fiber); Pace; Value (mathematics); Data science; Data mining; World Wide Web; Geography","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":[0.000232236,0.00003821728,0.00005554622,0.0001282504,0.0000728704,0.0000934211,0.0003218781,0.00001924617,0.0000443836],"category_scores_gemma":[0.00002169874,0.00003575648,0.0000171951,0.0006051622,0.00003217621,0.00007848416,0.00007347702,0.00005892539,0.0000208604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001160592,"about_ca_system_score_gemma":0.00003680071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002483432,"about_ca_topic_score_gemma":0.000183304,"domain_scores_codex":[0.9994375,0.00000701522,0.0002115337,0.0001493969,0.0001154599,0.00007916878],"domain_scores_gemma":[0.999464,0.00003611599,0.00005868841,0.0003639777,0.00005467498,0.00002250294],"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":[0.000001246151,0.0004149499,0.0003766732,0.00001167524,0.000008746243,6.036763e-7,0.001028978,0.001637312,0.1049084,0.8779941,0.002007753,0.01160957],"study_design_scores_gemma":[0.0001848819,0.00001441055,0.007417671,0.000004399514,0.000002306469,0.000002801697,0.0001043433,0.9687631,0.01863116,0.002934953,0.001859928,0.00008004548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3128001,0.000007228442,0.6825125,0.0005090814,0.0003662154,0.0001796161,0.000006665236,0.00006746393,0.003551188],"genre_scores_gemma":[0.9476888,0.000002647476,0.04953232,0.00001504366,0.00001099387,0.00005736762,0.000003910426,0.000001950473,0.002686939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9671258,"threshold_uncertainty_score":0.1458107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006950176333583624,"score_gpt":0.2472271092515987,"score_spread":0.2402769329180151,"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."}}