{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003123207,0.001063615,0.001986769,0.007438798,0.001813252,0.004801149,0.002800128,0.001412111,0.0008370964],"category_scores_gemma":[0.02000737,0.001284906,0.001399948,0.008830023,0.001286032,0.007291189,0.003762812,0.001247333,0.0006827358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009887825,"about_ca_system_score_gemma":0.001960439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003870296,"about_ca_topic_score_gemma":0.007755754,"domain_scores_codex":[0.9961568,0.0007750758,0.000540364,0.001072559,0.001197616,0.0002577381],"domain_scores_gemma":[0.9889408,0.005243048,0.00182795,0.002156813,0.001426489,0.0004049327],"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":[0.000783982,0.0004172076,0.06572029,0.001699218,0.0007189721,0.001247924,0.003900724,0.07818832,0.04386374,0.02136355,0.008627829,0.7734683],"study_design_scores_gemma":[0.00009740516,0.0003556872,0.0289893,0.0002110362,0.000521371,0.00238694,0.003682638,0.7968583,0.05721187,0.08708704,0.02239923,0.0001991381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2609639,0.001830184,0.7275292,0.0005015182,0.0000519832,0.0007174738,0.002825923,0.003673496,0.00190635],"genre_scores_gemma":[0.2656723,0.0005657913,0.7273602,0.00006136469,0.00005751467,0.000211899,0.004755609,0.0002189717,0.001096357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007438798,"threshold_uncertainty_score":0.01651728,"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."}}