{"id":"W4239044865","doi":"10.1007/978-0-387-39940-9_3614","title":"Similarity-based Data Partitioning","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Similarity (geometry); Computer science; Artificial intelligence; Pattern recognition (psychology)","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":[0.0008167159,0.0009852119,0.001485272,0.002783288,0.001097508,0.002340181,0.002828554,0.0007953774,0.0108162],"category_scores_gemma":[0.002855239,0.0006317117,0.001189003,0.00455538,0.0006116553,0.002429237,0.002733949,0.001017043,0.006483221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007158291,"about_ca_system_score_gemma":0.001165144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002311425,"about_ca_topic_score_gemma":0.003005551,"domain_scores_codex":[0.9985676,0.0001672786,0.0001334256,0.0003297531,0.0007015297,0.0001004045],"domain_scores_gemma":[0.9984142,0.0002822419,0.00005791584,0.0006025619,0.0005850124,0.00005803184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001778652,0.0001090847,0.0004343468,0.0002064558,0.00004995434,0.00005361348,0.0001141898,0.0127082,0.01616353,0.01353598,0.02163911,0.9348076],"study_design_scores_gemma":[0.0001085443,0.000375698,0.002828587,0.0001577364,0.000144522,0.001875022,0.0005149888,0.6090121,0.1037802,0.1026858,0.1783876,0.0001292411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006178856,0.001560118,0.9795849,0.0001483442,0.0001453627,0.0002947139,0.0006982583,0.003641322,0.007748222],"genre_scores_gemma":[0.06649502,0.001107817,0.9149735,0.0001332226,0.00008132635,0.0002340543,0.005040637,0.0007565145,0.01117792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0108162,"threshold_uncertainty_score":0.03618377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04371430576372633,"score_gpt":0.2877773731228339,"score_spread":0.2440630673591076,"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."}}