{"id":"W2385412997","doi":"","title":"An Improved K-means Algorithm for Web Document Clustering","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Algorithm; Similarity (geometry); k-means clustering; Canopy clustering algorithm; Document clustering; Data mining; Correlation clustering; Artificial intelligence; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003100566,0.00020084,0.0001552183,0.0001478121,0.0003864648,0.0002000989,0.001220395,0.00007431168,0.00000280015],"category_scores_gemma":[2.990892e-7,0.0002159803,0.0001005106,0.0004520692,0.00003906868,0.0004336195,0.000215235,0.0001109589,0.00002191187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001029361,"about_ca_system_score_gemma":0.00005766146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006299248,"about_ca_topic_score_gemma":0.00001085604,"domain_scores_codex":[0.9983754,0.00001188867,0.0004060329,0.0006663812,0.000131701,0.0004086328],"domain_scores_gemma":[0.9986462,0.0001219531,0.0001379075,0.0006974379,0.0002161671,0.0001803534],"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":[0.000001319132,0.0001149375,0.000002566507,0.000006906152,0.000009866581,3.515989e-7,0.00007438352,0.0005521674,0.01842604,0.04586605,0.0002766044,0.9346688],"study_design_scores_gemma":[0.0002861373,0.00006755442,0.000104036,0.000004819015,0.000005410214,0.00001898719,0.000009205603,0.5736317,0.005308264,0.02732027,0.3929945,0.0002490706],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007028788,0.000033592,0.9965224,0.0005760394,0.00002832763,0.00172858,0.00002436049,0.0007900631,0.0002263979],"genre_scores_gemma":[0.007359042,0.000005658808,0.989507,0.0009499165,0.0003221295,0.001674281,0.000074673,0.00002574571,0.00008161302],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9344198,"threshold_uncertainty_score":0.8807423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009155241307754386,"score_gpt":0.3015569390585168,"score_spread":0.2924016977507624,"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."}}