{"id":"W2118013824","doi":"10.1007/s10115-010-0367-z","title":"Statistical semantics for enhancing document clustering","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Semantic similarity; Computer science; Cluster analysis; Document clustering; Similarity (geometry); Vector space model; Explicit semantic analysis; Semantics (computer science); Representation (politics); Benchmark (surveying); Context (archaeology); Artificial intelligence; Information retrieval; Distributional semantics; Data mining; Natural language processing; Semantic computing; Semantic technology; Semantic Web","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":[0.000537654,0.00009313502,0.0001294619,0.0001198911,0.0001735374,0.0004649937,0.0002491954,0.000056959,0.000002158636],"category_scores_gemma":[0.0001204792,0.00008362466,0.00001741457,0.000119601,0.00002646845,0.002474161,0.0002268613,0.0001339074,0.00007456307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000307707,"about_ca_system_score_gemma":0.00005157014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000824185,"about_ca_topic_score_gemma":0.00003039517,"domain_scores_codex":[0.9991048,0.00001972941,0.0003442348,0.0001237735,0.0001658347,0.0002416326],"domain_scores_gemma":[0.9991529,0.0001862439,0.00007727305,0.0002425785,0.0002299595,0.0001110593],"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":[0.00001982205,0.00003668342,0.0001139307,0.002016826,0.00003751753,0.000002200778,0.01072934,0.0009884767,0.003240237,0.53394,0.001474167,0.4474008],"study_design_scores_gemma":[0.0003916157,0.00006480171,0.0001588402,0.00004177726,0.000001951267,0.0000396754,0.0001718253,0.8243201,0.0005976501,0.0002712749,0.1738006,0.0001398048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001323863,0.00005416876,0.9943241,0.00007007845,0.00117393,0.0003706124,0.000006977087,0.00009341141,0.002582897],"genre_scores_gemma":[0.8967787,0.00001917109,0.1023552,0.00003892464,0.0002202224,0.0001390813,0.0000141388,0.000007988332,0.0004265874],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8954548,"threshold_uncertainty_score":0.4483945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01213181996842227,"score_gpt":0.3032534578081119,"score_spread":0.2911216378396896,"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."}}