{"id":"W2095980495","doi":"10.1145/2740908.2742474","title":"Short-Text Clustering using Statistical Semantics","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Term (time); Similarity (geometry); Semantics (computer science); Representation (politics); Selection (genetic algorithm); Measure (data warehouse); Computation; Space (punctuation); Data mining; Artificial intelligence; Matrix (chemical analysis); Document clustering; Pattern recognition (psychology); Algorithm","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":[0.0003335949,0.0001202169,0.0001424468,0.00009090266,0.00007953052,0.0002098795,0.0006860466,0.0000446205,0.00001165916],"category_scores_gemma":[0.0001245197,0.0001106831,0.00002110393,0.0002946551,0.00005967213,0.0004835832,0.001056704,0.000162071,0.00009436504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000141717,"about_ca_system_score_gemma":0.0001013899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003661157,"about_ca_topic_score_gemma":0.00001048191,"domain_scores_codex":[0.9984192,0.0000549313,0.0001925904,0.0003478292,0.0005384929,0.0004470185],"domain_scores_gemma":[0.9989058,0.00009817693,0.00001850815,0.0005078582,0.0001486733,0.0003210218],"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":[0.00004025978,0.0002380159,0.001552781,0.0001143308,0.00006967514,0.001059837,0.002031012,0.1699575,0.003940362,0.08545558,0.002263078,0.7332776],"study_design_scores_gemma":[0.0001520753,0.00004696129,0.00016803,0.000009314072,0.000001624746,0.0001020067,0.0000605693,0.9960502,0.0004823311,0.001914246,0.0008581299,0.0001545359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004115366,0.00002265175,0.9928427,0.0002122001,0.0002898151,0.00009296096,0.000001523347,0.0002197069,0.002203055],"genre_scores_gemma":[0.333704,0.000001731046,0.6658034,0.00005669534,0.00006047409,0.000002324915,7.972256e-7,0.0000115619,0.0003590214],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8260927,"threshold_uncertainty_score":0.4513525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1306881645226687,"score_gpt":0.3815659194037594,"score_spread":0.2508777548810908,"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."}}