{"id":"W2894762547","doi":"10.1145/3209280.3229114","title":"Improving Short Text Clustering by Similarity Matrix Sparsification","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Cluster analysis; Similarity (geometry); Computer science; Artificial intelligence; Embedding; Word (group theory); Correlation clustering; Document clustering; Pattern recognition (psychology); Data mining; Mathematics; Image (mathematics)","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":[0.001106215,0.001212809,0.001431929,0.001679843,0.0007382945,0.001197233,0.001118483,0.001115,0.002818774],"category_scores_gemma":[0.00844011,0.0003463516,0.0009246353,0.002168434,0.0007111351,0.002877739,0.001499367,0.001246541,0.003261315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004206023,"about_ca_system_score_gemma":0.0008179648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002474062,"about_ca_topic_score_gemma":0.004272942,"domain_scores_codex":[0.9987832,0.0002929274,0.0001105825,0.0003397905,0.0003837986,0.00008973102],"domain_scores_gemma":[0.9959126,0.001780928,0.0003748833,0.0009523958,0.0008071004,0.00017203],"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":[0.0008163503,0.0003133263,0.003097088,0.0007259403,0.0002506904,0.0003131515,0.0004967307,0.2115953,0.1199886,0.008317976,0.0126425,0.6414423],"study_design_scores_gemma":[0.00003183699,0.0001368038,0.001018416,0.00001525282,0.00004098732,0.0002125972,0.0001689477,0.949486,0.03692346,0.008405699,0.003527996,0.00003207206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05747921,0.0009585542,0.9362311,0.0002735406,0.0001464871,0.0001259493,0.0004255096,0.003010596,0.00134903],"genre_scores_gemma":[0.3523392,0.0008477994,0.6367681,0.0002501371,0.0002691887,0.0002272657,0.003816069,0.0006755386,0.004806784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002818774,"threshold_uncertainty_score":0.009429693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02896945668198172,"score_gpt":0.2747629703535149,"score_spread":0.2457935136715332,"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."}}