{"id":"W4240152675","doi":"10.32920/ryerson.14663040","title":"Cluster-discovery of Twitter messages for event detection and trending","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Event (particle physics); Computer science; Locality-sensitive hashing; Cluster (spacecraft); Big data; Hash function; Social media; Data mining; Key (lock); Process (computing); Locality; Hash table; Computer security; World Wide 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005619518,0.0006061941,0.0007830869,0.003690478,0.0009948887,0.0009963167,0.0009874974,0.0005078515,0.001561585],"category_scores_gemma":[0.002937505,0.0003465295,0.0007060812,0.003671837,0.0002588338,0.001595968,0.001260535,0.000626298,0.001540045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007048311,"about_ca_system_score_gemma":0.001027756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006682361,"about_ca_topic_score_gemma":0.01274231,"domain_scores_codex":[0.9993518,0.00006852459,0.0000488014,0.0002168292,0.0002068958,0.0001070575],"domain_scores_gemma":[0.9987375,0.000252922,0.0002003279,0.0003073038,0.0003761027,0.0001257841],"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":[0.001407062,0.0004919001,0.07739107,0.0008256145,0.000351121,0.0006454156,0.001872173,0.02718944,0.09100705,0.0112006,0.02913536,0.7584833],"study_design_scores_gemma":[0.00006876739,0.0003599362,0.04216718,0.00004902782,0.0001331043,0.0007578706,0.002135552,0.855869,0.05932433,0.01350562,0.02552985,0.00009983405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4218708,0.001468826,0.5410861,0.001060126,0.0003038628,0.0009577063,0.01384155,0.01103002,0.008381087],"genre_scores_gemma":[0.7061613,0.0005232437,0.2748735,0.00008426925,0.0001299462,0.0002531435,0.01200819,0.0002346553,0.005731815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006682361,"threshold_uncertainty_score":0.01328695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02842525887803826,"score_gpt":0.2689567114933181,"score_spread":0.2405314526152799,"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."}}