{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002378585,0.0001379143,0.0002366376,0.0001161339,0.00004900131,0.0003056148,0.0002698012,0.0001040687,0.000001916449],"category_scores_gemma":[0.00002350769,0.0001238838,0.0001703805,0.00005380828,0.0000157606,0.0002495376,0.0009396101,0.0001533495,2.319425e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003165994,"about_ca_system_score_gemma":0.00004014733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001812383,"about_ca_topic_score_gemma":0.00006608814,"domain_scores_codex":[0.9990204,0.00004903223,0.0002281418,0.0004368733,0.0001391867,0.0001263501],"domain_scores_gemma":[0.9992715,0.0001194927,0.0001310805,0.0003908412,0.00005971543,0.0000274218],"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":[0.0001988538,0.0004868942,0.001922446,0.0034627,0.0011034,0.00003639916,0.007268559,0.007563761,0.1500789,0.006650449,0.002056875,0.8191708],"study_design_scores_gemma":[0.001738375,0.0003206958,0.005858775,0.001272104,0.0001908349,0.00007035429,0.001020619,0.9055458,0.07695688,0.005353075,0.0005179571,0.001154547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2997703,0.0003398401,0.6986436,0.0002309801,0.0006662337,0.0001273105,0.00000282677,0.00003919215,0.0001797487],"genre_scores_gemma":[0.9936813,0.00006223363,0.004679222,0.0001323602,0.0000643984,0.00003548701,0.000005450373,0.000007106373,0.001332403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.897982,"threshold_uncertainty_score":0.5051835,"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."}}