{"id":"W2765471337","doi":"10.5555/3107979.3107989","title":"Generating stochastic data to simulate a twitter user","year":2017,"lang":"en","type":"article","venue":"Communications and Networking Symposium","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Recommender system; Collaborative filtering; Similarity (geometry); Weibull distribution; Information retrieval; Cluster analysis; tf–idf; Data mining; Term (time); Machine learning; Artificial intelligence; Mathematics; Statistics","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":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0004151151,0.000102859,0.0001067448,0.00004864499,0.001451693,0.001653181,0.007079501,0.000024504,0.00000138117],"category_scores_gemma":[0.00001413266,0.0000984975,0.00001466164,0.00008544716,0.00006775471,0.0009022326,0.012633,0.0001103686,0.0000206322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008420842,"about_ca_system_score_gemma":0.00001140259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003522985,"about_ca_topic_score_gemma":0.00003657734,"domain_scores_codex":[0.9991432,0.00004709447,0.0001586429,0.0003438019,0.00009851837,0.0002087706],"domain_scores_gemma":[0.9912432,0.0000914061,0.0001071119,0.008449152,0.00003180547,0.00007733785],"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":[0.000008963876,0.0002172081,0.003407341,0.00003387639,0.0001936297,0.00001284702,0.002387086,0.01095844,0.001710416,0.0381694,0.03550708,0.9073937],"study_design_scores_gemma":[0.0001120801,0.00001374992,0.000308784,0.00004466142,0.00001074123,0.000001691032,0.000006673522,0.8451915,0.000001435278,0.00015152,0.1540303,0.0001267903],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003242943,0.0008390131,0.9727682,0.0197601,0.0006874178,0.0003166567,0.00001072097,0.0001419264,0.002232948],"genre_scores_gemma":[0.8652562,0.0003753219,0.132013,0.001184308,0.0003267669,0.00002100755,0.00006319478,0.00001296128,0.0007473023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9072669,"threshold_uncertainty_score":0.9998483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1287545541099956,"score_gpt":0.3418526201569586,"score_spread":0.2130980660469629,"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."}}