{"id":"W6931714364","doi":"10.5683/sp2/pxf2cu","title":"COVID-19 Twitter Dataset","year":2020,"lang":"en","type":"dataset","venue":"Borealis","topic":"","field":"","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Social media; Python (programming language); Sample (material); Software; Sampling (signal processing); Coronavirus disease 2019 (COVID-19)","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":[0.001105126,0.002156276,0.001304338,0.004209863,0.001870452,0.001987342,0.002553923,0.002221744,0.02279354],"category_scores_gemma":[0.005522117,0.0004860286,0.001338893,0.005349202,0.0003920844,0.002725952,0.002426178,0.001903343,0.05361924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001508123,"about_ca_system_score_gemma":0.001982377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02143227,"about_ca_topic_score_gemma":0.04110391,"domain_scores_codex":[0.9980472,0.0003566973,0.0002758173,0.0004443869,0.0005902681,0.0002856349],"domain_scores_gemma":[0.9979458,0.000378546,0.0001924214,0.0004781412,0.0007605152,0.0002445381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001269599,0.0000624341,0.002606594,0.0005833847,0.00003922882,0.0000790615,0.00006373304,0.0007001759,0.0005580429,0.0007139311,0.9873815,0.007084987],"study_design_scores_gemma":[0.0001888684,0.0001022168,0.01274772,0.0002878356,0.00005003116,0.0002284651,0.0004464466,0.006872507,0.001330738,0.001764606,0.975874,0.0001064931],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00204659,0.0002323067,0.0004086574,0.0003418365,0.0002158176,0.0001187856,0.99163,0.001476219,0.003529765],"genre_scores_gemma":[0.001755437,0.00009328988,0.0008975075,0.0001402089,0.00004076167,0.0001880852,0.9956082,0.00009096776,0.001185567],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02279354,"threshold_uncertainty_score":0.07625198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0698773696104188,"score_gpt":0.3445561891220138,"score_spread":0.274678819511595,"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."}}