{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004087283,0.000729328,0.0007686409,0.0003098199,0.0001487804,0.0002707068,0.001971378,0.0005319706,0.003195165],"category_scores_gemma":[0.002450691,0.0007023131,0.0001729766,0.0004374118,0.0002276666,0.0002081416,0.0007825184,0.0008534294,0.03416468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005065221,"about_ca_system_score_gemma":0.00124683,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2139081,"about_ca_topic_score_gemma":0.04614814,"domain_scores_codex":[0.9963616,0.0003062023,0.000568647,0.001149024,0.0009631109,0.0006513867],"domain_scores_gemma":[0.9944682,0.0001853932,0.0004479832,0.003116744,0.00005009499,0.001731647],"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":[0.000100986,0.00007402221,0.000001808348,0.0003542511,0.0001666726,0.001275684,0.00003340893,0.000003099369,0.000004609432,0.000007180319,0.9979612,0.00001707375],"study_design_scores_gemma":[0.0006203607,0.00005337593,0.00001742605,0.00002451099,0.0003818742,0.00006242237,0.00002142905,0.000002718014,0.000004661897,0.0000605371,0.9979665,0.0007842092],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[3.564944e-8,0.00008584383,0.000006625036,0.002200908,0.0001614644,0.0005168378,0.9965903,0.0002817398,0.0001562426],"genre_scores_gemma":[5.478917e-8,0.0001235493,0.00007467477,0.05141843,0.001047953,0.0001132995,0.9470235,0.0001743813,0.00002418468],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1677599,"threshold_uncertainty_score":0.9995428,"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."}}