{"id":"W4232002330","doi":"10.1101/2021.06.10.21257749","title":"Inferring global-scale temporal latent topics from news reports to predict public health interventions for COVID-19","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Psychological intervention; Scale (ratio); Computer science; Public health; Data science; Public health interventions; Transfer of learning; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Artificial intelligence; Machine learning; Medicine; Geography; Infectious disease (medical specialty); Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0030892,0.000197288,0.0005915393,0.0001377867,0.0005286329,0.0004330079,0.0003877479,0.0001835043,0.0003276701],"category_scores_gemma":[0.002616475,0.0002053737,0.0007416148,0.0005014267,0.00007169898,0.00010291,0.000637749,0.0002323945,0.000003745279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008575943,"about_ca_system_score_gemma":0.002799502,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04674485,"about_ca_topic_score_gemma":0.1377971,"domain_scores_codex":[0.9965805,0.0007991869,0.0009145034,0.0007427344,0.0005661642,0.0003969056],"domain_scores_gemma":[0.9976793,0.0002485216,0.0005329076,0.000459026,0.0002517567,0.0008284744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005009043,0.0001692088,0.9515412,0.0002559929,0.0002257161,0.00002921485,0.006931611,0.002359483,0.000001012091,0.002006344,0.002752774,0.03372247],"study_design_scores_gemma":[0.0003017478,0.00007323682,0.3710434,0.0005056391,0.0001642411,0.000004105107,0.003012191,0.001432248,0.000002956801,0.09327997,0.5295795,0.0006007335],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2997223,0.0008738633,0.6093182,0.08548355,0.002549963,0.0009281522,0.0001621471,0.0001833104,0.0007785605],"genre_scores_gemma":[0.8807703,0.0001498592,0.1103232,0.003477616,0.001729517,0.0003619208,0.00122664,0.00002456433,0.001936435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.581048,"threshold_uncertainty_score":0.959603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2229284879122773,"score_gpt":0.4718456974206761,"score_spread":0.2489172095083988,"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."}}