{"id":"W4220759704","doi":"10.3390/app12062891","title":"Survey of BERT-Base Models for Scientific Text Classification: COVID-19 Case Study","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Topic Modeling","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Computer science; Scientific literature; Pandemic; Data science; Context (archaeology); Task (project management); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Domain (mathematical analysis); Artificial intelligence; History; Infectious disease (medical specialty); Medicine; Engineering; Disease; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.006941106,0.0001177048,0.000184099,0.0002621088,0.002192229,0.0002856145,0.001935385,0.00001991475,0.00002253659],"category_scores_gemma":[0.0001189723,0.0001103851,0.00004067289,0.001912654,0.0003785467,0.000312362,0.0006104822,0.00009503204,0.000002819467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009182336,"about_ca_system_score_gemma":0.0009673313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001187973,"about_ca_topic_score_gemma":0.0007649089,"domain_scores_codex":[0.9973362,0.0001807635,0.0003889764,0.000954407,0.000828651,0.0003109944],"domain_scores_gemma":[0.998085,0.000618293,0.0002103853,0.0008163787,0.000118455,0.0001514626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003079794,0.00111671,0.00638741,0.00005111156,0.00002612232,0.00008476934,0.02240902,0.5101514,0.001729079,0.428259,0.002368181,0.02738643],"study_design_scores_gemma":[0.0004526117,0.0001625126,0.0003013402,8.272338e-7,0.00000585208,0.00005590993,0.007246073,0.9826067,0.0001212789,0.008493477,0.0003757649,0.0001776243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4028827,0.00005262014,0.5948555,0.0004407154,0.0003807901,0.0008082608,0.00002646219,0.00006884617,0.0004840664],"genre_scores_gemma":[0.9827083,2.421298e-7,0.01655345,0.0002317253,0.00001355305,0.0003712117,0.000004744399,0.000004911436,0.0001118944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5798256,"threshold_uncertainty_score":0.9991068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2673387486849687,"score_gpt":0.3575259476444219,"score_spread":0.09018719895945321,"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."}}