{"id":"W4287855142","doi":"10.18653/v1/2022.deeplo-1.14","title":"AfriTeVA: Extending ?Small Data? Pretraining Approaches to Sequence-to-Sequence Models","year":2022,"lang":"en","type":"article","venue":"","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Sequence (biology); Computer science; Artificial intelligence; Natural language processing; Biology; Genetics","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":[0.001294159,0.0002165053,0.0001966412,0.0001561572,0.0003122678,0.00009340868,0.001617911,0.0001078758,0.0001428177],"category_scores_gemma":[0.0003420907,0.0002013871,0.00006435881,0.0003432954,0.0001210707,0.00001310655,0.003106234,0.0002625972,0.00004331271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006315162,"about_ca_system_score_gemma":0.0002756703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006352664,"about_ca_topic_score_gemma":0.00005679198,"domain_scores_codex":[0.9974476,0.00009599134,0.0003878523,0.0007237095,0.0006313989,0.0007135058],"domain_scores_gemma":[0.9982482,0.00002975712,0.00005795656,0.00109408,0.0000658886,0.0005041377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003768664,0.0004016783,0.0004526716,0.0002644169,0.0002317513,0.00005131664,0.003522556,0.02063529,0.6604507,0.003768357,0.02766811,0.2821763],"study_design_scores_gemma":[0.00180459,0.004355359,0.0002737346,0.00008825651,0.00006636261,0.000213111,0.01254667,0.4928407,0.09128126,0.002953037,0.3911307,0.002446216],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5576142,0.0009644374,0.3659874,0.007602825,0.001017114,0.002962477,0.001907377,0.0001845938,0.06175961],"genre_scores_gemma":[0.9336978,0.00008113487,0.05998872,0.001760741,0.0002311622,0.0001273388,0.0009027895,0.00003181389,0.003178556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5691695,"threshold_uncertainty_score":0.8212327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4124934241705409,"score_gpt":0.3435203856514142,"score_spread":0.06897303851912667,"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."}}