{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001434032,0.001852539,0.0008505564,0.0008005789,0.0006274628,0.001417133,0.002795256,0.001645478,0.01061693],"category_scores_gemma":[0.005968431,0.001045417,0.001708115,0.0008074816,0.000639522,0.002301943,0.001955901,0.005282361,0.007822314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001064788,"about_ca_system_score_gemma":0.001703554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01107186,"about_ca_topic_score_gemma":0.0255173,"domain_scores_codex":[0.9994387,0.0001746731,0.00003323206,0.0002095451,0.00008318383,0.00006067743],"domain_scores_gemma":[0.998047,0.00119625,0.00005638862,0.0003895453,0.000255526,0.00005530451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003511553,0.0003178066,0.002587356,0.000497881,0.0004351488,0.0002795983,0.0003400753,0.3946956,0.01375213,0.01319035,0.06804178,0.5055112],"study_design_scores_gemma":[0.0000291972,0.00005820006,0.0002377541,0.00004133482,0.00002649668,0.00006227127,0.00003485365,0.9736961,0.0059109,0.009794511,0.01008702,0.00002131768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02391417,0.001083577,0.9134505,0.000867719,0.0003815299,0.0002447447,0.003534646,0.04887585,0.007647285],"genre_scores_gemma":[0.1947496,0.0009816347,0.7603938,0.001434302,0.0001708015,0.001130358,0.02217337,0.00553046,0.01343566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01107186,"threshold_uncertainty_score":0.03551716,"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."}}