{"id":"W2997205428","doi":"10.1609/aaai.v34i04.5822","title":"Nonlinear Mixup: Out-Of-Manifold Data Augmentation for Text Classification","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Nonlinear system; Mixing (physics); Manifold (fluid mechanics); Computer science; Regularization (linguistics); Scalar (mathematics); Interpolation (computer graphics); Benchmark (surveying); Mathematics; Artificial intelligence; Pattern recognition (psychology); Algorithm; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.00033477,0.0001570563,0.0002090433,0.00008331267,0.0001169446,0.0001623826,0.003697287,0.00008678984,0.00002187277],"category_scores_gemma":[0.0008069013,0.0001239708,0.00007277098,0.0004992922,0.0001657963,0.0007066545,0.0005505591,0.0001441218,0.00004941087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002335237,"about_ca_system_score_gemma":0.00008345805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000058039,"about_ca_topic_score_gemma":0.000003233139,"domain_scores_codex":[0.998278,0.000009456557,0.0006008007,0.0005517531,0.0003696916,0.0001902612],"domain_scores_gemma":[0.9981022,0.0001092795,0.0006415391,0.0005480581,0.0005443922,0.00005457232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004621621,0.00009114343,0.00008101243,0.00005556144,0.00001119579,2.598225e-8,0.0008275225,0.000003800869,0.1346215,0.7711114,0.0008869607,0.09226366],"study_design_scores_gemma":[0.0000439981,0.0002286492,0.0001153977,0.00005721511,0.00001544882,2.086081e-7,0.001185045,0.2604725,0.6817673,0.05461723,0.001352474,0.0001445388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03135372,0.00004934012,0.8838167,0.07606008,0.0008698027,0.001868023,0.0001063144,0.0004923767,0.005383696],"genre_scores_gemma":[0.9726282,0.00003836573,0.0268971,0.0002347761,0.00005787928,0.00003773192,0.000009349051,0.000009065433,0.00008748028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9412745,"threshold_uncertainty_score":0.6870541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2956569575793979,"score_gpt":0.3630008410034393,"score_spread":0.06734388342404135,"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."}}