{"id":"W6910558641","doi":"10.48448/jb6n-0z38","title":"SSMix: Saliency-Based Span Mixup for Text Classification","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Sentence; Locality; Code (set theory); Range (aeronautics); Phrase; Mixing (physics); Span (engineering)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008618605,0.00211706,0.0008888651,0.00289468,0.0007807252,0.001077445,0.001319199,0.001042557,0.01365995],"category_scores_gemma":[0.003166139,0.0005042545,0.001163399,0.001663924,0.0005718995,0.002882276,0.002808876,0.001346262,0.01137333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004705004,"about_ca_system_score_gemma":0.0006766588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001321107,"about_ca_topic_score_gemma":0.003044018,"domain_scores_codex":[0.9992292,0.0001278138,0.00006597211,0.0003010317,0.0002030193,0.00007304578],"domain_scores_gemma":[0.9989531,0.0003572158,0.00009911724,0.0002703815,0.0002321514,0.00008810248],"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":[0.0005766882,0.0002112439,0.001281445,0.0003988897,0.00008777675,0.0002140697,0.0003166535,0.003890313,0.0681885,0.002242472,0.02854579,0.8940461],"study_design_scores_gemma":[0.0002148855,0.0008006277,0.004324748,0.0001059372,0.0001740936,0.0007121241,0.0005962961,0.6904572,0.204145,0.02676175,0.07156339,0.0001439438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04161093,0.001733385,0.8792368,0.0003976798,0.0005401136,0.0005852146,0.005130959,0.0660599,0.004705099],"genre_scores_gemma":[0.1839204,0.0005387985,0.7794673,0.0004176729,0.0004288,0.0009304145,0.01917405,0.002982928,0.01213948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01365995,"threshold_uncertainty_score":0.04569709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06545904730639952,"score_gpt":0.3503864667441492,"score_spread":0.2849274194377497,"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."}}