{"id":"W6966796338","doi":"10.48448/nmpn-1949","title":"SSMix: Saliency-based Span Mixup for Text Classification","year":2021,"lang":"en","type":"other","venue":"Open MIND","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":[0.0009119522,0.002163369,0.000918253,0.002792566,0.000818807,0.001047086,0.001311548,0.001039314,0.01305109],"category_scores_gemma":[0.003271301,0.0004936189,0.001179982,0.001624065,0.0005854166,0.00284991,0.002825112,0.001421575,0.009813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004604283,"about_ca_system_score_gemma":0.0006910454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001283161,"about_ca_topic_score_gemma":0.003137376,"domain_scores_codex":[0.9992405,0.000129051,0.00006565626,0.0002969998,0.0001932953,0.00007443818],"domain_scores_gemma":[0.9989464,0.0003871913,0.00009324033,0.0002630575,0.000226837,0.00008327815],"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":[0.0006035564,0.0002398683,0.001281118,0.0004158322,0.0000926945,0.0002114504,0.0003313524,0.003977364,0.07169198,0.002288522,0.02494424,0.893922],"study_design_scores_gemma":[0.0002210993,0.0008551093,0.004349655,0.0001053628,0.0001866697,0.0006842394,0.0006393778,0.6918541,0.2136857,0.02448341,0.0627896,0.0001457699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04479186,0.001650449,0.885465,0.0003755875,0.0005214593,0.000612129,0.004544421,0.0577681,0.004271129],"genre_scores_gemma":[0.1855639,0.0005169086,0.7812061,0.0003822031,0.0003917413,0.0009903795,0.01700304,0.002698329,0.01124732],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01305109,"threshold_uncertainty_score":0.04366028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1107690524069312,"score_gpt":0.3718557211151181,"score_spread":0.2610866687081869,"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."}}