{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001524505,0.0005663912,0.0005434325,0.001627869,0.0004109161,0.0003551855,0.001706106,0.0004002175,0.003671071],"category_scores_gemma":[0.000784643,0.0005469332,0.0001780261,0.002843923,0.002016981,0.0001791413,0.0001523757,0.0003329353,0.002485235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006540601,"about_ca_system_score_gemma":0.003978583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000217263,"about_ca_topic_score_gemma":0.001168883,"domain_scores_codex":[0.9950492,0.00009467953,0.0005471317,0.001755668,0.001514658,0.001038668],"domain_scores_gemma":[0.9966094,0.0001813285,0.0007109353,0.00161449,0.0005366043,0.0003471985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003405586,0.0006450369,0.0002785762,0.0003256268,0.00004848573,0.00001050371,0.00009389251,0.0001875799,0.1044177,0.02780719,0.8418395,0.02431187],"study_design_scores_gemma":[0.0009933346,0.0001406656,0.0004077356,0.0004495295,0.00008874743,0.000007265896,0.0002434104,0.08132224,0.004906246,0.0007214021,0.9097516,0.0009678018],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0001849329,0.001123745,0.1463451,0.001918719,0.003050458,0.003330427,0.001506407,0.001702098,0.8408381],"genre_scores_gemma":[0.05345242,0.00003159653,0.2095828,0.00136421,0.002036851,0.0005583562,0.003663205,0.002852084,0.7264584],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1143797,"threshold_uncertainty_score":0.9996982,"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."}}