{"id":"W4229048469","doi":"10.32473/flairs.v35i.130722","title":"Generative Adversarial learning with Negative Data Augmentation for Semi-supervised Text Classification","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Discriminator; Generator (circuit theory); Computer science; Generative grammar; Manifold (fluid mechanics); Representation (politics); Boundary (topology); Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Mode (computer interface); Generative model; Decision boundary; Matching (statistics); Mixing (physics); Key (lock); Power (physics); Machine learning; Mathematics; Statistics; Physics; Support vector machine","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":[0.002310546,0.0001709781,0.000173313,0.0001371919,0.0009387408,0.0005804647,0.003909872,0.00005369719,0.00005583677],"category_scores_gemma":[0.001403612,0.0001421145,0.0001150053,0.001085778,0.0004256674,0.001757391,0.002073715,0.0006851821,0.000007876832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004939458,"about_ca_system_score_gemma":0.0004941854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009635271,"about_ca_topic_score_gemma":0.000021775,"domain_scores_codex":[0.996314,0.00006590647,0.0004515367,0.0007581469,0.002029925,0.0003804849],"domain_scores_gemma":[0.9959128,0.0006059495,0.0003482544,0.000342202,0.002708345,0.00008245148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006901989,0.0002757422,0.0004444006,0.00006820293,0.0002953563,5.90768e-7,0.017294,0.003646613,0.1459032,0.696938,0.005481457,0.1289623],"study_design_scores_gemma":[0.0001459198,0.0003957065,0.00007785138,0.00004340792,0.00001135345,0.000005278398,0.0195698,0.778241,0.1462484,0.05356883,0.001522594,0.0001699051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1670853,0.00002589302,0.7971298,0.02076861,0.003649272,0.00313509,0.0002385147,0.0002229156,0.007744633],"genre_scores_gemma":[0.9807264,0.00002140578,0.01786701,0.000076306,0.0003284056,0.0004170365,0.00005134074,0.00001681221,0.0004953416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8136411,"threshold_uncertainty_score":0.726558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.214596084131797,"score_gpt":0.3702213578985494,"score_spread":0.1556252737667524,"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."}}