{"id":"W4385967449","doi":"10.48550/arxiv.2308.01681","title":"NBIAS: A Natural Language Processing Framework for Bias Identification in Text","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Government of Canada; Canadian Institute for Advanced Research","keywords":"Security token; Computer science; Transformer; Identification (biology); Data science; Natural language processing; Artificial intelligence; Variety (cybernetics); Social media; Machine learning; Data mining; World Wide Web; Computer security; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02333219,0.002162516,0.001609985,0.007846926,0.002362236,0.005961976,0.003429562,0.002596426,0.006070636],"category_scores_gemma":[0.06431084,0.001205005,0.003121938,0.004380352,0.003269916,0.008156504,0.005819902,0.005391894,0.005725771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003352864,"about_ca_system_score_gemma":0.006023425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005729147,"about_ca_topic_score_gemma":0.009727158,"domain_scores_codex":[0.9800341,0.009486996,0.002133481,0.003279025,0.004564297,0.0005019972],"domain_scores_gemma":[0.9463795,0.03504303,0.006220388,0.005647453,0.005960694,0.0007488766],"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":[0.0005819128,0.0003763014,0.01270691,0.002939459,0.000540027,0.001115512,0.004847306,0.0363563,0.01997888,0.1932672,0.05842752,0.6688626],"study_design_scores_gemma":[0.0001022216,0.0001570276,0.002719489,0.000678802,0.0001540184,0.0007006699,0.0009401576,0.5430275,0.01507508,0.3567551,0.0795073,0.0001827002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002626413,0.0003626311,0.9848209,0.0008238492,0.0001606674,0.0005321223,0.002305658,0.007233109,0.001134657],"genre_scores_gemma":[0.0539228,0.0004682252,0.9358917,0.0006881546,0.0003308143,0.001182018,0.005361447,0.0007197328,0.001435004],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02333219,"threshold_uncertainty_score":0.1233939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.199665017893937,"score_gpt":0.2732585389733455,"score_spread":0.07359352107940845,"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."}}