{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075143,0.0002078421,0.0002373419,0.0003885659,0.0001549485,0.0002399949,0.001244917,0.00033552,0.000005167674],"category_scores_gemma":[0.0004317906,0.0002443311,0.0001477988,0.001106301,0.0000471219,0.0003708921,0.0007618259,0.0007313882,0.00008414446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000208718,"about_ca_system_score_gemma":0.0001806969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000608869,"about_ca_topic_score_gemma":0.00006265539,"domain_scores_codex":[0.9982688,0.0001348679,0.0002551992,0.000917543,0.0000903402,0.0003332373],"domain_scores_gemma":[0.9985059,0.0003079625,0.0003093198,0.000660726,0.0001396173,0.00007644208],"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":[0.0001099583,0.0001494774,0.008016957,0.0009606715,0.00007746989,0.0003265613,0.009177813,0.06226521,0.0002248744,0.8937117,0.0003331908,0.02464609],"study_design_scores_gemma":[0.0002557172,0.00001123254,0.003874497,0.0003621759,0.00001957408,0.00000128713,0.0005547545,0.8430491,0.0003640305,0.151073,0.000083692,0.0003508942],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1030477,0.0002426893,0.8947022,0.0003050773,0.0007950066,0.0004329262,0.00001691254,0.0004002288,0.00005722846],"genre_scores_gemma":[0.9901227,0.00002749627,0.007859592,0.00007845507,0.00008718988,0.000005918373,0.00006018015,0.00001890436,0.001739611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8870749,"threshold_uncertainty_score":0.9963531,"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."}}