{"id":"W7125000707","doi":"10.26615/978-954-452-098-4-142","title":"Demographic Features for Annotation-Aware Classification","year":2025,"lang":"","type":"article","venue":"International conference Recent advances in natural language processing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Population; Identification (biology); Feature (linguistics); Set (abstract data type); Field (mathematics)","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006015815,0.000387288,0.0003399871,0.0009143434,0.0003426043,0.001055487,0.001639917,0.0002104135,0.00005253797],"category_scores_gemma":[0.00108718,0.0003800552,0.0001104699,0.001499173,0.0001618195,0.002856305,0.0001998918,0.0007963516,0.000006625613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003022946,"about_ca_system_score_gemma":0.0004644072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002430387,"about_ca_topic_score_gemma":0.0003565812,"domain_scores_codex":[0.9969032,0.0001689391,0.0008015514,0.001084445,0.0005643107,0.0004775199],"domain_scores_gemma":[0.9972307,0.0003114445,0.0006290558,0.0004271027,0.001329754,0.00007192537],"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":[0.0001434637,0.0001064681,0.002670676,0.0003090787,0.00002382965,0.000003484298,0.001057716,0.0001435983,0.0006975023,0.04634678,0.00009749264,0.9483999],"study_design_scores_gemma":[0.001133085,0.00004298421,0.01690664,0.001624029,0.00002917818,0.000008660609,0.001860253,0.9126465,0.0003589789,0.005630777,0.05926438,0.0004944867],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001242715,0.2178216,0.7453054,0.01856895,0.00519574,0.0009934198,0.00009521692,0.0002250731,0.01055195],"genre_scores_gemma":[0.9670709,0.01670237,0.01283992,0.0004965354,0.0002216511,0.0001632452,0.0007180144,0.00001699179,0.001770408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9658281,"threshold_uncertainty_score":0.9999815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02015870596706755,"score_gpt":0.362967026904323,"score_spread":0.3428083209372554,"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."}}