{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004179066,0.001255907,0.0005236314,0.002435924,0.0008878244,0.001004814,0.001328223,0.0009321309,0.003421008],"category_scores_gemma":[0.01695619,0.0003245649,0.0005352453,0.001759067,0.0004386845,0.003465516,0.001779667,0.001809969,0.002832682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001162422,"about_ca_system_score_gemma":0.001034375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005903402,"about_ca_topic_score_gemma":0.01477269,"domain_scores_codex":[0.9974592,0.001083697,0.0001050596,0.0008056029,0.0003899652,0.0001563687],"domain_scores_gemma":[0.9933413,0.003445657,0.0006058714,0.001091546,0.001263949,0.0002517935],"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":[0.0009023683,0.0004451372,0.1074978,0.0006759497,0.0002799352,0.0005083787,0.002119455,0.03754111,0.01698168,0.02132252,0.1106375,0.7010881],"study_design_scores_gemma":[0.00007391492,0.0002954107,0.08011783,0.0003892373,0.0002521903,0.0007720275,0.001065082,0.6480157,0.01722068,0.1016835,0.1498925,0.000222057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1494581,0.003221923,0.7855222,0.004318998,0.00132627,0.0003587286,0.02367076,0.01094019,0.02118285],"genre_scores_gemma":[0.7984194,0.001113234,0.1490705,0.001187176,0.001014313,0.0007728076,0.03424752,0.0008480163,0.01332697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005903402,"threshold_uncertainty_score":0.02210122,"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."}}