{"id":"W2587209668","doi":"10.29173/cais195","title":"Boosting for Text Classification with Subject Headings","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Classifier (UML); Subject (documents); Boosting (machine learning); Information retrieval; Natural language processing; Artificial intelligence; Library science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007215162,0.0004100465,0.0005718088,0.000252856,0.0003000852,0.006178169,0.003303223,0.0003158668,0.00004051354],"category_scores_gemma":[0.01300158,0.000314484,0.0002060044,0.0009307301,0.001114789,0.02093444,0.0006686053,0.000368662,0.00001744143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001260891,"about_ca_system_score_gemma":0.0004431109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000402798,"about_ca_topic_score_gemma":0.00001363201,"domain_scores_codex":[0.9972946,0.00002638081,0.0007781895,0.0006480128,0.0005510685,0.0007017636],"domain_scores_gemma":[0.9434701,0.0003862196,0.001655539,0.0004510767,0.05389145,0.0001456093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001266957,0.0003423592,0.09459799,0.001200495,0.0001716883,4.349631e-7,0.02894094,0.000004740049,0.06197121,0.6383491,0.02263671,0.1516577],"study_design_scores_gemma":[0.002340815,0.002490017,0.3430563,0.002719223,0.0003317006,0.0001196877,0.01615682,0.02742711,0.2574834,0.08627342,0.2600253,0.001576243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9170225,0.0008418113,0.00827674,0.06053298,0.0004545479,0.001912005,0.0001029794,0.0002721915,0.01058423],"genre_scores_gemma":[0.9821671,0.0001474015,0.011357,0.000221771,0.00009638585,0.0002525825,0.000004020299,0.00003310199,0.005720611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5520756,"threshold_uncertainty_score":0.9999307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04504300598340083,"score_gpt":0.2606952696426386,"score_spread":0.2156522636592377,"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."}}