{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003312415,0.0007028386,0.001166236,0.003754633,0.0007456913,0.001247007,0.0008980467,0.0008009021,0.003741283],"category_scores_gemma":[0.009224035,0.0002858996,0.0009889158,0.002581942,0.0003675969,0.001328461,0.0007458446,0.00110702,0.004371911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008325962,"about_ca_system_score_gemma":0.001344928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003615585,"about_ca_topic_score_gemma":0.003343517,"domain_scores_codex":[0.9985749,0.0004302693,0.0001023771,0.0002436467,0.0005030392,0.0001458059],"domain_scores_gemma":[0.9941262,0.003247528,0.0003444091,0.0005562352,0.001564598,0.0001610671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006379379,0.0002430519,0.008467483,0.0004698546,0.0001409112,0.000153881,0.0002606711,0.02454645,0.03119758,0.00465967,0.01453132,0.9146912],"study_design_scores_gemma":[0.0001031627,0.0007010073,0.01518029,0.0001464496,0.0002929166,0.0003923104,0.0002102763,0.8829074,0.04346993,0.01635935,0.04018129,0.00005559581],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1291144,0.008348484,0.8363698,0.001231404,0.001430816,0.00063526,0.00175685,0.0100272,0.01108592],"genre_scores_gemma":[0.6150829,0.002034189,0.3607881,0.0004588327,0.001601589,0.0004059405,0.005199371,0.0004058435,0.01402331],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003754633,"threshold_uncertainty_score":0.01751792,"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."}}