{"id":"W4392200326","doi":"10.18280/isi.290123","title":"Augmenting Document Classification Accuracy Through the Integration of Deep Contextual Embeddings","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Information retrieval; Computer science; Artificial intelligence; Natural language processing; Data science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009139198,0.001071914,0.0008184533,0.001493962,0.000337206,0.001146299,0.0008377364,0.0007903249,0.001221041],"category_scores_gemma":[0.004022975,0.0001969171,0.0005539345,0.001604058,0.0003426844,0.002899813,0.001008897,0.001283969,0.001588705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005530147,"about_ca_system_score_gemma":0.0005889564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002448692,"about_ca_topic_score_gemma":0.005416501,"domain_scores_codex":[0.9993635,0.0001356592,0.00005980415,0.0001752118,0.0001967528,0.00006906324],"domain_scores_gemma":[0.9979582,0.0006983613,0.0002140755,0.0004578184,0.0006115339,0.00006007323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002089428,0.0003102507,0.008783422,0.0002232362,0.0001067646,0.00007034931,0.0001299604,0.04981565,0.02078726,0.002518306,0.009036516,0.9080095],"study_design_scores_gemma":[0.00001911948,0.0001899486,0.003742996,0.00003986994,0.00009053192,0.0001116461,0.00008625997,0.9645544,0.0201395,0.005140739,0.005852459,0.0000325758],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2420632,0.003975535,0.7370383,0.0009585075,0.0004311384,0.0001331282,0.001497815,0.007973844,0.005928622],"genre_scores_gemma":[0.7284549,0.001338654,0.2612751,0.0002342389,0.0002682552,0.0001189828,0.003616993,0.0001979558,0.004494815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002448692,"threshold_uncertainty_score":0.004868865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03038136928308593,"score_gpt":0.289087797511525,"score_spread":0.258706428228439,"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."}}