{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005581399,0.0001602814,0.0001455734,0.0002160224,0.0002709639,0.001107296,0.0007538258,0.00009877516,0.00002704073],"category_scores_gemma":[0.0004565967,0.0001125615,0.00008710557,0.0008217171,0.0001901699,0.009652778,0.0001681921,0.0001728862,0.0001155446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002375404,"about_ca_system_score_gemma":0.00007064805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004785143,"about_ca_topic_score_gemma":0.0000054007,"domain_scores_codex":[0.9984158,0.0000576808,0.0007612226,0.0001834655,0.000369109,0.0002127796],"domain_scores_gemma":[0.9985463,0.0002729045,0.000419643,0.0004959935,0.0002420858,0.00002305075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000315048,0.000006384178,0.00001986676,0.00007458757,0.00001759499,1.988353e-7,0.01258446,0.00004085153,0.001372364,0.5433845,0.0005149742,0.441981],"study_design_scores_gemma":[0.0005459855,0.00023797,0.004605685,0.0007109487,0.00005840479,0.00005073766,0.03214007,0.5256039,0.06671398,0.3009186,0.06777197,0.0006417964],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01792388,0.0004376652,0.9701226,0.001462198,0.0005145847,0.0004120134,0.000003473946,0.000763925,0.008359686],"genre_scores_gemma":[0.9880732,0.0000886436,0.01142803,0.0001244283,0.00003086098,0.0001233225,0.00003840013,0.000006231084,0.00008685312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9701493,"threshold_uncertainty_score":0.9999297,"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."}}