{"id":"W4283832524","doi":"10.18280/mmep.090315","title":"Assessment of Information Extraction Techniques, Models and Systems","year":2022,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Knowledge Management and Technology","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Search engine indexing; Information retrieval; GRASP; Digital library; Information extraction; Data science; Precision and recall; Data mining; Software engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.001639751,0.00008420366,0.0002029055,0.0003238148,0.00008724166,0.00009159146,0.0001400695,0.00004171384,0.00001191692],"category_scores_gemma":[0.00004730846,0.00007060361,0.00002245572,0.0002324181,0.00002242084,0.0003092699,0.0001794983,0.0001582474,0.000001500054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002212362,"about_ca_system_score_gemma":0.000006582942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004967219,"about_ca_topic_score_gemma":6.015028e-8,"domain_scores_codex":[0.9988407,0.00002301243,0.0004698351,0.0001373951,0.0004098097,0.0001192242],"domain_scores_gemma":[0.9994295,0.0001887681,0.0001159902,0.0001775764,0.0000546058,0.0000335665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.944369e-7,0.0000170259,0.00001146922,0.0001261581,0.000005738198,1.968905e-7,0.0001797705,0.6870652,0.0000702099,0.3074953,0.00001467744,0.005013471],"study_design_scores_gemma":[0.00006154487,0.00004392889,0.000005861078,0.00002303501,0.000007321393,0.00001116791,0.000217877,0.8827689,0.00001623389,0.1150895,0.00168828,0.00006631355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01655436,0.0001460961,0.9794271,0.00006054177,0.00006387147,0.0002255927,0.00000268255,0.0001142873,0.003405481],"genre_scores_gemma":[0.9639065,0.00002748269,0.03581,0.00000363662,0.000006236176,0.00009424709,0.000001777044,0.000006286485,0.0001438166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9473522,"threshold_uncertainty_score":0.2879132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07610456055055362,"score_gpt":0.3125352703394824,"score_spread":0.2364307097889288,"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."}}