{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02304644,0.002004149,0.001756031,0.01900089,0.0009987711,0.008325068,0.002444748,0.002370093,0.002653399],"category_scores_gemma":[0.06654175,0.0006156426,0.002109524,0.01320985,0.001118697,0.01072447,0.002007448,0.001010857,0.001574246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003730737,"about_ca_system_score_gemma":0.00366277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003257052,"about_ca_topic_score_gemma":0.002114613,"domain_scores_codex":[0.979376,0.005987595,0.002143508,0.001544225,0.01054261,0.0004061206],"domain_scores_gemma":[0.9388431,0.04144876,0.003408224,0.004115351,0.01187719,0.0003074252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000350443,0.0002914996,0.01996779,0.0120303,0.001582025,0.000223807,0.0006156708,0.03501225,0.002664872,0.05565205,0.008739658,0.8628696],"study_design_scores_gemma":[0.0001673916,0.002865176,0.06066432,0.02009062,0.004888967,0.002543871,0.004421622,0.4122578,0.02944631,0.1523685,0.3097087,0.0005767488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09928878,0.3403702,0.4717978,0.009194196,0.001116242,0.001755634,0.006905675,0.00316074,0.06641064],"genre_scores_gemma":[0.402278,0.1307596,0.4525702,0.0007836556,0.0007675209,0.001328773,0.006860949,0.0003012219,0.004350129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02304644,"threshold_uncertainty_score":0.1218827,"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."}}