{"id":"W2784152338","doi":"10.1109/icmla.2017.0-122","title":"Cybersecurity Automated Information Extraction Techniques: Drawbacks of Current Methods, and Enhanced Extractors","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Science and Technology Directorate; Ministère de la Défense Nationale; UT-Battelle; Battelle; U.S. Department of Homeland Security; U.S. Department of Energy","keywords":"Overfitting; Computer science; Leverage (statistics); Information extraction; Relationship extraction; Identification (biology); Information retrieval; Domain (mathematical analysis); Precision and recall; Recall; Artificial intelligence; Natural language processing; Data mining","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0005377474,0.00008740273,0.0001251005,0.00008811323,0.0001517145,0.0002509029,0.0004209429,0.00006649279,0.000008370109],"category_scores_gemma":[0.0001563829,0.00007781063,0.00002903006,0.00004572685,0.00004299979,0.003075588,0.00018587,0.0001156991,0.000003597829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002479233,"about_ca_system_score_gemma":0.00003736709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009468081,"about_ca_topic_score_gemma":0.000005642777,"domain_scores_codex":[0.9992398,0.00004735883,0.0002913131,0.0001563326,0.0001474537,0.0001177553],"domain_scores_gemma":[0.9988211,0.00004988118,0.0003494884,0.0006205994,0.0001103055,0.0000486333],"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":[0.000002207679,0.00002235893,0.00008499513,0.00003657684,0.000004513357,1.587532e-7,0.001054778,0.000005976367,0.01839915,0.0243134,0.00007647069,0.9559994],"study_design_scores_gemma":[0.0002475355,0.00004430682,0.005363056,0.00006900501,0.0000080295,0.000007593467,0.00009048673,0.4504732,0.533393,0.004608736,0.005461685,0.0002333275],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02929624,0.00003239864,0.9641377,0.00008767223,0.000350656,0.000162646,7.221529e-7,0.0004727563,0.005459165],"genre_scores_gemma":[0.6082659,0.00002761464,0.3916646,0.00001305745,0.00001198045,0.000006588777,8.478294e-7,0.000001555002,0.000007923582],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9557661,"threshold_uncertainty_score":0.3173026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0255260958909049,"score_gpt":0.4003089176312616,"score_spread":0.3747828217403567,"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."}}