{"id":"W4403881534","doi":"10.1111/1755-6724.15213","title":"GeoNER: Geological Named Entity Recognition with Enriched Domain Pre‐Training Model and Adversarial Training","year":2024,"lang":"en","type":"article","venue":"Acta Geologica Sinica - English Edition","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Training (meteorology); Adversarial system; Computer science; Domain (mathematical analysis); Training set; Artificial intelligence; Named-entity recognition; Pattern recognition (psychology); Engineering; Mathematics; Geography","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001247748,0.0003364561,0.0004049672,0.0001812709,0.000296745,0.0004156262,0.0005364114,0.0004062623,0.00009219479],"category_scores_gemma":[0.000818388,0.0002739191,0.0001037173,0.0003872198,0.0002614332,0.001663157,0.0003413174,0.0007126153,0.00001146806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008531061,"about_ca_system_score_gemma":0.0001985125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001807484,"about_ca_topic_score_gemma":0.00001895537,"domain_scores_codex":[0.9969534,0.0002438938,0.0005009702,0.001194219,0.000479329,0.000628138],"domain_scores_gemma":[0.9982851,0.0006761212,0.0001579292,0.0004788503,0.0002004576,0.0002015802],"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":[0.001322799,0.001266871,0.001889289,0.0006234721,0.001104859,0.001350133,0.2122741,0.03321621,0.01371026,0.2255667,0.01197763,0.4956976],"study_design_scores_gemma":[0.001759971,0.0007784247,0.002597965,0.0002148146,0.0001062894,0.0001521078,0.001530246,0.8430144,0.00006312349,0.1445494,0.004315188,0.000918077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5690967,0.0001091075,0.4229332,0.001435434,0.001491951,0.0003563851,0.00001723027,0.001115744,0.003444219],"genre_scores_gemma":[0.906262,0.00008050595,0.09178752,0.0003072291,0.001288787,0.00009904968,0.0001020371,0.00001743122,0.00005541684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8097982,"threshold_uncertainty_score":0.9999713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04337033694538565,"score_gpt":0.2466242737974124,"score_spread":0.2032539368520268,"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."}}