{"id":"W4409407626","doi":"10.1007/978-3-031-88036-0_8","title":"GERA: A Corpus of Russian School Texts Annotated for Grammatical Error Correction","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Error analysis; Linguistics; Mathematics; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001518273,0.001158133,0.0008543183,0.005530607,0.001790706,0.001148249,0.0009965346,0.001171064,0.01622104],"category_scores_gemma":[0.00539881,0.000655458,0.0005040997,0.004255797,0.0009178835,0.001424488,0.001531601,0.0009750792,0.01549639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007442715,"about_ca_system_score_gemma":0.001783356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005445157,"about_ca_topic_score_gemma":0.0108406,"domain_scores_codex":[0.9978448,0.0007577615,0.0002541882,0.0006086729,0.0004156108,0.0001189657],"domain_scores_gemma":[0.9951425,0.002342028,0.0003674669,0.0008917859,0.001090398,0.0001657875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001556611,0.0006807077,0.01521361,0.008754805,0.0002974964,0.003258895,0.01535551,0.003891631,0.08316336,0.009983946,0.5781515,0.2796918],"study_design_scores_gemma":[0.0002633095,0.0002311789,0.08876015,0.0007002201,0.0002666543,0.002655752,0.003907891,0.005183829,0.02669841,0.002912446,0.8682514,0.000168741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.254973,0.005541711,0.02377054,0.001236362,0.001148073,0.0006732851,0.6339568,0.01684141,0.06185888],"genre_scores_gemma":[0.2124943,0.001431021,0.04186243,0.0002246318,0.0002357673,0.000512771,0.7206328,0.003738429,0.01886793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01622104,"threshold_uncertainty_score":0.05426478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01177045022988296,"score_gpt":0.2758623785684261,"score_spread":0.2640919283385431,"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."}}