{"id":"W7077859507","doi":"10.48448/rhdk-9b58","title":"Unified Automated Essay Scoring and Grammatical Error Correction","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Kootenay Association for Science & Technology","funders":"","keywords":"Task (project management); Multi-task learning; Error detection and correction; Error analysis; Task analysis; Computational linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006124079,0.0002328372,0.0002490601,0.0003941563,0.0002654706,0.0002912128,0.001078118,0.0002027261,0.00009658896],"category_scores_gemma":[0.0004761174,0.0002077478,0.00002794426,0.001097679,0.0005404128,0.0001898164,0.0006431554,0.000274154,0.00003631573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007470018,"about_ca_system_score_gemma":0.0006891188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00015779,"about_ca_topic_score_gemma":0.00004023857,"domain_scores_codex":[0.9981596,0.0000388593,0.0002310661,0.0007693905,0.0003830005,0.00041808],"domain_scores_gemma":[0.9988871,0.00009132516,0.000154392,0.0005959973,0.0001333403,0.000137863],"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":[0.00001181052,0.0003373277,0.0008698686,0.0009377737,0.0001146677,0.0001481002,0.0007956129,0.001542187,0.005175929,0.3788594,0.4173022,0.1939051],"study_design_scores_gemma":[0.0001990476,0.00003576493,0.0001769072,0.0003676686,0.00001397889,0.00003971469,0.00006461878,0.9063785,0.0009736818,0.004740305,0.08664145,0.0003683259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00002952323,0.00009013969,0.2714206,0.001516917,0.002013575,0.0002045064,0.000002434527,0.001882463,0.7228398],"genre_scores_gemma":[0.06076584,0.0000222509,0.05514962,0.0002783232,0.0001876048,0.00001686779,0.00001399442,0.00002495007,0.8835406],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9048364,"threshold_uncertainty_score":0.847171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01609491600111776,"score_gpt":0.2725009427485385,"score_spread":0.2564060267474208,"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."}}