{"id":"W7077933530","doi":"10.48448/ce7k-8233","title":"Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Rubric; Benchmark (surveying); Trait; Language model; Code (set theory); Scoring system; Qualitative property","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":[0.005439923,0.001645451,0.0006622614,0.002666957,0.0004294579,0.002341394,0.001458406,0.001089095,0.006510466],"category_scores_gemma":[0.03576275,0.0003535665,0.0008028658,0.001381107,0.0004530791,0.00327398,0.002368609,0.001812818,0.006334265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009735001,"about_ca_system_score_gemma":0.001667751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001956051,"about_ca_topic_score_gemma":0.004101857,"domain_scores_codex":[0.99559,0.002091831,0.0003944144,0.0007512749,0.001035062,0.000137488],"domain_scores_gemma":[0.9886673,0.005794072,0.0008916974,0.001520394,0.002782842,0.0003436016],"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":[0.0003495479,0.0003782669,0.0166917,0.0005998897,0.00008808226,0.0002347933,0.0008281249,0.02365942,0.01205803,0.008540761,0.04392391,0.8926474],"study_design_scores_gemma":[0.000153312,0.0002970119,0.007519659,0.0001445589,0.00006178619,0.0002129314,0.0003766479,0.9104687,0.01608443,0.02591401,0.03865771,0.0001092981],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0898459,0.001010176,0.8104843,0.001975017,0.0005345014,0.001194693,0.006239942,0.07590608,0.01280944],"genre_scores_gemma":[0.4254512,0.000283645,0.5477265,0.000536026,0.0001624411,0.0008405582,0.01192068,0.001505899,0.01157312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006510466,"threshold_uncertainty_score":0.02876937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01635607734806291,"score_gpt":0.2471395748755525,"score_spread":0.2307834975274896,"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."}}