{"id":"W7106807502","doi":"10.48448/gxvr-8451","title":"Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Tracing; Scalability; Context (archaeology); Generalization; Security token; Weighting; Categorical variable; Question answering","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":[0.002818274,0.001351757,0.0009549641,0.001925612,0.001136503,0.002343371,0.003774314,0.002271489,0.009833625],"category_scores_gemma":[0.01977249,0.0008351862,0.001586244,0.001856392,0.001282672,0.008129559,0.003717915,0.0032706,0.004097633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001761785,"about_ca_system_score_gemma":0.002406958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008739157,"about_ca_topic_score_gemma":0.02007863,"domain_scores_codex":[0.9979253,0.000726541,0.0001424304,0.000801452,0.0002609757,0.0001433386],"domain_scores_gemma":[0.9949355,0.003009844,0.0002574611,0.001147405,0.0004288519,0.0002209858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001037692,0.0003398355,0.008402069,0.0007977708,0.0001857537,0.0005415209,0.001726023,0.09102865,0.007312773,0.05881034,0.02956853,0.8002489],"study_design_scores_gemma":[0.00008525576,0.00007055633,0.0008618873,0.0001457836,0.00006698717,0.0001929157,0.0002616915,0.832212,0.006111522,0.1473844,0.01254633,0.00006072298],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02445315,0.0009050781,0.9539756,0.0007576245,0.0001596088,0.0001954629,0.002747337,0.0134338,0.003372416],"genre_scores_gemma":[0.3911172,0.0003526793,0.5923224,0.0006899238,0.00009008558,0.000411673,0.007079968,0.001160671,0.006775376],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009833625,"threshold_uncertainty_score":0.03289676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09784930155383827,"score_gpt":0.3732330527241421,"score_spread":0.2753837511703038,"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."}}