{"id":"W4415428016","doi":"10.3233/faia251274","title":"Adversarial Topic-Aware Prompt-Tuning for Cross-Topic Automated Essay Scoring","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Adversarial system; Robustness (evolution); Classifier (UML); Focus (optics); Limiting; Training set; Feature (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004047768,0.00151124,0.001281434,0.0009291375,0.0004424128,0.001197949,0.001927509,0.0011291,0.003028255],"category_scores_gemma":[0.01338821,0.000394144,0.0006154226,0.0008173438,0.0006960068,0.002045006,0.002699357,0.002193021,0.002505442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007121975,"about_ca_system_score_gemma":0.001077377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001120005,"about_ca_topic_score_gemma":0.001860932,"domain_scores_codex":[0.9969569,0.001387537,0.000165043,0.0008635626,0.0004430648,0.0001838727],"domain_scores_gemma":[0.9949507,0.002449971,0.0004054056,0.0009492327,0.0009132377,0.0003315208],"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":[0.0008951667,0.0005902663,0.008297039,0.0004534922,0.0001845854,0.000301463,0.0006465254,0.2383675,0.0303931,0.006452112,0.02811085,0.6853079],"study_design_scores_gemma":[0.00006667625,0.0001444649,0.001220917,0.00002049153,0.00001972351,0.00008031347,0.00005950022,0.9794226,0.007105951,0.007937011,0.003896512,0.00002577378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09171769,0.00139932,0.8834776,0.0004437304,0.0003762894,0.0003170221,0.001055711,0.01733547,0.003877175],"genre_scores_gemma":[0.7536246,0.0003575373,0.2303632,0.0004303872,0.0003032274,0.0005878176,0.004052273,0.0007694568,0.009511523],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004047768,"threshold_uncertainty_score":0.02140689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05388806863981957,"score_gpt":0.3233714527852051,"score_spread":0.2694833841453855,"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."}}