{"id":"W7125578338","doi":"10.1109/cascon66301.2025.00124","title":"Towards an LLM-Based Auto-Corrector Agent for Symboleo Specifications","year":2025,"lang":"","type":"article","venue":"","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Executable; Compiler; Formal specification; Specification language; Code (set theory); Formal verification; Formal methods; Semantics (computer science)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008535915,0.0003967206,0.000442077,0.0004239712,0.0006532822,0.0007441196,0.001283522,0.0002217335,0.000504282],"category_scores_gemma":[0.0001232257,0.0003811526,0.0003307371,0.0009650191,0.00006276232,0.0006170999,0.0001303342,0.0001542103,0.0001873745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003491845,"about_ca_system_score_gemma":0.001021272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004084785,"about_ca_topic_score_gemma":0.0002120362,"domain_scores_codex":[0.9965332,0.0002335575,0.00097509,0.001198962,0.0004505875,0.0006086481],"domain_scores_gemma":[0.997126,0.0002076788,0.000303931,0.001644981,0.000483574,0.000233806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001025711,0.003641509,0.001784046,0.0007824851,0.0002229791,0.000004857531,0.002749841,0.002758938,0.008992858,0.5046886,0.06948714,0.4047842],"study_design_scores_gemma":[0.001160167,0.00026392,0.01877343,0.0001624792,0.00005885888,8.252175e-7,0.0001412152,0.8851495,0.01107826,0.0004633197,0.08233418,0.0004138868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003462171,0.0002772861,0.9718496,0.005042305,0.008119446,0.002160634,0.00005797521,0.0003063614,0.008724255],"genre_scores_gemma":[0.9269841,0.00002907638,0.05168591,0.001633103,0.0004558191,0.0003895441,0.0000730538,0.0000259223,0.01872346],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9235219,"threshold_uncertainty_score":0.999864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08185617724225776,"score_gpt":0.3180195295762351,"score_spread":0.2361633523339774,"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."}}