{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004305115,0.0006906997,0.0005620176,0.0008614439,0.0008232457,0.002336514,0.002400188,0.002066273,0.004801372],"category_scores_gemma":[0.009742068,0.0007109441,0.001000474,0.0003437541,0.001537097,0.002621304,0.002891148,0.001929131,0.002447792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054274,"about_ca_system_score_gemma":0.002728407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00275787,"about_ca_topic_score_gemma":0.00353756,"domain_scores_codex":[0.9974672,0.0008223768,0.000235277,0.000397804,0.0008921062,0.000185133],"domain_scores_gemma":[0.9960289,0.001175939,0.0004917432,0.001363257,0.0007445564,0.0001956862],"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":[0.001190231,0.0007967809,0.009754533,0.0007667805,0.0001870295,0.00155158,0.0033868,0.1565809,0.09931182,0.1532286,0.01664832,0.5565968],"study_design_scores_gemma":[0.000102566,0.0001546744,0.0003703984,0.00008074986,0.00005855581,0.0003743795,0.0002334953,0.8819004,0.05107925,0.01820899,0.04737483,0.00006167751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01059378,0.00007181901,0.9724299,0.0002632608,0.00003750996,0.0001551557,0.00005365895,0.01437608,0.002018838],"genre_scores_gemma":[0.1216692,0.00007393114,0.8718733,0.0002063756,0.00001531133,0.0001521132,0.0002363336,0.001036693,0.004736794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004801372,"threshold_uncertainty_score":0.02276784,"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."}}