{"id":"W4411552659","doi":"10.1109/icse55347.2025.00012","title":"Reasoning Runtime Behavior of a Program with LLM: How Far are We?","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Science Foundation of Ningbo","keywords":"Computer science; Programming language","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":[0.00960756,0.00140346,0.001312346,0.002011067,0.0009542106,0.004675909,0.003531777,0.002111766,0.001523459],"category_scores_gemma":[0.05179247,0.0006780073,0.001723505,0.001610434,0.002224893,0.01132757,0.003253419,0.002864101,0.001027594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002076262,"about_ca_system_score_gemma":0.00451365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01939053,"about_ca_topic_score_gemma":0.02075011,"domain_scores_codex":[0.9907326,0.003511366,0.0006696219,0.002157777,0.00237191,0.0005567009],"domain_scores_gemma":[0.9664704,0.01649233,0.003812327,0.009044179,0.003275262,0.0009055],"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":[0.00117343,0.0007564471,0.08402202,0.001477482,0.0004276719,0.000278101,0.002220244,0.08329098,0.02264625,0.01523931,0.009082207,0.7793859],"study_design_scores_gemma":[0.0001088167,0.0006907748,0.02251981,0.0005514219,0.0004297949,0.0004429329,0.00247116,0.8683459,0.04563651,0.04392655,0.01463795,0.0002384654],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.4097625,0.005730348,0.5240401,0.009652192,0.0001464914,0.000267992,0.001936609,0.04200593,0.006457874],"genre_scores_gemma":[0.675873,0.00111672,0.3164126,0.0009813998,0.00006097524,0.0001009045,0.002740115,0.001660909,0.001053338],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01939053,"threshold_uncertainty_score":0.05081022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01673049310134625,"score_gpt":0.2872280263207825,"score_spread":0.2704975332194363,"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."}}