{"id":"W4414276204","doi":"10.5753/sast.2025.13826","title":"Detecção de Conflitos Semânticos com Testes Gerados por LLM","year":2025,"lang":"pt","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Merge (version control)","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":[0.0008951826,0.0004558081,0.0005023952,0.0003894668,0.0003920573,0.0008495797,0.001760727,0.0003036464,0.00008089275],"category_scores_gemma":[0.001707015,0.000439862,0.0001914988,0.001078415,0.0001746121,0.0003063031,0.0008305503,0.0004951498,0.0001520048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001666965,"about_ca_system_score_gemma":0.0006522108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006546641,"about_ca_topic_score_gemma":0.00001542593,"domain_scores_codex":[0.9970132,0.0002351587,0.0006159711,0.0008801665,0.0003744591,0.0008810438],"domain_scores_gemma":[0.9955618,0.002199616,0.0001798732,0.001498183,0.0003198962,0.0002406557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003028257,0.0008819574,0.1134951,0.0005045848,0.0001915199,0.0002388155,0.001850222,0.0000427945,0.001248072,0.04090805,0.5461951,0.2944135],"study_design_scores_gemma":[0.001327717,0.0008044742,0.01761884,0.002086509,0.0001842179,0.0002247063,0.00006176495,0.8097305,0.02975573,0.109584,0.02698958,0.001631978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003642496,0.0009061171,0.9597639,0.006280456,0.0008945118,0.0005407261,0.000008352331,0.01953512,0.008428356],"genre_scores_gemma":[0.7841845,0.00002860897,0.1767109,0.007043938,0.00009775789,0.00007252037,0.000003397275,0.00003552635,0.03182286],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8096877,"threshold_uncertainty_score":0.9998053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02318122068552407,"score_gpt":0.3002464998347447,"score_spread":0.2770652791492206,"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."}}