{"id":"W4410536486","doi":"10.1109/icst62969.2025.10989022","title":"Addressing Data Leakage in HumanEval Using Combinatorial Test Design","year":2025,"lang":"en","type":"article","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Leakage (economics); Reliability engineering; Test (biology); Engineering; Geology","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":[0.006984303,0.001330021,0.0008053443,0.001140091,0.0004669015,0.002168819,0.003180958,0.001253248,0.0029862],"category_scores_gemma":[0.02977771,0.0005624335,0.0009348757,0.0008178638,0.001915132,0.003639948,0.002259483,0.00180507,0.0008142588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001465526,"about_ca_system_score_gemma":0.003069987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00198876,"about_ca_topic_score_gemma":0.002821522,"domain_scores_codex":[0.9889608,0.005871743,0.0006288546,0.001406262,0.002564331,0.0005680508],"domain_scores_gemma":[0.9767845,0.01241269,0.001421212,0.006256066,0.002674096,0.0004514912],"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":[0.002443719,0.001397871,0.01629288,0.002075423,0.0003959332,0.0008468489,0.001154498,0.3290456,0.05473455,0.04529534,0.01830012,0.5280173],"study_design_scores_gemma":[0.0003365166,0.002459503,0.002692078,0.0001663297,0.0001198312,0.0004466819,0.0003401423,0.8128487,0.1199137,0.04057188,0.01997627,0.0001282941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2337983,0.001189852,0.7289793,0.0009405641,0.0003158771,0.000812931,0.001082331,0.02248151,0.0103994],"genre_scores_gemma":[0.6240909,0.0001932562,0.3690856,0.0006333649,0.00003275078,0.0008028274,0.001543254,0.001451749,0.00216647],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006984303,"threshold_uncertainty_score":0.036937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3731923182925919,"score_gpt":0.3999106756467645,"score_spread":0.02671835735417266,"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."}}