{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001028604,0.0001300389,0.0002214386,0.0002586372,0.0001380431,0.0004327836,0.001487961,0.00007686955,0.00002406307],"category_scores_gemma":[0.0004089317,0.0001337106,0.00002497942,0.0006742596,0.00003524356,0.001400877,0.001054603,0.00017619,0.00003408097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001142643,"about_ca_system_score_gemma":0.0002830118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003499104,"about_ca_topic_score_gemma":0.0001120361,"domain_scores_codex":[0.9983976,0.0002480936,0.0003129154,0.0005459621,0.0002416199,0.0002538189],"domain_scores_gemma":[0.9977325,0.0009774349,0.00008077781,0.001090805,0.00007568991,0.00004277346],"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":[0.0001282296,0.003281892,0.04717569,0.000465858,0.0002340194,0.0006621763,0.002549865,0.000942943,0.102912,0.141157,0.03432626,0.666164],"study_design_scores_gemma":[0.002485474,0.00006450287,0.002344221,0.0005622224,0.0000173201,0.00003878127,0.0001175004,0.9688913,0.00879859,0.01340071,0.002761431,0.0005180017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004945908,0.00006191469,0.9879932,0.0002305677,0.001495776,0.0003012417,0.000004924632,0.0001873505,0.004779152],"genre_scores_gemma":[0.9705884,9.711965e-7,0.02888103,0.0001808084,0.00008486258,0.000006091248,0.000005087823,0.000006884796,0.0002458222],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9679483,"threshold_uncertainty_score":0.5452558,"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."}}