detect-benchmark-leakage-code-specific-membership-classifier TEC-0113 · proposedDetect benchmark leakage with a code-specific membership cla
Fine-tune a shadow model on part of a benchmark to label members and non-members, then train a classifier on expert features (pass rate, CodeBLEU, edit distance, perplexity) fused with CodeBERT embeddings to predict whether a benchmark item
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Fine-tune a shadow model on part of a benchmark to label members and non-members, then train a classifier on expert features (pass rate, CodeBLEU, edit distance, perplexity) fused with CodeBERT embeddings to predict whether a benchmark item Filed by the drafting stage from Keep Evaluation Fair: Detecting Data Leakage in Code Generation Benchmarks via Membership Inference Attacks (2609.09865) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Eight benchmarks, four target models, against eight MIA baselines: average gains of 0.05-0.16 Precision, 0.06-0.11 Recall, 0.17-0.26 MCC, 0.09-0.13 AUC over the strongest baseline per model; recovered over 65% of 108 known leaked APPS samples in StarCoder-7B.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.