Research

Paper

TESTING March 23, 2026

Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis

Authors

Tae-Eun Song

Abstract

LLM coding benchmarks face a credibility crisis: widespread solution leakage and test quality issues undermine SWE-bench Verified, while existing detection methods--paraphrase consistency, n-gram overlap, perplexity analysis--never directly observe whether a model reasons or recalls. Meanwhile, simply repeating verification degrades accuracy: multi-turn review generates false positives faster than it discovers true errors, suggesting that structural approaches are needed. We introduce Cross-Context Verification (CCV), a black-box method that solves the same benchmark problem in N independent sessions and measures solution diversity, combined with the Hierarchical Cross-Context Architecture (HCCA), a multi-agent analysis framework that prevents confirmation bias through intentional information restriction across specialized analytical roles. On 9 SWE-bench Verified problems (45 trials, Claude Opus 4.6, temperature 0), CCV achieves perfect separation between contaminated and genuine reasoning (Mann-Whitney U=0, p approx 0.012, r = 1.0). Key findings: (1) contamination is binary--models either recall perfectly or not at all; (2) reasoning absence is a perfect discriminator; (3) 33% of prior contamination labels are false positives; (4) HCCA's independent analysis structure discovers contamination-flaw composite cases that single-analyst approaches miss. A pilot experiment extending HCCA to multi-stage verification (Worker to Verifier to Director) yields a negative result--100% sycophantic confirmation--providing further evidence that information restriction, not structural complexity, is the key mechanism. We release all code and data.

Metadata

arXiv ID: 2603.21454
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-23
Fetched: 2026-03-24 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.21454v1</id>\n    <title>Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis</title>\n    <updated>2026-03-23T00:18:34Z</updated>\n    <link href='https://arxiv.org/abs/2603.21454v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.21454v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>LLM coding benchmarks face a credibility crisis: widespread solution leakage and test quality issues undermine SWE-bench Verified, while existing detection methods--paraphrase consistency, n-gram overlap, perplexity analysis--never directly observe whether a model reasons or recalls. Meanwhile, simply repeating verification degrades accuracy: multi-turn review generates false positives faster than it discovers true errors, suggesting that structural approaches are needed.\n  We introduce Cross-Context Verification (CCV), a black-box method that solves the same benchmark problem in N independent sessions and measures solution diversity, combined with the Hierarchical Cross-Context Architecture (HCCA), a multi-agent analysis framework that prevents confirmation bias through intentional information restriction across specialized analytical roles.\n  On 9 SWE-bench Verified problems (45 trials, Claude Opus 4.6, temperature 0), CCV achieves perfect separation between contaminated and genuine reasoning (Mann-Whitney U=0, p approx 0.012, r = 1.0). Key findings: (1) contamination is binary--models either recall perfectly or not at all; (2) reasoning absence is a perfect discriminator; (3) 33% of prior contamination labels are false positives; (4) HCCA's independent analysis structure discovers contamination-flaw composite cases that single-analyst approaches miss. A pilot experiment extending HCCA to multi-stage verification (Worker to Verifier to Director) yields a negative result--100% sycophantic confirmation--providing further evidence that information restriction, not structural complexity, is the key mechanism. We release all code and data.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-23T00:18:34Z</published>\n    <arxiv:comment>11 pages, 3 figures, 4 tables</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Tae-Eun Song</name>\n    </author>\n  </entry>"
}