{"paper":{"title":"iCoRe: An Iterative Correlation-Aware Retriever for Bug Reproduction Test Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"An iterative retriever that tracks source-test differences, semantic-structural links, and generation feedback raises LLM success at producing bug reproduction tests.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jialun Cao, Junyi Wang, Zhongxin Liu","submitted_at":"2026-04-21T08:26:30Z","abstract_excerpt":"Automatically generating bug reproduction tests (BRT) from issue descriptions is crucial for software maintenance. LLM-based approaches have shown great potential for this task. Their effectiveness heavily relies on retrieving high-quality context from the codebase. The retrieval phase of existing approaches relies on either traditional methods like BM25 or LLM-driven strategies. LLM-based retrieval strategies typically equip an LLM with tools to autonomously explore the repository or select the most relevant files and code snippets from a provided list as context. However, these retrieval met"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results show that our method achieves a Fail-to-Pass rate of 42.0% and 52.8% respectively, representing 19.7%-31.7% relative improvements over existing retrieval methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The three named correlations (source-test differentiation, semantic-structural relevance, retrieval-generation feedback) are the dominant factors limiting current retrievers and that an iterative loop will improve them without introducing new noise or instability in the LLM outputs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"iCoRe improves Fail-to-Pass rates to 42.0% and 52.8% on two bug reproduction benchmarks by using correlation-aware iterative retrieval instead of standard semantic or BM25 methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An iterative retriever that tracks source-test differences, semantic-structural links, and generation feedback raises LLM success at producing bug reproduction tests.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d93f4a3ab5ecbea507a0ed0643678b64efbc58a2d66259368d93e9cd69b6f2cc"},"source":{"id":"2604.19224","kind":"arxiv","version":2},"verdict":{"id":"78f1f270-afdd-40e3-9037-3852389aedb2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T02:29:08.468144Z","strongest_claim":"Experimental results show that our method achieves a Fail-to-Pass rate of 42.0% and 52.8% respectively, representing 19.7%-31.7% relative improvements over existing retrieval methods.","one_line_summary":"iCoRe improves Fail-to-Pass rates to 42.0% and 52.8% on two bug reproduction benchmarks by using correlation-aware iterative retrieval instead of standard semantic or BM25 methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The three named correlations (source-test differentiation, semantic-structural relevance, retrieval-generation feedback) are the dominant factors limiting current retrievers and that an iterative loop will improve them without introducing new noise or instability in the LLM outputs.","pith_extraction_headline":"An iterative retriever that tracks source-test differences, semantic-structural links, and generation feedback raises LLM success at producing bug reproduction tests."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.19224/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T03:13:42.648865Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"afd3970f5458426274371f7d1f4a31ee532d277e5b401a12014f5684508e7d53"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}