{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4MJVZM4R3Q77C7P7U42BUTBUSH","short_pith_number":"pith:4MJVZM4R","schema_version":"1.0","canonical_sha256":"e3135cb391dc3ff17dffa7341a4c3491dd749ef66c4839bf58b3d46ea9c7e2c8","source":{"kind":"arxiv","id":"2604.19224","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.19224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-21T08:26:30Z","cross_cats_sorted":[],"title_canon_sha256":"abb38a1066bf0bcf5027e3c21030c89b79b2a65220adb96c346f4593965acb74","abstract_canon_sha256":"5ea115f1410d3f0ab1ac953833dcba5a1431a3bfc45bdeb5698cdff638042a33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:30.083952Z","signature_b64":"LxbR1+1YIWtMhM5dp5+L5oong5MTv5ONqYVAghaT+4ySJtINdxnx/0FtXA3e3v4jCpPGNqi6HkExWYRTnu+KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3135cb391dc3ff17dffa7341a4c3491dd749ef66c4839bf58b3d46ea9c7e2c8","last_reissued_at":"2026-06-30T01:16:30.083384Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:30.083384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.19224","created_at":"2026-06-30T01:16:30.083441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.19224v2","created_at":"2026-06-30T01:16:30.083441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19224","created_at":"2026-06-30T01:16:30.083441+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MJVZM4R3Q77","created_at":"2026-06-30T01:16:30.083441+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MJVZM4R3Q77C7P7","created_at":"2026-06-30T01:16:30.083441+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MJVZM4R","created_at":"2026-06-30T01:16:30.083441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH","json":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH.json","graph_json":"https://pith.science/api/pith-number/4MJVZM4R3Q77C7P7U42BUTBUSH/graph.json","events_json":"https://pith.science/api/pith-number/4MJVZM4R3Q77C7P7U42BUTBUSH/events.json","paper":"https://pith.science/paper/4MJVZM4R"},"agent_actions":{"view_html":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH","download_json":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH.json","view_paper":"https://pith.science/paper/4MJVZM4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.19224&json=true","fetch_graph":"https://pith.science/api/pith-number/4MJVZM4R3Q77C7P7U42BUTBUSH/graph.json","fetch_events":"https://pith.science/api/pith-number/4MJVZM4R3Q77C7P7U42BUTBUSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH/action/storage_attestation","attest_author":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH/action/author_attestation","sign_citation":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH/action/citation_signature","submit_replication":"https://pith.science/pith/4MJVZM4R3Q77C7P7U42BUTBUSH/action/replication_record"}},"created_at":"2026-06-30T01:16:30.083441+00:00","updated_at":"2026-06-30T01:16:30.083441+00:00"}