{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CHQ5YMAJVEVAJHAN6TEXVDEVVF","short_pith_number":"pith:CHQ5YMAJ","schema_version":"1.0","canonical_sha256":"11e1dc3009a92a049c0df4c97a8c95a95637343d980b174564249ea2d601544a","source":{"kind":"arxiv","id":"2604.17016","version":2},"attestation_state":"computed","paper":{"title":"HELO-APR: Enhancing Low-Resource Program Repair through Cross-Lingual Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Boyang Yang, Liuye Guo, Tao Zheng, Tieke He, Yidong Wan, You Lv, Zhipeng Wang, Zhuowei Wang","submitted_at":"2026-04-18T14:55:11Z","abstract_excerpt":"Large Language Models (LLMs) perform well on automatic program repair (APR) for high-resource programming languages (HRPLs), but their effectiveness drops sharply in low-resource programming languages (LRPLs), due to a lack of sufficient verified buggy-fixed pairs for APR training. To address this challenge, we propose HELO-APR (High-resource Enabled LOw-resource APR), a two-stage APR framework that enables cross-lingual transfer of repair knowledge from HRPLs to LRPLs. HELO-APR (1) constructs high-quality LRPL training data by synthesizing LRPL buggy-fixed pairs from HRPL counterparts, preser"},"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":"2604.17016","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-04-18T14:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"c027bc053bcaff1abefdc79161e815c57e73202564579f4d01825063c149f4bd","abstract_canon_sha256":"c916f14ece20d2160ff43bd6f62e8df00218e1587d1b666e426cfe8f7453ab5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:30.315744Z","signature_b64":"nlQt3xYteDoDDoiEu0hXJkBvBG6D9r31jwEtU5sCzbJ79Hl2PhSM4cRJK20w502nqnuHwNfI7L4niGPumWEVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11e1dc3009a92a049c0df4c97a8c95a95637343d980b174564249ea2d601544a","last_reissued_at":"2026-05-26T01:03:30.314757Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:30.314757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HELO-APR: Enhancing Low-Resource Program Repair through Cross-Lingual Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Boyang Yang, Liuye Guo, Tao Zheng, Tieke He, Yidong Wan, You Lv, Zhipeng Wang, Zhuowei Wang","submitted_at":"2026-04-18T14:55:11Z","abstract_excerpt":"Large Language Models (LLMs) perform well on automatic program repair (APR) for high-resource programming languages (HRPLs), but their effectiveness drops sharply in low-resource programming languages (LRPLs), due to a lack of sufficient verified buggy-fixed pairs for APR training. To address this challenge, we propose HELO-APR (High-resource Enabled LOw-resource APR), a two-stage APR framework that enables cross-lingual transfer of repair knowledge from HRPLs to LRPLs. HELO-APR (1) constructs high-quality LRPL training data by synthesizing LRPL buggy-fixed pairs from HRPL counterparts, preser"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Using C++ as the source HRPL and Ruby and Rust as the target LRPLs, experiments on xCodeEval show that HELO-APR consistently outperforms strong baselines, increasing Pass@1 from 31.32% to 48.65% on DeepSeek-Coder-6.7B and from 1.67% to 11.97% on CodeLlama-7B, while improving syntactic validity by raising the average target compilation rate on CodeLlama from 49.77% to 91.98%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that synthesizing LRPL buggy-fixed pairs from HRPL counterparts can preserve defect type consistency while ensuring the synthesized code is idiomatic, which is required for the data construction stage to provide effective supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HELO-APR improves LLM-based automatic program repair in low-resource languages by synthesizing cross-lingual training data and using curriculum learning, raising Pass@1 from 31.32% to 48.65% on DeepSeek-Coder for Ruby/Rust targets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e3ac8e7e947544067d5a7cc502884fba2e4e99a5117b8cf36df218139dcf4dbc"},"source":{"id":"2604.17016","kind":"arxiv","version":2},"verdict":{"id":"a8aa1d5a-afa0-48cb-bcd1-86abdacf3ced","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T06:29:21.507469Z","strongest_claim":"Using C++ as the source HRPL and Ruby and Rust as the target LRPLs, experiments on xCodeEval show that HELO-APR consistently outperforms strong baselines, increasing Pass@1 from 31.32% to 48.65% on DeepSeek-Coder-6.7B and from 1.67% to 11.97% on CodeLlama-7B, while improving syntactic validity by raising the average target compilation rate on CodeLlama from 49.77% to 91.98%.","one_line_summary":"HELO-APR improves LLM-based automatic program repair in low-resource languages by synthesizing cross-lingual training data and using curriculum learning, raising Pass@1 from 31.32% to 48.65% on DeepSeek-Coder for Ruby/Rust targets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that synthesizing LRPL buggy-fixed pairs from HRPL counterparts can preserve defect type consistency while ensuring the synthesized code is idiomatic, which is required for the data construction stage to provide effective supervision.","pith_extraction_headline":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17016/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2604.17016","created_at":"2026-05-26T01:03:30.314890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.17016v2","created_at":"2026-05-26T01:03:30.314890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17016","created_at":"2026-05-26T01:03:30.314890+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHQ5YMAJVEVA","created_at":"2026-05-26T01:03:30.314890+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHQ5YMAJVEVAJHAN","created_at":"2026-05-26T01:03:30.314890+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHQ5YMAJ","created_at":"2026-05-26T01:03:30.314890+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/CHQ5YMAJVEVAJHAN6TEXVDEVVF","json":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF.json","graph_json":"https://pith.science/api/pith-number/CHQ5YMAJVEVAJHAN6TEXVDEVVF/graph.json","events_json":"https://pith.science/api/pith-number/CHQ5YMAJVEVAJHAN6TEXVDEVVF/events.json","paper":"https://pith.science/paper/CHQ5YMAJ"},"agent_actions":{"view_html":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF","download_json":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF.json","view_paper":"https://pith.science/paper/CHQ5YMAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.17016&json=true","fetch_graph":"https://pith.science/api/pith-number/CHQ5YMAJVEVAJHAN6TEXVDEVVF/graph.json","fetch_events":"https://pith.science/api/pith-number/CHQ5YMAJVEVAJHAN6TEXVDEVVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/action/storage_attestation","attest_author":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/action/author_attestation","sign_citation":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/action/citation_signature","submit_replication":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/action/replication_record"}},"created_at":"2026-05-26T01:03:30.314890+00:00","updated_at":"2026-05-26T01:03:30.314890+00:00"}