{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CHQ5YMAJVEVAJHAN6TEXVDEVVF","short_pith_number":"pith:CHQ5YMAJ","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"},"canonical_sha256":"11e1dc3009a92a049c0df4c97a8c95a95637343d980b174564249ea2d601544a","source":{"kind":"arxiv","id":"2604.17016","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17016","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17016v2","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17016","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"CHQ5YMAJVEVA","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"CHQ5YMAJVEVAJHAN","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"CHQ5YMAJ","created_at":"2026-05-26T01:03:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CHQ5YMAJVEVAJHAN6TEXVDEVVF","target":"record","payload":{"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"},"canonical_sha256":"11e1dc3009a92a049c0df4c97a8c95a95637343d980b174564249ea2d601544a","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"},"source_kind":"arxiv","source_id":"2604.17016","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2C+htk3lLoqoWdfzz0EvFcXR4dKl5FOvEumuIsZFyDV0RsWME5uxTgTKQUwDHz3sBAX/SMlmuqFMgHLIMX3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:33:21.016186Z"},"content_sha256":"702aa2c142e8c60b86c995b264979d61f98a46d2e5880e3b1e01a957ce6291aa","schema_version":"1.0","event_id":"sha256:702aa2c142e8c60b86c995b264979d61f98a46d2e5880e3b1e01a957ce6291aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CHQ5YMAJVEVAJHAN6TEXVDEVVF","target":"graph","payload":{"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"},"verdict_id":"a8aa1d5a-afa0-48cb-bcd1-86abdacf3ced"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z7QB5yKvzmjiRif1iNNeiGy356f3/KJdriCz7kJzkp/7Qw0bwbpeExKDkFZBhiTrPUb1uyZm5lOe5UOzndzEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:33:21.016671Z"},"content_sha256":"4f9f3a6b0dba495628b95539c51d08ff3bf3b6d0a5a037a463ffd7fb84ba1a6f","schema_version":"1.0","event_id":"sha256:4f9f3a6b0dba495628b95539c51d08ff3bf3b6d0a5a037a463ffd7fb84ba1a6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/bundle.json","state_url":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T01:33:21Z","links":{"resolver":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF","bundle":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/bundle.json","state":"https://pith.science/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CHQ5YMAJVEVAJHAN6TEXVDEVVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CHQ5YMAJVEVAJHAN6TEXVDEVVF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c916f14ece20d2160ff43bd6f62e8df00218e1587d1b666e426cfe8f7453ab5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-04-18T14:55:11Z","title_canon_sha256":"c027bc053bcaff1abefdc79161e815c57e73202564579f4d01825063c149f4bd"},"schema_version":"1.0","source":{"id":"2604.17016","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17016","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17016v2","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17016","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"CHQ5YMAJVEVA","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"CHQ5YMAJVEVAJHAN","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"CHQ5YMAJ","created_at":"2026-05-26T01:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:4f9f3a6b0dba495628b95539c51d08ff3bf3b6d0a5a037a463ffd7fb84ba1a6f","target":"graph","created_at":"2026-05-26T01:03:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama."}],"snapshot_sha256":"e3ac8e7e947544067d5a7cc502884fba2e4e99a5117b8cf36df218139dcf4dbc"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.17016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Boyang Yang, Liuye Guo, Tao Zheng, Tieke He, Yidong Wan, You Lv, Zhipeng Wang, Zhuowei Wang","cross_cats":[],"headline":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-04-18T14:55:11Z","title":"HELO-APR: Enhancing Low-Resource Program Repair through Cross-Lingual Knowledge Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.17016","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T06:29:21.507469Z","id":"a8aa1d5a-afa0-48cb-bcd1-86abdacf3ced","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama.","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%.","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."}},"verdict_id":"a8aa1d5a-afa0-48cb-bcd1-86abdacf3ced"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:702aa2c142e8c60b86c995b264979d61f98a46d2e5880e3b1e01a957ce6291aa","target":"record","created_at":"2026-05-26T01:03:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c916f14ece20d2160ff43bd6f62e8df00218e1587d1b666e426cfe8f7453ab5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-04-18T14:55:11Z","title_canon_sha256":"c027bc053bcaff1abefdc79161e815c57e73202564579f4d01825063c149f4bd"},"schema_version":"1.0","source":{"id":"2604.17016","kind":"arxiv","version":2}},"canonical_sha256":"11e1dc3009a92a049c0df4c97a8c95a95637343d980b174564249ea2d601544a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11e1dc3009a92a049c0df4c97a8c95a95637343d980b174564249ea2d601544a","first_computed_at":"2026-05-26T01:03:30.314757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:30.314757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nlQt3xYteDoDDoiEu0hXJkBvBG6D9r31jwEtU5sCzbJ79Hl2PhSM4cRJK20w502nqnuHwNfI7L4niGPumWEVBg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:30.315744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.17016","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:702aa2c142e8c60b86c995b264979d61f98a46d2e5880e3b1e01a957ce6291aa","sha256:4f9f3a6b0dba495628b95539c51d08ff3bf3b6d0a5a037a463ffd7fb84ba1a6f"],"state_sha256":"3eed570e07bc9b4b4a6c410a1e4cc352a7d464e742dac927f0fce223250ebc4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGXBq3YnF3TMD/9xA9qE8asWRm8pxXFQMdVNXUQ3sSDemienCZQsZEMpsmkXUP5pXB5gGZdneb5MQqTgHDVUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T01:33:21.018912Z","bundle_sha256":"b205b3ba43bd143cd0c951851d2359fe36f6d2dfb1ad05fbf6ebdf15a9543bec"}}