{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IVP2LCNRPD6ODXSHILT6TEQQ26","short_pith_number":"pith:IVP2LCNR","schema_version":"1.0","canonical_sha256":"455fa589b178fce1de4742e7e99210d7a248e1c960b44d0e129b84ed2e2d1151","source":{"kind":"arxiv","id":"2605.13896","version":1},"attestation_state":"computed","paper":{"title":"Neural Code Translation of Legacy Code: APL to C#","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Guided large language models translate APL legacy code to functional C# across program complexities","cross_cats":["cs.PL"],"primary_cat":"cs.SE","authors_text":"Abdulrahman Ramadan, Allan Peter Engsig-Karup, Hanen Borchani, Iben Lilholm, Mikkel Almind","submitted_at":"2026-05-12T12:11:33Z","abstract_excerpt":"Automatic translation between programming languages remains a challenging problem, particularly when the source language is highly concise and specialized. This paper investigates the translation of APL into C# using large language models. The task is difficult due to APL's sparse syntax, the scarcity of large-scale parallel corpora, and the requirement for specialized knowledge to interpret APL programs. To address these challenges, we introduce a novel framework for APL-to-C# translation by comparing three guided strategies, namely natural language description-mediated, retrieval-augmented, "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-12T12:11:33Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"407a2f00cefb1db40d5e7feffe1987c375d0d1cf9fee498a6c14faf3a95089af","abstract_canon_sha256":"d983d5e5394c6ce4c425f0a3b284900758da43b01f9cfe07b765a4031e6c3b4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:18.997945Z","signature_b64":"gg3RvqEhMu4LqLegz5TYSSv2hPKXigACRZpl77SjE/8vdZ6h+iYZeK6OCIFMO5eky7YMPruxWm2e/5Jr1EOzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"455fa589b178fce1de4742e7e99210d7a248e1c960b44d0e129b84ed2e2d1151","last_reissued_at":"2026-05-17T23:39:18.997182Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:18.997182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Code Translation of Legacy Code: APL to C#","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Guided large language models translate APL legacy code to functional C# across program complexities","cross_cats":["cs.PL"],"primary_cat":"cs.SE","authors_text":"Abdulrahman Ramadan, Allan Peter Engsig-Karup, Hanen Borchani, Iben Lilholm, Mikkel Almind","submitted_at":"2026-05-12T12:11:33Z","abstract_excerpt":"Automatic translation between programming languages remains a challenging problem, particularly when the source language is highly concise and specialized. This paper investigates the translation of APL into C# using large language models. The task is difficult due to APL's sparse syntax, the scarcity of large-scale parallel corpora, and the requirement for specialized knowledge to interpret APL programs. To address these challenges, we introduce a novel framework for APL-to-C# translation by comparing three guided strategies, namely natural language description-mediated, retrieval-augmented, "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results demonstrate that neural code translation can successfully bridge the gap between APL and C# for a wide range of programs, and that incorporating additional context and guidance significantly improves model performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The constructed datasets of functionally equivalent APL-C# pairs are representative of real-world legacy code and that the automated pipeline of compilation plus execution testing reliably detects functional equivalence without false positives.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Guided LLM strategies with custom datasets and execution-based verification enable functional APL-to-C# translation across a range of program complexities.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Guided large language models translate APL legacy code to functional C# across program complexities","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"79f8f4b360caf3ab285b5c16e23ba97903d56e08165fa58e64b0b789babef962"},"source":{"id":"2605.13896","kind":"arxiv","version":1},"verdict":{"id":"97678042-8275-43a4-8b34-e3c965d8cb47","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:22:01.318670Z","strongest_claim":"Our results demonstrate that neural code translation can successfully bridge the gap between APL and C# for a wide range of programs, and that incorporating additional context and guidance significantly improves model performance.","one_line_summary":"Guided LLM strategies with custom datasets and execution-based verification enable functional APL-to-C# translation across a range of program complexities.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The constructed datasets of functionally equivalent APL-C# pairs are representative of real-world legacy code and that the automated pipeline of compilation plus execution testing reliably detects functional equivalence without false positives.","pith_extraction_headline":"Guided large language models translate APL legacy code to functional C# across program complexities"},"references":{"count":34,"sample":[{"doi":"","year":2023,"title":"Attention Is All You Need","work_id":"baafb5a2-5272-43bc-932f-09fa9ffe5316","ref_index":1,"cited_arxiv_id":"1706.03762","is_internal_anchor":true},{"doi":"","year":2016,"title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","work_id":"e294e5a1-5dd2-44a0-b348-adbd62fe1916","ref_index":2,"cited_arxiv_id":"1609.08144","is_internal_anchor":true},{"doi":"","year":2023,"title":"Harvard Business School, Working Paper 24-013 (2023)","work_id":"333c7066-3821-439d-ad67-ec07d87fe132","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1962,"title":"Wiley (1962)","work_id":"270242de-07ce-4585-b204-5dc36f15fc28","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"arXiv preprint arXiv:2307.07686 (2023)","work_id":"50778016-eb65-4dde-bca6-0905ac8c41ab","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":34,"snapshot_sha256":"9a33c11ae94c37ff2374e8a34ce4efebd3fca8c71b03ddd2919177a9f27ec0a3","internal_anchors":7},"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":"2605.13896","created_at":"2026-05-17T23:39:18.997332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13896v1","created_at":"2026-05-17T23:39:18.997332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13896","created_at":"2026-05-17T23:39:18.997332+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVP2LCNRPD6O","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVP2LCNRPD6ODXSH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVP2LCNR","created_at":"2026-05-18T12:33:37.589309+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/IVP2LCNRPD6ODXSHILT6TEQQ26","json":"https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26.json","graph_json":"https://pith.science/api/pith-number/IVP2LCNRPD6ODXSHILT6TEQQ26/graph.json","events_json":"https://pith.science/api/pith-number/IVP2LCNRPD6ODXSHILT6TEQQ26/events.json","paper":"https://pith.science/paper/IVP2LCNR"},"agent_actions":{"view_html":"https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26","download_json":"https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26.json","view_paper":"https://pith.science/paper/IVP2LCNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13896&json=true","fetch_graph":"https://pith.science/api/pith-number/IVP2LCNRPD6ODXSHILT6TEQQ26/graph.json","fetch_events":"https://pith.science/api/pith-number/IVP2LCNRPD6ODXSHILT6TEQQ26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26/action/storage_attestation","attest_author":"https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26/action/author_attestation","sign_citation":"https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26/action/citation_signature","submit_replication":"https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26/action/replication_record"}},"created_at":"2026-05-17T23:39:18.997332+00:00","updated_at":"2026-05-17T23:39:18.997332+00:00"}