Pith Number

pith:IVP2LCNR

pith:2026:IVP2LCNRPD6ODXSHILT6TEQQ26

not attested not anchored not stored refs resolved

Neural Code Translation of Legacy Code: APL to C#

Abdulrahman Ramadan, Allan Peter Engsig-Karup, Hanen Borchani, Iben Lilholm, Mikkel Almind

Guided large language models translate APL legacy code to functional C# across program complexities

arxiv:2605.13896 v1 · 2026-05-12 · cs.SE · cs.PL

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IVP2LCNRPD6ODXSHILT6TEQQ26}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest 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.

C2weakest 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.

C3one line summary

Guided LLM strategies with custom datasets and execution-based verification enable functional APL-to-C# translation across a range of program complexities.

References

34 extracted · 34 resolved · 7 Pith anchors

[1] Attention Is All You Need 2023 · arXiv:1706.03762

[2] Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 2016 · arXiv:1609.08144

[3] Harvard Business School, Working Paper 24-013 (2023) 2023

[4] Wiley (1962) 1962

[5] arXiv preprint arXiv:2307.07686 (2023) 2023

Receipt and verification

First computed	2026-05-17T23:39:18.997182Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

455fa589b178fce1de4742e7e99210d7a248e1c960b44d0e129b84ed2e2d1151

Aliases

arxiv: 2605.13896 · arxiv_version: 2605.13896v1 · doi: 10.48550/arxiv.2605.13896 · pith_short_12: IVP2LCNRPD6O · pith_short_16: IVP2LCNRPD6ODXSH · pith_short_8: IVP2LCNR

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/IVP2LCNRPD6ODXSHILT6TEQQ26 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 455fa589b178fce1de4742e7e99210d7a248e1c960b44d0e129b84ed2e2d1151

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d983d5e5394c6ce4c425f0a3b284900758da43b01f9cfe07b765a4031e6c3b4c",
    "cross_cats_sorted": [
      "cs.PL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-12T12:11:33Z",
    "title_canon_sha256": "407a2f00cefb1db40d5e7feffe1987c375d0d1cf9fee498a6c14faf3a95089af"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13896",
    "kind": "arxiv",
    "version": 1
  }
}