Pith Number

pith:RR35HHR3

pith:2026:RR35HHR3SSR64JGOS7543GP5Z2

not attested not anchored not stored refs resolved

Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization

Chen Shen, Huan Zhang, Jingyue Yang, Wei Cheng, Wei Hu, Yuhan Wu

A contrastively trained cross-lingual model supplies reliable semantic rewards for code translation inside direct preference optimization.

arxiv:2605.13229 v1 · 2026-05-13 · cs.AI · cs.SE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{RR35HHR3SSR64JGOS7543GP5Z2}

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

Through contrastive learning, we train a cross-lingual semantic model to directly assess functional equivalence between source and translated code. By formulating code translation as a multi-objective optimization problem, this robust semantic signal is seamlessly unified with compiler-based syntactic feedback within the direct preference optimization framework.

C2weakest assumption

A robust semantic reward for code translation must be derived directly from the source code via a contrastively trained cross-lingual model that accurately captures functional equivalence without test cases or reference translations.

C3one line summary

CTO improves code translation by training a semantic equivalence model through contrastive learning and unifying it with syntactic compiler feedback in a multi-objective direct preference optimization setup.

References

50 extracted · 50 resolved · 0 Pith anchors

[1] NeurIPS , year = 2020, pages = 2020

[2] ICSE , year = 2024, pages = 2024

[3] ICLR , year = 2022, pages = 2022

[4] ICLR , year = 2023, pages = 2023

[5] ASE , year = 2023, pages = 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:49.603180Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8c77d39e3b94a3ee24ce97fbcd99fdce9cf33e25db9facab778c90e059c6555b

Aliases

arxiv: 2605.13229 · arxiv_version: 2605.13229v1 · doi: 10.48550/arxiv.2605.13229 · pith_short_12: RR35HHR3SSR6 · pith_short_16: RR35HHR3SSR64JGO · pith_short_8: RR35HHR3

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/RR35HHR3SSR64JGOS7543GP5Z2 \
  | 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: 8c77d39e3b94a3ee24ce97fbcd99fdce9cf33e25db9facab778c90e059c6555b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9ea870095e492d672e296c3d73d3d11d9d3e9b71d8ef8ca681e4847ef4bb619d",
    "cross_cats_sorted": [
      "cs.SE"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T09:19:39Z",
    "title_canon_sha256": "bfa47f7ff6d8fcedf058a50d520f791ff9308234d1a2f2df080e78e9d2f57b41"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13229",
    "kind": "arxiv",
    "version": 1
  }
}