Pith Number

pith:4NEZIZX6

pith:2026:4NEZIZX6OXML22CB5SLZ526733

not attested not anchored not stored refs resolved

Fluency and Faithfulness in Human and Machine Literary Translation

Sarah Griebel, Ted Underwood

Literary translations that sound more natural in the target language tend to preserve less of the source meaning.

arxiv:2605.15282 v1 · 2026-05-14 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{4NEZIZX6OXML22CB5SLZ526733}

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

We control for paragraph length and find a consistent negative correlation between fluency and faithfulness. The pattern appears for both human and Google Translate, but is weaker and often non-significant for TranslateGemma.

C2weakest assumption

That the paragraph-level POS n-gram translationese classifier validly measures target-language fluency and that COMET-KIWI validly measures semantic faithfulness specifically for literary novel paragraphs (as opposed to other text genres).

C3one line summary

Large-scale analysis of literary translations reveals a consistent negative correlation between fluency (measured via POS n-gram translationese classifier) and faithfulness (COMET-KIWI), controlled for length, across human and machine systems.

References

12 extracted · 12 resolved · 1 Pith anchors

[1] InFindings of the Asso- ciation for Computational Linguistics: ACL 2024, pages 2318–2335, Bangkok, Thailand 2024

[2] ArXiv:2601.09012 [cs]

[3] ArXiv:2210.13746 [cs]

[4] InProceedings of the International Conference Recent Advances in Natural Language Processing 2011, pages 634–639, Hissar, Bulgaria 2011

[5] arXiv preprint

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:50.542186Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e3499466fe75d8bd6841ec979eebdfdeffb42abd848dd95d32db1ad2cc5c6f3a

Aliases

arxiv: 2605.15282 · arxiv_version: 2605.15282v1 · doi: 10.48550/arxiv.2605.15282 · pith_short_12: 4NEZIZX6OXML · pith_short_16: 4NEZIZX6OXML22CB · pith_short_8: 4NEZIZX6

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/4NEZIZX6OXML22CB5SLZ526733 \
  | 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: e3499466fe75d8bd6841ec979eebdfdeffb42abd848dd95d32db1ad2cc5c6f3a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6e20492dd975a541ba4b7c3a0990ef1a93b62602f1e79db7b73f91434b6fb9ef",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-14T18:00:34Z",
    "title_canon_sha256": "c54bf4aceb1ea589c04a894e41303db515d11806602152bedd4c34b546894369"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15282",
    "kind": "arxiv",
    "version": 1
  }
}