Pith Number

pith:WQ3MBGKQ

pith:2026:WQ3MBGKQNBC3HINPMHCPFO7HXP

not attested not anchored not stored refs pending

Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining

Barbara Plank, Felicia K\"orner, Florian Eichin, Gitta Kutyniok, Maria Matveev, Michael A. Hedderich

In multilingual pretraining, models first copy tokens before developing general translation abilities.

arxiv:2604.17633 v2 · 2026-04-19 · 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{WQ3MBGKQNBC3HINPMHCPFO7HXP}

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 find that the model quickly acquires basic linguistic capabilities in parallel with token-level copying, while translation develops in two distinct phases: an initial phase dominated by copying and surface-level similarities, and a second phase in which more generalizing translation mechanisms are developed while copying is refined.

C2weakest assumption

The behavioral analyses, model-component inspections, and parameter-based ablations on the chosen checkpoints and novel dataset accurately isolate translation dynamics from confounding factors such as data overlap or model architecture specifics.

C3one line summary

Multilingual pretraining develops translation in two phases: early copying driven by surface similarities, followed by generalizing mechanisms while copying is refined.

Receipt and verification

First computed	2026-06-29T01:14:31.301956Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b436c099506845b3a1af61c4f2bbe7bbf7dc94eaf82729b430158303d1b2072b

Aliases

arxiv: 2604.17633 · arxiv_version: 2604.17633v2 · doi: 10.48550/arxiv.2604.17633 · pith_short_12: WQ3MBGKQNBC3 · pith_short_16: WQ3MBGKQNBC3HINP · pith_short_8: WQ3MBGKQ

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/WQ3MBGKQNBC3HINPMHCPFO7HXP \
  | 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: b436c099506845b3a1af61c4f2bbe7bbf7dc94eaf82729b430158303d1b2072b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "26ecc0725eb1d5d23b9592e66c2c085489973cc5e00cd72c346a18720ea05657",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-19T22:03:29Z",
    "title_canon_sha256": "bf9a95b979750584e07a21384d86edfc4ed095fff75093558bfb7eecabe4580f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.17633",
    "kind": "arxiv",
    "version": 2
  }
}