pith. sign in
Pith Number

pith:WVCPJ7DF

pith:2026:WVCPJ7DFE2VY4HPZU2G4CROND4
not attested not anchored not stored refs pending

Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B

Abay Bektursun

Frozen text-pretrained transformer weights transfer to robotic and memory tasks through a thin trainable interface without modifying the core model.

arxiv:2605.00333 v2 · 2026-05-01 · cs.LG · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{WVCPJ7DFE2VY4HPZU2G4CROND4}

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

Frozen Gemma 4 31B weights pretrained exclusively on text tokens, unmodified, transfer across modality boundaries through a thin trainable interface.

C2weakest assumption

That the geometry captured by text-only pretraining remains useful and transferable to non-text modalities without any modification to the core frozen weights.

C3one line summary

Frozen text-pretrained transformer weights transfer across modalities through a thin interface, achieving SOTA on a robotic task and parity on decision-making with far fewer trainable parameters.

Receipt and verification
First computed 2026-05-20T01:05:14.867261Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

b544f4fc6526ab8e1df9a68dc145cd1f2b01c9cf294eae838dc1cda66159d5a7

Aliases

arxiv: 2605.00333 · arxiv_version: 2605.00333v2 · doi: 10.48550/arxiv.2605.00333 · pith_short_12: WVCPJ7DFE2VY · pith_short_16: WVCPJ7DFE2VY4HPZ · pith_short_8: WVCPJ7DF
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/WVCPJ7DFE2VY4HPZU2G4CROND4 \
  | 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: b544f4fc6526ab8e1df9a68dc145cd1f2b01c9cf294eae838dc1cda66159d5a7
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "c42832faa1011e543464576bba8cdbfe5f0e9aaea9274cbf7c22b3b5121c35df",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-01T01:23:37Z",
    "title_canon_sha256": "b90d0fe3051a66c4bdbdf8f7076876895ec97d5ccca464eb5c6fec71f83d6de2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.00333",
    "kind": "arxiv",
    "version": 2
  }
}