Pith Number
pith:H52DLYJ5
pith:2026:H52DLYJ5RKWIPJADHZ36262HXI
not attested
not anchored
not stored
refs resolved
Exploring Geographic Relative Space in Large Language Models through Activation Patching
Large language models encode relative geographic space in patterns isolatable by activation patching.
arxiv:2605.14535 v1 · 2026-05-14 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{H52DLYJ5RKWIPJADHZ36262HXI}
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
· sign in to
claim
4
Citations
5
Replications
✓
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 examine how LLMs process relative geographic space using activation patching, an emerging tool for mechanistic interpretability.
C2weakest assumption
That activation patching can meaningfully isolate and reveal the mechanisms by which LLMs represent relative geographic space.
C3one line summary
Activation patching is used to explore how LLMs encode relative geographic relationships.
References
[1] Geospatial Mechanistic Interpretability of Large Language Models , author=. 2025 , eprint=
[2] Computing Geographically: Bridging Giscience and Geography , author=. 2024 , publisher=
[3] Locating and Editing Factual Associations in GPT , volume =
[4] Investigating Gender Bias in Language Models Using Causal Mediation Analysis , volume =
[5] Towards Best Practices of Activation Patching in Language Models: Metrics and Methods , author=. 2024 , eprint=
Formal links
Receipt and verification
| First computed | 2026-05-17T23:39:05.896196Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
3f7435e13d8aac87a4033e77ed7b47ba1cb9f482cd692e447eb5924741003fe7
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/H52DLYJ5RKWIPJADHZ36262HXI \
| 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: 3f7435e13d8aac87a4033e77ed7b47ba1cb9f482cd692e447eb5924741003fe7
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "fffae026f5dbd0c2dedeb494dd683b1d315ff8c5ea7f48ab2ce122c8e141cb95",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-14T08:18:31Z",
"title_canon_sha256": "d4800f9b7aa5673c5ce0e6892ee910f27c7f6e4d47e68e9a3d77983ca7b105a1"
},
"schema_version": "1.0",
"source": {
"id": "2605.14535",
"kind": "arxiv",
"version": 1
}
}