pith. sign in
Pith Number

pith:LPH6T5NM

pith:2026:LPH6T5NM6EZ3BVPTSI7NPVSVZ6
not attested not anchored not stored refs pending

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure

Chenchen Tan, Cunjian Chen, Longxiang Gao, Shujie Cui, Xinghao Li, Youyang Qu

Geometric Unlearning lets LLMs forget specific private facts using only a handful of synthetic prompts while retaining general performance.

arxiv:2605.01735 v2 · 2026-05-03 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{LPH6T5NM6EZ3BVPTSI7NPVSVZ6}

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

Across privacy-oriented unlearning benchmarks (ToFU and UnlearnPII), GU achieves strong target suppression with minimal impact on non-target performance, demonstrating that effective unlearning can be achieved with minimal synthetic data.

C2weakest assumption

The assumption that a compact low-rank geometry distilled from safe reference prompts, combined with projection-based alignment using synthetic anchors, can effectively suppress target information in the model's hidden states without access to the original training corpus or significant utility loss.

C3one line summary

Geometric Unlearning suppresses specific knowledge in LLMs by projecting hidden planning states onto a low-rank safe geometry derived from minimal reference prompts.

Receipt and verification
First computed 2026-05-28T01:05:12.457391Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

5bcfe9f5acf133b0d5f3923ed7d655cfbddc63545e95bdba97fcc61944227ad5

Aliases

arxiv: 2605.01735 · arxiv_version: 2605.01735v2 · doi: 10.48550/arxiv.2605.01735 · pith_short_12: LPH6T5NM6EZ3 · pith_short_16: LPH6T5NM6EZ3BVPT · pith_short_8: LPH6T5NM
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/LPH6T5NM6EZ3BVPTSI7NPVSVZ6 \
  | 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: 5bcfe9f5acf133b0d5f3923ed7d655cfbddc63545e95bdba97fcc61944227ad5
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "cd49f95c3619721b41c2f54a7b45db22a147bc8f16cb6f123b2c130f4fe60b06",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-03T06:20:03Z",
    "title_canon_sha256": "d0dca146ca6ae22b09ad7a3a1b68227629cf8b01ce07edf5f79e8523fbec5cb9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.01735",
    "kind": "arxiv",
    "version": 2
  }
}