Pith Number

pith:U5D6HC2V

pith:2026:U5D6HC2VS2GCHQZBKOXHVRDGSN

not attested not anchored not stored refs pending

Not All Entities are Created Equal: A Dynamic Anonymization Framework for Privacy-Preserving Retrieval-Augmented Generation

Enye Wang, Guo Jia, Qingkai Zeng, Ruijie Wang, Ruiqi He, Xinyuan Zhu, Zekun Fei, Zheli Liu

TRIP-RAG dynamically selects only high-risk entities for anonymization in RAG knowledge bases by scoring marginal privacy risk, knowledge divergence, and topical relevance.

arxiv:2603.26074 v2 · 2026-03-27 · cs.CR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{U5D6HC2VS2GCHQZBKOXHVRDGSN}

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

While maintaining privacy protection comparable to full anonymization, TRIP-RAG's Recall@k decreases by less than 35% compared to the original data, and the generation quality improves by up to 56% over existing baselines; theoretical analysis and experiments indicate it can effectively reduce context inference risks.

C2weakest assumption

That the three context-aware metrics (marginal privacy risk, knowledge divergence, topical relevance) can be reliably quantified and combined to correctly identify only the truly high-risk entities without missing leaks or over-anonymizing useful content.

C3one line summary

TRIP-RAG dynamically anonymizes only high-risk entities in RAG knowledge bases via three context-aware metrics, achieving privacy comparable to full anonymization with under 35% recall drop and up to 56% better generation quality than baselines.

Receipt and verification

First computed	2026-05-18T02:44:30.631449Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a747e38b55968c23c32153ae7ac466934b7c05785097fe084e950df749c2c5cb

Aliases

arxiv: 2603.26074 · arxiv_version: 2603.26074v2 · doi: 10.48550/arxiv.2603.26074 · pith_short_12: U5D6HC2VS2GC · pith_short_16: U5D6HC2VS2GCHQZB · pith_short_8: U5D6HC2V

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/U5D6HC2VS2GCHQZBKOXHVRDGSN \
  | 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: a747e38b55968c23c32153ae7ac466934b7c05785097fe084e950df749c2c5cb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e3e1a88f01cfd624ccf1609bcc28ba042780ce37c6275038a1b03d51f77a4496",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-03-27T05:03:24Z",
    "title_canon_sha256": "9ae9ca29dec8f34b6d995c3d1caedfcc8522b8df91994811a3f297269d23e04d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.26074",
    "kind": "arxiv",
    "version": 2
  }
}