Pith Number

pith:T5TAHX3B

pith:2025:T5TAHX3BRVAQGEPVQ32ZLBHQAA

not attested not anchored not stored refs resolved

From RAG to Memory: Non-Parametric Continual Learning for Large Language Models

Bernal Jim\'enez Guti\'errez, Sizhe Zhou, Weijian Qi, Yiheng Shu, Yu Su

HippoRAG 2 enhances Personalized PageRank with deeper passage integration and online LLM use to outperform standard RAG on factual, sense-making, and associative memory tasks.

arxiv:2502.14802 v2 · 2025-02-20 · cs.CL · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{T5TAHX3BRVAQGEPVQ32ZLBHQAA}

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

HippoRAG 2 ... achieving a 7% improvement in associative memory tasks over the state-of-the-art embedding model while also exhibiting superior factual knowledge and sense-making memory capabilities.

C2weakest assumption

That the specific enhancements to passage integration depth and online LLM usage in the Personalized PageRank process are what drive the reported gains and that the chosen memory-task benchmarks accurately reflect the dynamic, interconnected nature of human long-term memory.

C3one line summary

HippoRAG 2 improves on standard RAG and prior HippoRAG by adding deeper passage integration and more effective LLM use in Personalized PageRank, delivering superior performance on factual, sense-making, and associative memory tasks including a 7% gain in associative memory over state-of-the-art.

References

11 extracted · 11 resolved · 2 Pith anchors

[1] LightRAG: Simple and Fast Retrieval-Augmented Generation 2024 · arXiv:2410.05779

[2] In: Proceedings of the 11th international conference on World Wide Web (WWW) 2002 · doi:10.1145/511446.511513

[3] Mitigating catastrophic forgetting in large language models with self-synthesized rehearsal 2023 · doi:10.18653/v1/2024.acl-long.77

[4] Towards General Text Embeddings with Multi-stage Contrastive Learning 2024 · doi:10.18653/v1/2024

[5] Red Teaming Language Models with Language Models.Proceedings of EMNLP 2022, pp 2022 · doi:10.18653/v1/2022.emnlp-main

Formal links

3 machine-checked theorem links

Cited by

23 papers in Pith

SeedER: Seed-and-Expand Retrieval from Knowledge Graphs

PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments

Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems

G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge

Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation

Receipt and verification

First computed	2026-05-17T23:38:45.966151Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9f6603df618d410311f586f59584f000182d65814519a5232ba48889ea3049bf

Aliases

arxiv: 2502.14802 · arxiv_version: 2502.14802v2 · doi: 10.48550/arxiv.2502.14802 · pith_short_12: T5TAHX3BRVAQ · pith_short_16: T5TAHX3BRVAQGEPV · pith_short_8: T5TAHX3B

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/T5TAHX3BRVAQGEPVQ32ZLBHQAA \
  | 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: 9f6603df618d410311f586f59584f000182d65814519a5232ba48889ea3049bf

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f654d7b685b2fe89159830b4af05295abf0236d8455be59c85157462e84296a5",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-02-20T18:26:02Z",
    "title_canon_sha256": "328069aa3c1ce500a395303508bcebfdd7e0f9d727dec094984ce4c47707d8eb"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.14802",
    "kind": "arxiv",
    "version": 2
  }
}