Pith Number

pith:LRYPOV6G

pith:2026:LRYPOV6GKFZKCVQ7DLOLENAJXD

not attested not anchored not stored refs resolved

MeMo: Memory as a Model

Alfred Wei Lun Leong, Alok Prakash, Armando Solar-Lezama, Arun Verma, Bryan Kian Hsiang Low, Daniela Rus, Nancy F. Chen, Ryan Wei Heng Quek, Sanghyuk Lee

A dedicated memory model encodes new knowledge so LLMs can use it without changing parameters or retraining.

arxiv:2605.15156 v1 · 2026-05-14 · cs.CL · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LRYPOV6GKFZKCVQ7DLOLENAJXD}

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

MeMo offers several advantages: (a) it captures complex cross-document relationships, (b) it is robust to retrieval noise, (c) it avoids catastrophic forgetting in the LLM, (d) it does not require access to the LLM's weights or output logits, enabling plug-and-play integration with both open and proprietary closed-source LLMs, and (e) its retrieval cost is independent of corpus size at inference time.

C2weakest assumption

The assumption that a dedicated memory model can reliably encode and retrieve complex cross-document knowledge without any access to the LLM's internal weights or logits, and that this separation delivers the claimed robustness and performance gains on the tested benchmarks.

C3one line summary

MeMo encodes new knowledge into a separate memory model for frozen LLMs, achieving strong performance on BrowseComp-Plus, NarrativeQA, and MuSiQue while capturing cross-document relationships and remaining robust to retrieval noise.

References

85 extracted · 85 resolved · 17 Pith anchors

[1] Large Language Models are Zero-Shot Reasoners 2023 · arXiv:2205.11916

[2] A Survey of Large Language Models 2023 · arXiv:2303.18223

[3] A survey on large language models for code generation.ACM Transactions on Software Engineering and Method- ology, 2026 2026

[4] Knowledge conflicts for LLMs : A survey 2024

[5] Dated data: Tracing knowledge cutoffs in large language models 2024

Receipt and verification

First computed	2026-05-17T21:40:25.437468Z
Last reissued	2026-05-17T21:57:18.760051Z
Builder	pith-number-builder-2026-05-17-v1
Signature	unsigned_v0
Schema	pith-number/v1.0

Canonical hash

5c70f757c65172a1561f1adcb23409b8de092099ac8dfe652bfde395b50341e6

Aliases

arxiv: 2605.15156 · arxiv_version: 2605.15156v1 · pith_short_12: LRYPOV6GKFZK · pith_short_16: LRYPOV6GKFZKCVQ7 · pith_short_8: LRYPOV6G

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/LRYPOV6GKFZKCVQ7DLOLENAJXD \
  | 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: 5c70f757c65172a1561f1adcb23409b8de092099ac8dfe652bfde395b50341e6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4511675e7d58b801544f6e7768af3f8c6f11125fead76befb43a5284f634ae01",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-14T17:51:34Z",
    "title_canon_sha256": "cd6ce2f1a7fc1a5ed18488a41b28cb6182d5e90cffaf86c28e62050de8efb577"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15156",
    "kind": "arxiv",
    "version": 1
  }
}