Pith Number

pith:WACISFZT

pith:2023:WACISFZT37RK7MX3HVULZXPOZG

not attested not anchored not stored refs resolved

MemoryBank: Enhancing Large Language Models with Long-Term Memory

He Ye, Lianghong Guo, Qiqi Gao, Wanjun Zhong, Yanlin Wang

MemoryBank equips large language models with a long-term memory system modeled on human forgetting.

arxiv:2305.10250 v3 · 2023-05-17 · 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{WACISFZT37RK7MX3HVULZXPOZG}

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

MemoryBank enables the models to summon relevant memories, continually evolve through continuous memory updates, comprehend, and adapt to a user personality by synthesizing information from past interactions.

C2weakest assumption

The assumption that incorporating the Ebbinghaus Forgetting Curve will allow the AI to selectively preserve memory in a way that improves long-term interaction without introducing errors or forgetting critical information.

C3one line summary

MemoryBank equips LLMs with long-term memory using Ebbinghaus-inspired updates, allowing recall and personality adaptation in chatbots like SiliconFriend.

References

12 extracted · 12 resolved · 8 Pith anchors

[1] Language models are few-shot learners 1901

[2] PaLM: Scaling Language Modeling with Pathways · arXiv:2204.02311

[3] Scaling Instruction-Finetuned Language Models · arXiv:2210.11416

[4] Neural Turing Machines · arXiv:1410.5401

[5] Dense Passage Retrieval for Open-Domain Question Answering 2004 · arXiv:2004.04906

Formal links

3 machine-checked theorem links

Cited by

32 papers in Pith

CALMem : Application-Layer Dual Memory for Conversational AI

Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery

PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning

Episodic-Semantic Memory Architecture for Long-Horizon Scientific Agents

A Comprehensive Overview of Large Language Models

Receipt and verification

First computed	2026-05-17T23:38:48.713627Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b004891733dfe2afb2fb3d68bcddeec9af197edb5b1ad6b80dbc6426484018a1

Aliases

arxiv: 2305.10250 · arxiv_version: 2305.10250v3 · doi: 10.48550/arxiv.2305.10250 · pith_short_12: WACISFZT37RK · pith_short_16: WACISFZT37RK7MX3 · pith_short_8: WACISFZT

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/WACISFZT37RK7MX3HVULZXPOZG \
  | 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: b004891733dfe2afb2fb3d68bcddeec9af197edb5b1ad6b80dbc6426484018a1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "361bc1388846349fde1c40739e3567dc6f692fcc81fc8a2d37ed502975a9321a",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-05-17T14:40:29Z",
    "title_canon_sha256": "91eae365ea37dc8001f62964a5c5e4a781a449a9f63af80679afde491359c7b1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.10250",
    "kind": "arxiv",
    "version": 3
  }
}