pith:LVEOBLVN
ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
ScrapMem lets LLM agents keep long-term multimodal memories on edge devices by progressively lowering the resolution of old entries.
arxiv:2605.03804 v2 · 2026-05-05 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{LVEOBLVNVDJSRZVH5QMRJFSNTN}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
ScrapMem provides three main benefits: (1) strong performance, achieving a new state-of-the-art with a 51.0% Joint@10 score; (2) high storage efficiency, reducing memory usage by up to 93% via optical forgetting; and (3) improved recall, increasing Recall@10 to 70.3% through structured aggregation.
That progressively lowering resolution of older memories via optical forgetting preserves semantic consistency and that the Episodic Memory Graph maintains causal-temporal structure without introducing errors or losing critical multimodal details.
ScrapMem introduces optical forgetting to compress multimodal memories for LLM agents on edge devices, cutting storage by up to 93% while reaching 51.0% Joint@10 and 70.3% Recall@10 on ATM-Bench.
Receipt and verification
| First computed | 2026-05-26T02:04:11.967474Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
5d48e0aeada8d328e6a7ec1914964d9b5a69169d60ac1ef1d9d2529ad90acf68
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/LVEOBLVNVDJSRZVH5QMRJFSNTN \
| 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: 5d48e0aeada8d328e6a7ec1914964d9b5a69169d60ac1ef1d9d2529ad90acf68
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "c9e60c6f3912befc56b2b39411b9519674c7df04953bc4b1469241bc0e50b30e",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-05T14:30:30Z",
"title_canon_sha256": "7c77391bb2ede1aad0d1f6a2f3900b9fca862bc02bb10bbc2a7f73379a6b99a0"
},
"schema_version": "1.0",
"source": {
"id": "2605.03804",
"kind": "arxiv",
"version": 2
}
}