pith:COUQ6OIQ
Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing
Even with perfect data and training, limited capacity forces LLMs to assign high confidence to some non-facts
arxiv:2602.00906 v7 · 2026-01-31 · cs.LG · cs.AI · cs.CL · cs.DS · cs.IT · math.IT
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{COUQ6OIQ2YDCWRXVHSUW35EZKS}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
even with optimal training, perfect data, and a simplified closed world setting, the information-theoretically optimal strategy under limited capacity is not to abstain or forget, but to assign high confidence to some non-facts, resulting in hallucination.
The regime in which facts are sparse in the universe of plausible claims, together with the modeling choice that unifies discrete Bloom-filter error with continuous log-loss under a single rate-distortion objective.
Hallucinations are the space-optimal behavior for limited-capacity models performing membership testing on sparse facts, as shown by a rate-distortion theorem that equates optimal memory use to minimum KL divergence between fact and non-fact score distributions.
Formal links
Receipt and verification
| First computed | 2026-06-02T01:03:41.727527Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
13a90f3910d6062b46f53ca96df49954b8fd9a643c7b6c3a10203f560440d1fd
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/COUQ6OIQ2YDCWRXVHSUW35EZKS \
| 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: 13a90f3910d6062b46f53ca96df49954b8fd9a643c7b6c3a10203f560440d1fd
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "ded0d6a9ce377f077ab0fd83b96766f8267820895964baf8db5a43b51069eaf6",
"cross_cats_sorted": [
"cs.AI",
"cs.CL",
"cs.DS",
"cs.IT",
"math.IT"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-01-31T21:18:28Z",
"title_canon_sha256": "09c1a2f0b896d2323af97c5dfd4a990494b8d768f3a2d1265f5a5f067db8c74b"
},
"schema_version": "1.0",
"source": {
"id": "2602.00906",
"kind": "arxiv",
"version": 7
}
}