pith:IW3VIUTT
Algorithmic Blindness in Large Language Models: A Calibration Study of Performance Prediction
Large language models exhibit systematic failure at predicting algorithmic outcomes despite knowing algorithm facts.
arxiv:2602.21947 v5 · 2026-02-25 · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{IW3VIUTTAZXJV5WNFJ5SN5FY4U}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We find systematic, near-total failure across models. The predicted ranges are far wider than true confidence intervals yet still fail to contain the true algorithmic mean in most cases. Most models perform worse than random guessing and the best model's marginal improvement is attributable to benchmark memorization rather than principled reasoning.
That performance on causal discovery tasks constitutes a valid and generalizable test of algorithmic reasoning ability rather than a narrow or confounded proxy.
LLMs exhibit algorithmic blindness, producing predictions whose ranges miss true algorithmic means in most cases and often perform worse than random guessing.
Receipt and verification
| First computed | 2026-07-28T01:22:30.388470Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
45b7545273066e9af6cd2a7b26f4b8e50fded2c25b5620de1dd6f293096be22c
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/IW3VIUTTAZXJV5WNFJ5SN5FY4U \
| 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: 45b7545273066e9af6cd2a7b26f4b8e50fded2c25b5620de1dd6f293096be22c
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "8cba68210066087d5ea0ad0b49dae0ff41901c5d32fee6cfe3046bab57a2a2f1",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-02-25T14:32:15Z",
"title_canon_sha256": "438db4d5b341362553dfc592b579c836629a2fb5d41bd991285198e03575af59"
},
"schema_version": "1.0",
"source": {
"id": "2602.21947",
"kind": "arxiv",
"version": 5
}
}