pith. sign in
Pith Number

pith:YVLLQUFL

pith:2026:YVLLQUFLYQ5IARVFRFUNYX4EQH
not attested not anchored not stored refs pending

When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models

Abhishek Upperwal, Mayank Singh, Pritam Kadasi, Sailesh Panda

LLMs lose accuracy on following multi-step arithmetic procedures as length grows from 5 to 95 steps.

arxiv:2605.00817 v2 · 2026-05-01 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{YVLLQUFLYQ5IARVFRFUNYX4EQH}

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

Across 14 models and 55 datasets, average first-answer accuracy drops from 61% on 5-step procedures to 20% on 95-step procedures.

C2weakest assumption

That the measured accuracy drop reflects failures of procedural fidelity rather than unrelated factors such as context-window limits, arithmetic capability, or prompt formatting.

C3one line summary

LLM accuracy on controlled procedural arithmetic drops from 61% at 5 steps to 20% at 95 steps, with failures including skipped steps, premature answers, and hallucinated operations.

Receipt and verification
First computed 2026-05-22T01:04:03.936329Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

c556b850abc43a8046a58968dc5f8481c1fa3e0421bd2948b31121bbb0fa1dd5

Aliases

arxiv: 2605.00817 · arxiv_version: 2605.00817v2 · doi: 10.48550/arxiv.2605.00817 · pith_short_12: YVLLQUFLYQ5I · pith_short_16: YVLLQUFLYQ5IARVF · pith_short_8: YVLLQUFL
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/YVLLQUFLYQ5IARVFRFUNYX4EQH \
  | 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: c556b850abc43a8046a58968dc5f8481c1fa3e0421bd2948b31121bbb0fa1dd5
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "22dee1d81089a51a767edbb4cc74cbe1aff0ce3c780e9934232ed5424f06c492",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-01T17:55:47Z",
    "title_canon_sha256": "304992a20482eb25a54260df7b77e4d59301518ef19be62c90933ffa0fdc90bd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.00817",
    "kind": "arxiv",
    "version": 2
  }
}