Pith. sign in
Pith Number

pith:WBJQQUX3

pith:2026:WBJQQUX3HD72QTWS7VASMO66AG
not attested not anchored not stored refs pending

When Direct Prediction Fails: Evidence from LLM-Based Misinformation Risk Evaluation

Xiang Zheng, Xingjun Ma, Yutao Wu, Zonghuan Xu

LLM judges for disinformation risk form a coherent group more aligned with each other than with human readers.

arxiv:2604.06820 v2 · 2026-04-08 · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{WBJQQUX3HD72QTWS7VASMO66AG}

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

These results suggest that LLM judges form a coherent evaluative group that is much more aligned internally than it is with human readers, indicating that internal agreement is not evidence of validity as a proxy for reader response.

C2weakest assumption

That the collected human ratings on the 290 articles constitute a reliable and representative ground truth for how readers actually perceive disinformation risk.

C3one line summary

LLM judges for disinformation risk are harsher than humans, weakly match human rankings, rely on different textual signals, and agree far more with each other than with readers.

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-07-21T00:19:57.370939Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

b0530852fb38ffa84ed2fd41263bde018d19344a5042cc9e49b4888cce6723a8

Aliases

arxiv: 2604.06820 · arxiv_version: 2604.06820v2 · doi: 10.48550/arxiv.2604.06820 · pith_short_12: WBJQQUX3HD72 · pith_short_16: WBJQQUX3HD72QTWS · pith_short_8: WBJQQUX3
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/WBJQQUX3HD72QTWS7VASMO66AG \
  | 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: b0530852fb38ffa84ed2fd41263bde018d19344a5042cc9e49b4888cce6723a8
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "52307bb2a2247e3232a674d0d2b56dbad9311f3bad63aa527951efe2f6d62553",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-08T08:37:37Z",
    "title_canon_sha256": "5d8fb95f1540085c827af0c285ae038f5361df83fbde2316699f8f5ac510049c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.06820",
    "kind": "arxiv",
    "version": 2
  }
}