pith:BYP3EDXS
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
Grounding multi-hop fact verification in a structural causal model and optimizing it with group relative policy optimization yields more accurate and less hallucinated reasoning than standard chain-of-thought methods.
arxiv:2605.01482 v3 · 2026-05-02 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{BYP3EDXS64SMWB6ENJ7UJJ2HWR}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework significantly outperforms state-of-the-art baselines, offering a reliable and interpretable solution for complex fact verification.
That explicitly modeling verification as a constructive causal inference process inside a structural causal model will produce more accurate and less hallucinated reasoning chains than standard chain-of-thought methods without introducing new modeling errors.
SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.
Formal links
Receipt and verification
| First computed | 2026-06-24T01:14:28.376907Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/BYP3EDXS64SMWB6ENJ7UJJ2HWR \
| 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: 0e1fb20ef2f724cb07c46a7f44a747b467c87bb76afa580c953c19e8ef98f707
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "05a6525bd4ceedf8bbd193e91497d6ede74be7fd164567922e83a8be1297b8d8",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-02T15:05:38Z",
"title_canon_sha256": "71e14239f79f5c4f86636cb7a3888b965dfeb42fa3ba80670f22295bdb5a1e08"
},
"schema_version": "1.0",
"source": {
"id": "2605.01482",
"kind": "arxiv",
"version": 3
}
}