pith:3DKCT2U7
ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold
ReSS extracts decision paths from trees to scaffold LLM fine-tuning for tabular prediction with faithful reasoning.
arxiv:2604.13392 v2 · 2026-04-15 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{3DKCT2U7UEJAJBOXXWRK4WPQOB}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experimental results on medical and financial benchmarks demonstrate that ReSS-trained models improve traditional decision trees and standard fine-tuning approaches up to 10% while producing faithful and consistent reasoning.
That decision-tree paths extracted from the data can serve as sufficient and non-restrictive scaffolds that force an LLM to generate reasoning which is both logically faithful and semantically useful without introducing new inconsistencies or losing predictive power.
ReSS uses decision-tree scaffolds to fine-tune LLMs for faithful tabular reasoning, reporting up to 10% gains over baselines on medical and financial data.
Receipt and verification
| First computed | 2026-05-20T01:05:13.307052Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
d8d429ea9fa1120485d7bda2ae59f0707c43533db2a1784541da174baae2f9d1
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/3DKCT2U7UEJAJBOXXWRK4WPQOB \
| 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: d8d429ea9fa1120485d7bda2ae59f0707c43533db2a1784541da174baae2f9d1
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "d918d0c95a1fd03b27ec64eb963fb5e09ca4c1c26f841f15493b45dc2fd7aae4",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-04-15T01:43:00Z",
"title_canon_sha256": "0b3db06d23ee531df9516d0b7662208bc175dd40edda1dfad0e6e7281fb92742"
},
"schema_version": "1.0",
"source": {
"id": "2604.13392",
"kind": "arxiv",
"version": 2
}
}