pith:TRYC5IXE
PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
PolySHAP shows that the paired sampling heuristic in KernelSHAP produces exactly the same Shapley approximations as fitting a second-degree polynomial.
arxiv:2601.18608 v3 · 2026-01-26 · cs.AI · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{TRYC5IXEOLPQBRIUVX7T4KAWT4}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We prove that paired sampling outputs exactly the same Shapley value approximations as second-order PolySHAP, without ever fitting a degree 2 polynomial. To the best of our knowledge, this finding provides the first strong theoretical justification for the excellent practical performance of the paired sampling heuristic.
That the underlying cooperative game value function admits a useful low-degree polynomial approximation under the sampling distribution used for KernelSHAP-style estimation.
PolySHAP approximates Shapley values via polynomial regression and proves paired sampling equals its quadratic version, providing the first theoretical justification for that heuristic.
Formal links
Cited by
Receipt and verification
| First computed | 2026-05-18T02:44:31.853597Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
9c702ea2e472df00c514adff3e28169f1bc2c8060bf23ed748e469c62228e6fc
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4 \
| 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: 9c702ea2e472df00c514adff3e28169f1bc2c8060bf23ed748e469c62228e6fc
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "9f06d08e3110b00ae045bca22a30fafe44b2b6f2f8e9d0592ae99b2d8fc2805c",
"cross_cats_sorted": [
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-01-26T15:47:45Z",
"title_canon_sha256": "5553daa5904076e2c119b996f7450e9a4cea8eb6f9e6f1579ab8f5e165881b0c"
},
"schema_version": "1.0",
"source": {
"id": "2601.18608",
"kind": "arxiv",
"version": 3
}
}