pith:USEEI4GL
ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming
ANDRE learns first-order logic rules from noisy probabilistic data by optimizing a continuous space with attention-driven conjunction and disjunction operators.
arxiv:2605.04193 v2 · 2026-05-05 · cs.AI · cs.LG · cs.LO
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{USEEI4GLQIYKDPAXLV7Q4G73WD}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
ANDRE achieves competitive or superior predictive performance while reliably recovering correct symbolic rules under uncertainty. In particular, ANDRE remains robust to moderate label noise, substantially outperforming existing differentiable ILP methods in both rule extraction quality and stability.
That attention-based operators can accurately and stably approximate min-max logical semantics over probabilistic predicate valuations without vanishing gradients or loss of interpretability when optimizing the continuous rule space.
ANDRE learns first-order logic programs via attention-driven differentiable operators that approximate logical semantics, achieving competitive performance and robust rule recovery on noisy and probabilistic ILP benchmarks.
Receipt and verification
| First computed | 2026-06-02T02:04:18.575135Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
a4884470cb8230a1bc175d7f0e1bfbb0e8c3aae9abcb4a87a1a8403e81740e90
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/USEEI4GLQIYKDPAXLV7Q4G73WD \
| 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: a4884470cb8230a1bc175d7f0e1bfbb0e8c3aae9abcb4a87a1a8403e81740e90
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "3bdcaa77ad05f78d7749b8ccf6ccef89a59e9b25f88540938063569e0af12d2a",
"cross_cats_sorted": [
"cs.LG",
"cs.LO"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-05T18:35:06Z",
"title_canon_sha256": "b9728e4103424a7ff14399736b539bea1d104da6bfbc200454c8a87c312f0883"
},
"schema_version": "1.0",
"source": {
"id": "2605.04193",
"kind": "arxiv",
"version": 2
}
}