Metraipolis › archive › dc_ada2132a1ea8
XLOG: A CUDA-Native Engine for Neurosymbolic Integration — arXiv:2609.27203
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27203
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T09:11:09.390Z
- SHA-256 of the archived text
0ab52961858688c40d23fd98c5eb5b905d69bf6f80821c3cd4f99eed89c19044- Stable URL of this page
https://metraipolis.com/documento/dc_ada2132a1ea8
How to cite
XLOG: A CUDA-Native Engine for Neurosymbolic Integration — arXiv:2609.27203 — arXiv (en), https://arxiv.org/abs/2609.27203 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ada2132a1ea8 (Metraipolis archive dc_ada2132a1ea8, sha256 0ab52961858688c40d23fd98c5eb5b905d69bf6f80821c3cd4f99eed89c19044)
BibTeX
@misc{dcada2132a1ea8,
title = {XLOG: A CUDA-Native Engine for Neurosymbolic Integration — arXiv:2609.27203},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27203},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ada2132a1ea8; sha256 0ab52961858688c40d23fd98c5eb5b905d69bf6f80821c3cd4f99eed89c19044},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27203. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
xlog is a CUDA-native logic programming engine integrating neural perception with deterministic Datalog, probabilistic inference, and epistemic world views through a typed frontend and provider-owned CUDA runtime. Its reasoning modes share device data planes, but their execution boundaries differ: ordinary Datalog and exact inference are host-orchestrated, while certified resident recursive and Monte Carlo sampled cores record zero tracked host-device transfers before a bounded terminal receipt. The probabilistic path supports end-to-end gradients through GPU knowledge compilation from provenance to CNF to Decision-DNNF, exact weighted model counting, and backward gradients. A final smoothed circuit is certified against its source formula before caching or evaluation. Circuit caching yields a 2.74x MNIST-addition training speedup; a worst-case-optimal join subsystem yields a 27.96x geometric-mean gain over xlog's binary-join baseline. MNIST-addition accuracy matches Scallop's (0.9561 versus 0.9468), but no per-epoch speed claim is made because baseline epoch time varies with CPU quota. In five hub-skewed triangle-counting cases, the Souffle-to-fused-xlog execution-time ratio rises from 0.88x at 150k edges, where Souffle is faster, to 5.54x at 1.2M; fused peak device allocations are 85-1,033 MB versus 3,287-44,979 MB for the materializing arm. Exact inference is correctness-equivalent to but slower than ProbLog2. On a public video benchmark, a proximity predicate trained only through symbolic credit replaces hand-set geometry at unchanged held-out accuracy; within Event-Calculus rule search it fails ten-fold cross-validation and does not transfer on a leak-free split. On a maritime corpus, weighted clauses beat crisp selection by 0.065 F1, with the result reproduced by one chronological training pass. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.27203 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T08:13:26.476Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).