Metraipolis › archive › dc_cd28cd81211a

Halal-NeSyNet: Clause-Scoped Neuro-Symbolic Cross-Attention for Automated Food Ingredient Auditing and Risk-Aware Halal Logistics Triage — arXiv:2611.01612

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01612
License (as archived)
CC0-1.0
Archived
2026-11-03T11:06:36.316Z
SHA-256 of the archived text
dd80974aa61c343e0d8fc96d8b08cd1f45bb2d976264ed469981c1e8f7dd445f
Stable URL of this page
https://metraipolis.com/documento/dc_cd28cd81211a

How to cite

Halal-NeSyNet: Clause-Scoped Neuro-Symbolic Cross-Attention for Automated Food Ingredient Auditing and Risk-Aware Halal Logistics Triage — arXiv:2611.01612 — arXiv (en), https://arxiv.org/abs/2611.01612 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd28cd81211a (Metraipolis archive dc_cd28cd81211a, sha256 dd80974aa61c343e0d8fc96d8b08cd1f45bb2d976264ed469981c1e8f7dd445f)
BibTeX
@misc{dccd28cd81211a,
  title = {Halal-NeSyNet: Clause-Scoped Neuro-Symbolic Cross-Attention for Automated Food Ingredient Auditing and Risk-Aware Halal Logistics Triage — arXiv:2611.01612},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01612},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd28cd81211a; sha256 dd80974aa61c343e0d8fc96d8b08cd1f45bb2d976264ed469981c1e8f7dd445f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01612. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Verifying that a packaged food is Halal requires reading ingredient declarations and E-number additives before goods enter certified warehouses. Dual-origin additives such as E471, E422, E441 and E920 are Mushbooh (doubtful) unless a botanical, microbial or certified-Halal qualifier appears in the same ingredient clause, so a plant-based qualifier on one clause must not clear an unqualified additive in another. We call a failure to respect this scope cross-clause modifier confounding and build a benchmark of 3,199 items (277 Open Food Facts records and 2,922 template-generated clause-swap items, labelled by an explicit 50-code rule base rather than by a certification authority) with a 540-item counterfactual suite. We propose Halal-NeSyNet, which couples a DistilBERT encoder with a 16-dimensional rule-derived symbolic vector through cross-attention and gated fusion, trained with an asymmetric false-Halal risk loss. Over five seeds, text-only TF-IDF baselines reach 86.25-86.71 % accuracy with 13.42-21.73 % false-Halal leakage and 6.33-26.00 % counterfactual triad consistency, whereas Halal-NeSyNet reaches 97.04+/-0.34 % and 99.67+/-0.50 %. Gradient boosting given the same symbolic vector reaches 96.25+/-1.24 % (+0.59 points from Halal-NeSyNet, 95 % CI [-1.11, +2.28]), so most of the gain comes from clause-scoped symbolic features and not from the network, and the risk loss did not help. Holding out whole template families, text-only models fall to 61.91-78.35 %, Halal-NeSyNet to 90.87+/-11.76 % and logistic regression with the symbolic vector to 91.11+/-2.88 %, with far more spread for Halal-NeSyNet. A three-lane receiving simulation auto-clears 49.33 % of cargo at 0.76 % green-lane contamination. Because labels and features come from one rule engine and 91.3 % of the items are templated, the results measure fidelity to a rule policy, not religious certification.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01612 — 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 2026-11-03T10:59:46.031Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).