{
  "id": 7280,
  "url": "https://arxiv.org/abs/2603.12953v1",
  "title": "Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning",
  "summary": "Neuro-symbolic reasoning increasingly demands frameworks that unite the formal rigor of logic with the interpretability of large language models (LLMs). We introduce an end to end explainability by construction pipeline integrating the Automated Theorem Generator Delta1 based on the full triangular standard contradiction (FTSC) with LLMs. Delta1 deterministically constructs minimal unsatisfiable clause sets and complete theorems in polynomial time, ensuring both soundness and minimality by const",
  "authors": "Yang Xu, Jun Liu, Shuwei Chen, Chris Nugent, Hailing Guo",
  "category": "research",
  "topics": "safety-alignment,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-13T12:54:35.000Z",
  "fetched_at": "2026-07-14T16:33:08.011Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7280",
  "original_url": "https://arxiv.org/abs/2603.12953v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}