# Guardian Crawler: Retrieval-First Knowledge Discovery with Bounded LLM Augmentation for Noisy Web Intelligence

arXiv: https://arxiv.org/abs/2608.08994 · HTML: https://mlsanity.com/paper/2608.08994/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 13 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 3 of 3)

- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning](https://mlsanity.com/paper/2205.14704/) (2022)
- [Predictive Probability Density Mapping for Search and Rescue Using An Agent-Based Approach with Sparse Data](https://mlsanity.com/paper/2412.13317/) (2024)

## Abstract (arXiv)

Retrieving relevant evidence from noisy web data is challenging, particularly in sensitive domains containing incomplete reports, heterogeneous language, and irrelevant content. We present Guardian Crawler, a reproducible retrieval-first testbed for controlled experiments on knowledge discovery and evidence-grounded summarization over synthetic web-like corpora. The architecture combines BM25 retrieval with risk-aware, embedding-augmented, and hybrid reranking, followed by constrained retrieval-augmented generation with explicit document citations. Experiments on a synthetic 900-document corpus and 10 queries produced the highest descriptive retrieval scores under risk-based reranking, with P@10 = 1.00 and NDCG@10 = 0.94, compared with 0.94 and 0.81 for BM25. The best hybrid and BM25+Semantic configurations reached NDCG@10 values of 0.94 and 0.88, respectively. All 41 evaluable generated bullets passed the lexical coverage threshold; an automated LLM judge classified 36 as supported, one as partially supported, and four as unsupported. These results demonstrate the feasibility of Guardian Crawler as a controlled testbed but do not establish statistical superiority, human-validated faithfulness, or transfer to live-web investigative environments.