Metraipolis › archive › dc_3176fff40e48
Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs — arXiv:2608.14765
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14765
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:08:06.006Z
- SHA-256 of the archived text
2b740849224912d0a06ab88f788357d442bf0d34f4c1778599e81de03d0277ce- Stable URL of this page
https://metraipolis.com/documento/dc_3176fff40e48
How to cite
Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs — arXiv:2608.14765 — arXiv (en), https://arxiv.org/abs/2608.14765 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3176fff40e48 (Metraipolis archive dc_3176fff40e48, sha256 2b740849224912d0a06ab88f788357d442bf0d34f4c1778599e81de03d0277ce)
BibTeX
@misc{dc3176fff40e48,
title = {Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs — arXiv:2608.14765},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14765},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3176fff40e48; sha256 2b740849224912d0a06ab88f788357d442bf0d34f4c1778599e81de03d0277ce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14765. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Data cleaning without a trusted clean reference is challenging because unusual values may represent either genuine errors or valid observations. This paper studies how different agent capabilities affect reference-free data cleaning and proposes an evidence-grounded framework that combines structured context, profiling, LLM reasoning, executable checks, controlled evidence retrieval, source ranking, citation alignment, conservative repair, reversible scripts, and provenance logging. Seven configurations are evaluated across financial, clinical, and environmental-monitoring datasets using controlled synthetic corruption and original-data descriptive analysis, resulting in 126 completed runs. The evaluation includes two comparison baselines and a progressive LLM-based sequence that adds executable tools, evidence retrieval, evidence controls, and conservative repair. In the synthetic evaluation, the deterministic profiling baseline achieved the highest detection F1-score of 0.561. Among the LLM-based configurations, the full conservative configuration achieved the highest F1-score of 0.421, but no configuration performed best across all evaluation criteria. The source-ranked configurations achieved the lowest unsupported-rule rates, while decision-level citation alignment remained weak. The full conservative configuration produced no unsafe or unnecessary modifications, although these rates were already zero before the conservative policy was added, and it performed no direct repairs. Overall, the results show that additional capabilities introduce trade-offs among detection, repair, evidence grounding, conservative behaviour, reproducibility, and operational cost rather than producing consistent improvements. The study provides a structured framework and empirical methodology for evaluating these trade-offs in reference-free agentic data cleaning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Databases (cs.DB). Pagina del lavoro: https://arxiv.org/abs/2608.14765 — 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 2026-10-18T16:29:13.730Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).