One thread ties them: retrieved web evidence that keeps AI factual — thematic, not a formal affiliation

Asked:

“What Keenable and Ihsan Soydemir have in common?”

Six source-backed rows from six independent hosts — three on Ihsan Soydemir's hallucination-correction research at TU Munich, three on Keenable's web-search infrastructure for AI — each converging on the same theme: grounding AI output in retrieved web knowledge. No source supplies more than one row.

Six independent sources converge on one shared focus

Soydemir side: verifying and correcting generated text with retrieved evidenceKeenable side: productizing web retrieval for AI agentsVerified thematic overlap — dashed centre note: no direct affiliation found

Soydemir's 2025 paper corrected hallucinated news summaries using evidence snippets from three search engines — the same web-retrieval layer Keenable sells as a product. alphaxiv.org

His TU Munich master's thesis focused on post-hoc hallucination detection and Retrieval-Augmented Generation — the consumption side of the retrieval stack. cs.cit.tum.de

Keenable describes itself as a research-driven AI infrastructure company building the largest independent web index for AI systems — the supply side of the same stack. keenable.ai

Across all six sources, no row records an employment, founding, or partnership link between Soydemir and Keenable — the overlap is thematic and technical only. dblp.org

The evidence, row by row

Subject	Role	Common focus	Method	Source

Data: 6 evidence rows from one research result set, each from a distinct host (alphaxiv.org, dblp.org, cs.cit.tum.de, status.keenable.ai, keenable.ai, landing.keenable.ai), gathered 2026. Each row records a subject, role, shared focus, method, page title, and source URL. The diagram links each source to the shared theme it supports; long method text is shortened in the table for space, full detail on hover in the diagram. No numeric measures beyond row counts.

This report was generated automatically by Keenable SELECT at a user's request, from publicly available web sources linked herein. Keenable does not review, verify, or endorse its contents and makes no representation as to accuracy, completeness, or timeliness; AI-based extraction may contain errors. Nothing in this report is investment, legal, financial, or other professional advice. All trademarks and referenced content remain the property of their respective owners; no affiliation or endorsement is implied. To report an error, rights concern, or request removal: legal@keenable.ai.