Emmanuel Orta · VSNARY · Open research

Open research and datasets

Independent research on AI agent safety, crawler policies and what websites actually serve. Published by Emmanuel Orta, founder of CrawlCheck, with source code, dated datasets and reproducible evidence.

ORCID · Research CV · Machine-readable catalogue · All BibTeX · All RIS

Trace a result to its evidence

Follow the edition DOI to the archived files, then use the linked method or pinned source code to reproduce the work. For signed datasets, verify the edition and part hashes with the published signing keys and verification instructions. File checksums check transfer integrity. A signature identifies the signer and integrity of the record.

Publishing and measurement method · Corrections · Explore all CrawlCheck datasets

Preprint ·

Do AI Agents Stop Before Acting? A Frozen Benchmark of Lookalike Domains, Poisoned Tools, Revoked Receipts and Stale Answers, With and Without an External Verification Signal

A frozen, reproducible test of whether agents stop before hazardous web actions, with and without an external verification signal.

What this record establishes

Models stopped on 32 of 80 hazard trials unaided and 79 of 80 with a correct external signal.

Scope and limits

39 operator-selected cases, four models, one run per case and model. The external signal was correct by construction. This measures whether models heed that signal, not how often the verification service is right.

Use this work

Re-run the matched hazard and control cases to compare agent behaviour under the published scoring rule.

Download files (2)

Cite this edition

Orta, E. (2026). Do AI Agents Stop Before Acting? A Frozen Benchmark of Lookalike Domains, Poisoned Tools, Revoked Receipts and Stale Answers, With and Without an External Verification Signal. Preprint. Zenodo. https://doi.org/10.5281/zenodo.23682818

BibTeX · RIS · CC BY 4.0 reuse terms

Metadata captured from Zenodo. File checksums are repository-published MD5 values. Signed edition verification is a separate check.

Preprint ·

Naming a Crawler Unblocks It: Rule Shadowing in robots.txt Across 12,828 Popular Websites

How adding a named crawler group can drop restrictions inherited from the general robots.txt group.

What this record establishes

1,061 of 2,737 eligible sites (38.8%) gave at least one named crawler access to paths blocked by their general rules.

Scope and limits

One reading from one network, 26 crawler names, and 12,828 readable robots.txt files from a stratified 20,000-origin sample. Published rules do not establish operator intent or actual crawler behaviour.

Use this work

Reproduce the sample and parser comparison, or inspect a site for rules lost when a named group replaces the wildcard group.

Download files (2)

Cite this edition

Orta, E. (2026). Naming a Crawler Unblocks It: Rule Shadowing in robots.txt Across 12,828 Popular Websites. Preprint. Zenodo. https://doi.org/10.5281/zenodo.23682816

BibTeX · RIS · CC BY 4.0 reuse terms

Metadata captured from Zenodo. File checksums are repository-published MD5 values. Signed edition verification is a separate check.

Dataset edition ·

CrawlCheck agentic-web census, weekly edition 2026-W44

A sealed weekly edition of crawler policies, machine files and declared capabilities on fixed top-site frames.

What this record establishes

Edition 2026-W44 preserves the weekly census separately from the changing live dashboard.

Scope and limits

Identity tests send crawler user-agent strings from CrawlCheck’s network. They describe the test client’s response, not independently authenticated traffic from those crawlers. Weekly comparisons use the published fixed frame.

Use this work

Compare sealed editions on the same frame and cite the exact weekly DOI when reporting a result.

Download files (1)

Cite this edition

Orta, E. & CrawlCheck (2026). CrawlCheck agentic-web census, weekly edition 2026-W44. Dataset edition. Zenodo. https://doi.org/10.5281/zenodo.23874483

BibTeX · RIS · CC BY 4.0 reuse terms

Metadata captured from Zenodo. File checksums are repository-published MD5 values. Signed edition verification is a separate check.

Dataset edition ·

CrawlCheck AI-use declarations, top 10,000 (rights feed edition) rf-2026-10-28-7fc4c5

A signed manifest and compressed NDJSON parts recording AI-use declarations across the top 10,000 sites.

What this record establishes

Edition rf-2026-10-28-7fc4c5 preserves declarations with their read_at timestamps and per-part hashes.

Scope and limits

A published declaration describes what a site stated at read_at. It does not establish legal permission, enforceability, or crawler compliance.

Use this work

Join dated declarations to other measurements using the published schema, retaining each observation’s timestamp and manifest.

Download files (11)

Cite this edition

Orta, E. & CrawlCheck (2026). CrawlCheck AI-use declarations, top 10,000 (rights feed edition) rf-2026-10-28-7fc4c5. Dataset edition. Zenodo. https://doi.org/10.5281/zenodo.23746280

BibTeX · RIS · CC BY 4.0 reuse terms

Metadata captured from Zenodo. File checksums are repository-published MD5 values. Signed edition verification is a separate check.

Archived editions and live observations

The editions above preserve a dated result. Live figures carry their own source timestamps and can change. Use the exact edition DOI when citing a finding, and its series DOI when referring to the continuing dataset.

Collaborate or cover the work

Research replication, dataset reuse, interviews and partnerships are welcome. Include the publication DOI and the question you are exploring when you write to Emmanuel. Press kit · Press facts as JSON-LD.