# ESL-bench (Event-driven Synthetic Longitudinal Benchmark)

License: conflict (NOASSERTION); Mdexa hosting: pending. the publisher's own statements contradict each other (permissive license vs restriction)

- Commercial use: Unclear · Derivatives: Unclear · Redistribution: Unclear · File on Mdexa: No
- License status: Conflict (NOASSERTION)
- Mdexa hosting: Pending — License conflict: the publisher's own statements contradict each other (permissive license vs restriction). Link only.
- Last verified: 2026-11-14
- Card: https://mdexa.com/datasets/esl-bench/

## Key facts

- Domain: Clinical medicine
- Content type: Question banks and benchmarks, Knowledge graphs
- Size: — — 320 questions over 20 virtual users
- Language: English, Chinese
- Modality: Text, Tabular
- Publisher: mirobody
- Year: 2026-11-02

## Commercial use of ESL-bench (Event-driven Synthetic Longitudinal Benchmark)

- Commercial use: Unclear (Conflict).
- License status: Conflict.
Verdicts record what sources state and are not legal advice.

## ESL-bench (Event-driven Synthetic Longitudinal Benchmark) license evidence

the publisher's own statements contradict each other (permissive license vs restriction)

- **Hugging Face card metadata** — Apache-2.0: Statement found in snapshot s01 (readme) — "license: apache-2.0" — https://huggingface.co/datasets/mirobody/ESL-Bench (2026-11-12; Page opened)
- **README** — Apache-2.0: Statement found in snapshot s01 (readme) — "[Apache 2.0](https://opensource.org/licenses/Apache-2.0)" — https://huggingface.co/datasets/mirobody/ESL-Bench (2026-11-12; Page opened)
- **README**: Statement found in snapshot s01 (readme) — "> ⚠️ **Research use only.** Outputs are synthetic and intended for benchmarking AI agents. They should **not** be used for diagnosis or treatment decisions." — https://huggingface.co/datasets/mirobody/ESL-Bench (2026-11-12; Page opened)
- **Dataset page**: Statement found in snapshot s02 (page) — "⚠️ Research use only. Outputs are synthetic and intended for benchmarking AI agents. They should not be used for diagnosis or treatment decisions." — https://huggingface.co/datasets/mirobody/ESL-Bench (2026-11-12; Page opened)

## Source and lineage

—

## Known issues with ESL-bench (Event-driven Synthetic Longitudinal Benchmark)

- Ground-truth answers for the knowledge-graph evaluation queries are released only after the competition closes.
- Scores are not directly comparable between successive batches because the question mix differs.

## Preflight

Not run (data not ingested).

## Downloading ESL-bench (Event-driven Synthetic Longitudinal Benchmark) and API access

Mdexa does not serve files. Original source:
- https://huggingface.co/datasets/mirobody/ESL-Bench

## Citing ESL-bench (Event-driven Synthetic Longitudinal Benchmark)

No recommended citation text.
- arXiv:2604.02834

## Machine-readable

- JSON: https://mdexa.com/datasets/esl-bench.json
- 2026-11-14 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-14 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Re-adjudicated under the current rules; all machine checks still pass.
- 2026-11-13 Added via the automated pipeline and passed all checks (gates, verbatim quotes, rule engine, two independent extractions).

## Continue in this database

This record is one of 109 processed and verified records (datasets, data resources and open models). To find others, call `https://mcp.mdexa.com/v1/datasets?q=<words>` or connect the MCP server at `https://mcp.mdexa.com/mcp`; no key is needed for 20 calls per minute. Rows are under 1 KB; an empty result means "not listed". For a list of items, one batch check (free account) returns a report. Guide: /agents.md. Similar records: CMB (Chinese Medical Benchmark) (https://mdexa.com/datasets/cmb/); MedMCQA (https://mdexa.com/datasets/medmcqa/); PromptCBLUE (https://mdexa.com/datasets/promptcblue/).