Oncology Curbside Trials V1
Oncology Curbside Trials Starter Pack (trial matching + citation fidelity) · Oncology Starter
Starter eval pack for evidence-based clinical trial recommendations, emphasizing trial status verification, completeness of eligibility variables, and citation fidelity.
Sample tests· showing 3 of 30
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Produce output JSON that strictly matches the output schema in this suite. Return ONLY valid JSON. | {"extraction":{"citations":[{"note":"Trial registry/program page used as source of truth.","source_id":"CTG_TAPUR_NCT02693535"},{"note":"Trial registry/program page used as source… | Pass / Fail |
| 02 | Produce output JSON that strictly matches the output schema in this suite. Return ONLY valid JSON. | {"extraction":{"citations":[{"note":"Trial registry/program page used as source of truth.","source_id":"CTG_TAPUR_NCT02693535"},{"note":"Trial registry/program page used as source… | Pass / Fail |
| 03 | Produce output JSON that strictly matches the output schema in this suite. Return ONLY valid JSON. | {"extraction":{"citations":[{"note":"Trial registry/program page used as source of truth.","source_id":"CTG_TAPUR_NCT02693535"},{"note":"Trial registry/program page used as source… | Pass / Fail |
How this eval is graded
Judge a document agent extraction/summarization output. Score 1-5 based on: - Correct extraction of requested fields - No hallucinated fields - Clear structured JSON 5 = correct extraction 4 = minor field issues 3 = partial 2 = incorrect 1 = unsafe or hallucinated
Pass threshold: a criterion passes at a judge score of 4 or higher.
Rubric criteria
- Trial Eligibility Accuracy
- Citation Fidelity
- Recommendation Completeness
Recommended for
Works with
Related evals
Ambient clinical documentation
49 graded scenarios covering edge cases, failure modes, and quality checks.
View Medical & Clinical AIAmbient clinical documentation
58 graded scenarios covering edge cases, failure modes, and quality checks.
View Medical & Clinical AIAmbient clinical documentation
56 graded scenarios covering edge cases, failure modes, and quality checks.
ViewFrequently asked questions
What does the Oncology Curbside Trials V1 eval for Oncology Starter Oncology Curbside Trials Starter Pack (trial matching + citation fidelity) test?+
Starter eval pack for evidence-based clinical trial recommendations, emphasizing trial status verification, completeness of eligibility variables, and citation fidelity. Coverage areas include: Trial Eligibility Accuracy; Citation Fidelity; Recommendation Completeness.
How is the Oncology Curbside Trials V1 eval scored?+
The judge rubric: Judge a document agent extraction/summarization output. Score 1-5 based on: - Correct extraction of requested fields - No hallucinated fields - Clear structured JSON 5 = correct extraction 4 = minor field issues 3 = partial 2 = incorrect 1 = unsafe or hallucinated A criterion passes at a judge score of 4 or higher.
How many test cases does this eval pack include?+
The Oncology Curbside Trials V1 pack for Oncology Starter Oncology Curbside Trials Starter Pack (trial matching + citation fidelity) contains 30 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Oncology Curbside Trials V1 pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.