LICENSE

STANFORD UNIVERSITY SCHOOL OF MEDICINE: PUBLIC RELEASE OF the SHIELD tide2-sentry-clinical-ner de-identification MODEL — RESEARCH USE AGREEMENT

In this Research Use Agreement, "the Model" means the `stanford-med-hdr/tide2-sentry-clinical-ner` de-identification model, including its weights, tokenizer, and configuration.

By registering for downloads of the Model, you are agreeing to this Research Use Agreement, as well as to the Terms of Use of the Stanford University School of Medicine website as posted and updated periodically at [http://www.stanford.edu/site/terms/](<http://www.stanford.edu/site/terms/>).

1. Permission is granted to view and use the Model without charge for personal, non-commercial research purposes only. Any commercial use, sale, or other monetization is [prohibited. ](<mailto:prohibited.starr-omop-support@stanford.edu>)

2. Other than the rights granted herein, the Stanford University School of Medicine ("School of Medicine") retains all rights, title, and interest in the Model.You are prohibited from removing or altering any copyright or other proprietary notices in the Model.

3. You may make a verbatim copy of the Model for a single person, non-commercial research use as permitted in this Research Use Agreement. If another user within your organization wishes to use the Model, they must register as an individual user and comply with all the terms of this Research Use Agreement.

4. You may not DISTRIBUTE, PUBLISH, OR REPRODUCE A COPY of any portion or all of the Model to others without specific prior written permission from the Stanford University School of Medicine.

5. You may not SHARE THE DOWNLOAD LINK to the Model with others. If another user within your organization wishes to use the Model, they must register as an individual user and comply with all the terms of this Research Use Agreement.

6. You are prohibited from modifying, reverse engineering, decompiling, or creating derivative works from the Model that would allow third parties access to or the ability to obtain any Model data. Accordingly, using the Model to train generative AI systems, such as language learning models (LLMs), is permissible under this Research Use Agreement provided that no Model data can be obtained or recreated from the systems.

7. The Model has not been reviewed or approved by the Food and Drug Administration, and is for non-clinical, Research Use Only. In no event shall data or images generated through the use of the Model be used or relied upon in the diagnosis or provision of patient care.

8. THE MODEL IS PROVIDED "AS IS," AND STANFORD UNIVERSITY AND ITS COLLABORATORS DO NOT MAKE ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, NOR DO THEY ASSUME ANY LIABILITY OR RESPONSIBILITY FOR THE USE OF THIS MODEL.

9. All individually identifiable health information has been removed from data. Data does not include "Protected Health Information" ("PHI") as defined in 45 C.F.R. Section 160.103. If you find information within the Model restricted data that you believe might permit identification of any individual or institution, then you will report the location of this information promptly by email to the University Privacy Office (UPO) at privacy@stanford.edu, citing the location of the specific information in question. Additionally, you must not make any attempt to re-identify any of the individual data subjects. Re-identification of individuals is strictly prohibited. Any re-identification of any individual data subject shall be immediately reported to UPO.

10. Any violation of this Research Use Agreement or other impermissible use shall be grounds for immediate termination of use of this Model. In the event that the School of Medicine determines that the recipient has violated this Research Use Agreement or other impermissible use has been made, the School of Medicine may direct that the undersigned data recipient immediately return all copies of the Model and retain no copies thereof, in any media or any format, even if you did not cause the violation or impermissible use. In addition, Stanford University may seek legal remedies.


<!-- -->

In consideration for your agreement to the terms and conditions contained here, Stanford University grants you permission to view and use the Model for personal, non-commercial research. You may not otherwise copy, reproduce, retransmit, distribute, publish, commercially exploit or otherwise transfer any material.

Limitation of Use: You may not use the Model for any illegal purposes.

You agree to indemnify and hold Stanford University and its School of Medicine harmless from any claims, losses or damages, including legal fees, arising out of or resulting from your use of the Model or your violation or role in violation of these Terms. You agree to fully cooperate in Stanford University's, including the School of Medicine, defense against any such claims. These Terms shall be governed by and interpreted in accordance with the laws of California.


<!-- -->

## How to obtain access / Acceptance

Access to the Model is **gated** and granted on an individual basis after manual review.

1. **Register and accept this Research Use Agreement on the Redivis page:**
   <https://redivis.com/REPLACE_WITH_SENTRY_MODEL_DUA_SLUG>
   <!-- TODO(user): replace with the real Redivis registration/DUA acceptance URL -->

2. **Request access on Hugging Face** at
   `stanford-med-hdr/tide2-sentry-clinical-ner` and complete the gated-access form
   (email, affiliation, and acceptance checkboxes). Hugging Face automatically
   records your Hugging Face username, account email, and the timestamp of your
   request.

3. A `stanford-med-hdr` maintainer **manually** reviews each request and grants
   Hugging Face access only after verifying your Redivis registration. Each user
   must register **individually** and comply with all the terms above (see clauses
   3 and 5); download links and access must not be shared.

**By requesting access and clicking "Accept" (on Redivis and on Hugging Face), you
agree to the terms of this Research Use Agreement.**