NIST GenAI Participation Rules

Eligibility

• Participation in any NIST GenAI challenge is open to all who find the task of interest and agree to abide by the full Participation Agreement provided during registration and any rules stated on the GenAI website or as part of the applicable GenAI challenge evaluation plan.
• Participants must own the algorithms or have the right of the owner of the algorithms used or submitted to NIST to use for any NIST GenAI challenge.

Participant Conduct

• Participants must conduct and represent themselves and their organizations ethically and honestly.
• Participants must not defame, abuse, harass, or otherwise violate the legal rights of other participants.
• Participants must not publish or disseminate any defamatory, infringing, obscene, or unlawful material or information.
• Participants must not submit files or algorithms that contain viruses, are corrupted, or could in any other manner damage or disrupt the operation of a website or computer.

Data and Materials

• Use of all data and materials supplied by NIST in the course of any NIST GenAI challenge is limited to participation in the challenge, regardless of the origin or ownership of the data and materials
• Use of all data and materials supplied by NIST in the course of any NIST GenAI challenge is for noncommercial research purposes only.
• Participants must not transfer, publicize, disclose, or distribute any data or materials supplied by NIST for any NIST GenAI challenge to any third party.
• Participants must not attempt to identify any individual or decipher any identifiable information in the data and materials.
• At the conclusion of any NIST GenAI challenge, participants must cease all use of data and materials supplied by NIST for any NIST GenAI challenge. Participants who cease participation early or whose participation is terminated early by NIST must immediately cease all use of data and materials supplied by NIST for any NIST GenAI challenge.

Data Processing and Submissions

• Participants must not use publicly available NIST-released data to train their algorithms or tune parameters, however, they may use other publicly available data that complies with applicable laws and regulations to train their algorithms.
• Participants may not examine the test data manually or through human means, including analyzing the media and/or training their algorithms on the test data, to draw conclusions from prior to the challenge period to the end of the challenge period. This rule does not preclude online learning/adaptation during test data processing so long as the adaptation information is not reused for subsequent runs of the evaluation collection.

Public Statements

• Participants must not use the name of NIST or the GenAI Program on any commercial advertisement or promotional material or similar public statement.
• No reference may be made to NIST, or to reports or results furnished by NIST, in any advertising or sales promotion that would indicate or imply that NIST approves, recommends, or endorses any product, service, or material, or which has as its purpose an intent to cause directly or indirectly the advertised product, service, or material to be used or purchased because of NIST test reports or results.
• NIST may publicly identify the participant both individually and as a member of a team. Such identification will at times be paired with the results of NIST’s evaluations of the outputs of the participant’s algorithm, to include “rankings” among other participating teams.
• Participants may not use the names of any other teams or individuals participating in NIST GenAI in any commercial advertisement, promotional material, or similar public statement that makes a comparison, whether express or implied, between or among the evaluation results of the participating teams or individuals, without first obtaining the written permission of both NIST and the named team or individual for such use. This prohibition does not apply to any jointly authored publications for which all identified individuals (or their teams) are also co-authors.
• Participants must not utilize their own “rankings” or those of any other participating individual or team in any commercial advertisement, promotional material, or similar public statement.
• Participants may make public statements (including publications) about their own evaluation results from NIST and about their participation in the CHALLENGE, so long as such statements do not imply endorsement by NIST, the U.S. Department of Commerce, the U.S. Government, or any subunit of the foregoing entities.
• NIST may generate reports summarizing system results for conditions of interest. Participants may publish or otherwise disseminate these charts unaltered and with appropriate reference to their source.
• Scientific or technical publications, including newsletters from universities or research laboratories, must adhere to community standards for fairness and objectivity and must accurately and clearly state the limitations of the testing conditions and other factors which might influence scores. The experimental nature of the tasks, data, and evaluation procedures must also be stated. If available, the full NIST GenAI proceedings must be referenced.

Miscellaneous

• Participants agree to make at least one valid submission for any challenge registered for.
• Participants agree to have one or more representatives at the post-evaluation workshop, to present a meaningful description of their approach(es).