## Bias

| Field | Response |
| :---- | :---- |
| Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing | None. |
| Measures taken to mitigate against unwanted bias | Training, evaluation, and testing data are curated before release to filter restricted content, including content relating to protected classes. Downstream evaluation should assess coverage and model behavior across the environments and operating conditions relevant to the intended application. |
| Which characteristic (feature) show(s) the greatest difference in performance?: | Performance may vary with scene complexity, rollout length, and the input conditions used for generation. Long-horizon temporal consistency and fine-grained physical interactions are known challenges described for the Cosmos3-Nano base model and are relevant considerations for these simulation models. |
| Which feature(s) have the worst performance overall? | Challenging scenarios include long rollouts and complex physical interactions, where temporal consistency and fidelity to the supplied controls may degrade. Users should evaluate these aspects under their intended simulation conditions. |
| If using internal data, description of methods implemented in data acquisition or processing, if any, to address the prevalence of identifiable biases in the training, testing, and validation data: | Bias-specific methods applied during data processing include person-presence screening, demographic-taxonomy classification (age, gender, ethnicity), embedding-based diversity analysis, and dataset balancing across sources. Internal analysis of the Cosmos3-Nano base model's training data surfaced: non-person scenes are more prevalent than person-centric content; demographic-taxonomy outputs on person-present samples are most frequently "uncertain" across age, gender, and ethnicity dimensions; and source-type variation, with people-centric image and video datasets showing higher demographic signal than document-, object-, robotics-, or scene-focused datasets. *(Quantitative details are provided below.)* Downstream deployments should add bias audits, fairness evaluation, red-teaming, demographically balanced fine-tuning, or counterfactual augmentation as mitigations. |
| Tools used to assess statistical imbalances and highlight patterns that may introduce bias into AI models: | Dataset analytics pipelines, metadata distribution analysis, heuristic quality checks, embedding-based clustering, model-assisted filtering systems, and benchmark evaluation suites are used to assess statistical imbalances and identify patterns that may introduce bias into model behavior. |
| Tools used to assess statistical imbalances and highlight patterns that may introduce bias into AI models: | The following analysis covers training data used for the Cosmos3-Nano base model. These datasets, such as OpenImages-derived detection-to-NLP datasets, visual grounding and VQA datasets, document/image understanding datasets, video/action understanding datasets, and NVIDIA-created or curated visual datasets, do not collectively or exhaustively represent all demographic groups (and proportionally therein). For instance, automated person-presence screening did not identify a person in approximately 58% of visual samples analyzed across approximately 400 datasets, while person-present signals were identified in approximately 42% of analyzed samples. In the subset where person-present signals were identified, these datasets contain uneven representation splits across the measured visual taxonomies: age outputs were most frequently uncertain, followed by child and adult; gender outputs were most frequently uncertain, followed by male and female; and ethnicity outputs were most frequently uncertain, followed by Hispanic and White as the most frequent identified categories. Dataset-level results vary by source type, with people-centric image and video datasets containing higher person-present and demographic-taxonomy signals than document-, object-, robotics-, or scene-focused datasets. To mitigate these imbalances, we recommend considering evaluation techniques such as bias audits, task-specific fairness evaluation, and red-teaming, along with fine-tuning with demographically balanced datasets and counterfactual data augmentation to align with the desired model behavior. This evaluation used a baseline of 200 samples across all datasets, with larger subsets of up to 3,000 samples utilized for certain in-depth analyses, identified as optimal thresholds for maximizing embedder accuracy. |