messages listlengths 3 3 |
|---|
[
{
"role": "system",
"content": "<rubric>\n1. The response proposes a specific coordinate location for the CTCP. [Hard Rule] \n2. The response evaluates travel requirements using the provided coordinates, average speeds, vehicle frequencies, and soldier-per-vehicle rates to quantify transportation effort. [... |
[
{
"role": "system",
"content": "<rubric>\n1. The response proposes a specific coordinate location for the CTCP. [Hard Rule] \n2. The response evaluates travel requirements using the provided coordinates, average speeds, vehicle frequencies, and soldier-per-vehicle rates to quantify transportation effort. [... |
[
{
"role": "system",
"content": "<rubric>\n1. The response must provide a clear definition of the requested term or phrase. [Hard Rule] \n2. The response should begin with a concise statement of the core meaning before elaborating. [Principle] \n3. The response should illustrate the definition with example... |
[
{
"role": "system",
"content": "<rubric>\n1. The response must provide a clear definition of the requested term or phrase. [Hard Rule] \n2. The response should begin with a concise statement of the core meaning before elaborating. [Principle] \n3. The response should illustrate the definition with example... |
[
{
"role": "system",
"content": "<rubric>\n1. The response must explicitly confirm understanding of the instructions and rules. [Hard Rule] \n2. The response must adopt and maintain the specified role and context as defined by the instructions. [Hard Rule] \n3. The response must restrict its offerings to o... |
[
{
"role": "system",
"content": "<rubric>\n1. The response must explicitly confirm understanding of the instructions and rules. [Hard Rule] \n2. The response must adopt and maintain the specified role and context as defined by the instructions. [Hard Rule] \n3. The response must restrict its offerings to o... |
[
{
"role": "system",
"content": "<rubric>\n1. The response must explicitly confirm understanding of the instructions and rules. [Hard Rule] \n2. The response must adopt and maintain the specified role and context as defined by the instructions. [Hard Rule] \n3. The response must restrict its offerings to o... |
[
{
"role": "system",
"content": "<rubric>\n1. The response maintains a polite tone throughout. [Hard Rule] \n2. The response employs an accurate style in its presentation. [Hard Rule] \n3. The response targets an expert-level reader. [Hard Rule] \n4. The response adopts a planner’s perspective. [Hard Rule... |
[
{
"role": "system",
"content": "<rubric>\n1. The response maintains a polite tone throughout. [Hard Rule] \n2. The response employs an accurate style in its presentation. [Hard Rule] \n3. The response targets an expert-level reader. [Hard Rule] \n4. The response adopts a planner’s perspective. [Hard Rule... |
[
{
"role": "system",
"content": "<rubric>\n1. The response maintains a polite tone throughout. [Hard Rule] \n2. The response employs an accurate style in its presentation. [Hard Rule] \n3. The response targets an expert-level reader. [Hard Rule] \n4. The response adopts a planner’s perspective. [Hard Rule... |
[
{
"role": "system",
"content": "<rubric>\n1. The response must explicitly name the type of thread being described. [Hard Rule] \n2. The response must explain the meaning of each component of the statement: why no trap is needed, why no control switch is necessary, and why the memory cache does not need to ... |
[
{
"role": "system",
"content": "<rubric>\n1. The response must explicitly name the type of thread being described. [Hard Rule] \n2. The response must explain the meaning of each component of the statement: why no trap is needed, why no control switch is necessary, and why the memory cache does not need to ... |
[
{
"role": "system",
"content": "<rubric>\n1. The response must clearly define the sample product including its core features and purpose. [Hard Rule] \n2. The response must identify and describe the target audience segment for the product. [Hard Rule] \n3. The response must present the four AIDA component... |
End of preview. Expand in Data Studio
Prompts taken from https://huggingface.co/datasets/OpenRubrics/OpenRubric-v2/
Model: nvidia/Gemma-4-31B-IT-NVFP4
Settings:
- Temperature: 1.0
- Top P: 0.95
- Top K: 64
No undisclosed system prompts were used. Messages are exactly as collected -- except that reasoning was processed to remove excessive indentation (shared prefix indentation across all lines), with care to preserve code blocks and general structure.
- Downloads last month
- 71