messages listlengths 3 3 |
|---|
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question requires connecting multiple facts from different parts of the conversation.\n\nRules:\n1. Output a numbered list of factual observations.\n2. For each relevant fact, note its SOURCE (which excerpt or conversation segment it c... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question requires connecting multiple facts from different parts of the conversation.\n\nRules:\n1. Output a numbered list of factual observations.\n2. For each relevant fact, note its SOURCE (which excerpt or conversation segment it c... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question requires connecting multiple facts from different parts of the conversation.\n\nRules:\n1. Output a numbered list of factual observations.\n2. For each relevant fact, note its SOURCE (which excerpt or conversation segment it c... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question asks about timing, sequence, or chronological order of events.\n\nRules:\n1. Output a numbered list of factual observations in CHRONOLOGICAL ORDER.\n2. Include exact dates, times, and relative ordering (before/after/during).\n... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question asks about timing, sequence, or chronological order of events.\n\nRules:\n1. Output a numbered list of factual observations in CHRONOLOGICAL ORDER.\n2. Include exact dates, times, and relative ordering (before/after/during).\n... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question asks about timing, sequence, or chronological order of events.\n\nRules:\n1. Output a numbered list of factual observations in CHRONOLOGICAL ORDER.\n2. Include exact dates, times, and relative ordering (before/after/during).\n... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: When was Dashboard Redesign last deployed?\n\nCandidates:\n[B-7271] Frank Williams discuss... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question requires connecting multiple facts from different parts of the conversation.\n\nRules:\n1. Output a numbered list of factual observations.\n2. For each relevant fact, note its SOURCE (which excerpt or conversation segment it c... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: What did Grace Liu decide about React?\n\nCandidates:\n[B-8187] Bob Martinez discussed Sea... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question requires connecting multiple facts from different parts of the conversation.\n\nRules:\n1. Output a numbered list of factual observations.\n2. For each relevant fact, note its SOURCE (which excerpt or conversation segment it c... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: Who is responsible for SQLAlchemy maintenance?\n\nCandidates:\n[B-4739] Eve Johnson discus... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: When was Dashboard Redesign last deployed?\n\nCandidates:\n[B-2248] Decision: Migrate to G... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question asks about timing, sequence, or chronological order of events.\n\nRules:\n1. Output a numbered list of factual observations in CHRONOLOGICAL ORDER.\n2. Include exact dates, times, and relative ordering (before/after/during).\n... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are extracting evidence from conversation excerpts for an adversarial question.\nYour job is to extract relevant evidence, NOT to answer the question.\n\nRules:\n1. Include speaker attribution for each item. If unknown, write UNKNOWN.\n2. Prefer exact quotes, but if exact... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: How does DataLake v2 handle authentication?\n\nCandidates:\n[B-7659] Meeting notes from 20... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question asks about timing, sequence, or chronological order of events.\n\nRules:\n1. Output a numbered list of factual observations in CHRONOLOGICAL ORDER.\n2. Include exact dates, times, and relative ordering (before/after/during).\n... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: Who is responsible for RabbitMQ maintenance?\n\nCandidates:\n[B-8271] Decision: Migrate to... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are extracting evidence from conversation excerpts for an adversarial question.\nYour job is to extract relevant evidence, NOT to answer the question.\n\nRules:\n1. Include speaker attribution for each item. If unknown, write UNKNOWN.\n2. Prefer exact quotes, but if exact... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are extracting evidence from conversation excerpts for an adversarial question.\nYour job is to extract relevant evidence, NOT to answer the question.\n\nRules:\n1. Include speaker attribution for each item. If unknown, write UNKNOWN.\n2. Prefer exact quotes, but if exact... |
[
{
"role": "system",
"content": "You are extracting evidence from conversation excerpts for an adversarial question.\nYour job is to extract relevant evidence, NOT to answer the question.\n\nRules:\n1. Include speaker attribution for each item. If unknown, write UNKNOWN.\n2. Prefer exact quotes, but if exact... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question requires connecting multiple facts from different parts of the conversation.\n\nRules:\n1. Output a numbered list of factual observations.\n2. For each relevant fact, note its SOURCE (which excerpt or conversation segment it c... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question asks about timing, sequence, or chronological order of events.\n\nRules:\n1. Output a numbered list of factual observations in CHRONOLOGICAL ORDER.\n2. Include exact dates, times, and relative ordering (before/after/during).\n... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question asks about timing, sequence, or chronological order of events.\n\nRules:\n1. Output a numbered list of factual observations in CHRONOLOGICAL ORDER.\n2. Include exact dates, times, and relative ordering (before/after/during).\n... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are extracting evidence from conversation excerpts for an adversarial question.\nYour job is to extract relevant evidence, NOT to answer the question.\n\nRules:\n1. Include speaker attribution for each item. If unknown, write UNKNOWN.\n2. Prefer exact quotes, but if exact... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: Who is responsible for Django maintenance?\n\nCandidates:\n[B-2814] Frank Williams discuss... |
[
{
"role": "system",
"content": "You are a memory compression expert. Given a set of conversation memory excerpts and a question, extract ONLY the facts relevant to answering the question.\n\nRules:\n1. Output a numbered list of factual observations derived from the context.\n2. Each observation must be a si... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question requires connecting multiple facts from different parts of the conversation.\n\nRules:\n1. Output a numbered list of factual observations.\n2. For each relevant fact, note its SOURCE (which excerpt or conversation segment it c... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: Who is responsible for SQLAlchemy maintenance?\n\nCandidates:\n[B-9137] Carol Singh report... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question requires connecting multiple facts from different parts of the conversation.\n\nRules:\n1. Output a numbered list of factual observations.\n2. For each relevant fact, note its SOURCE (which excerpt or conversation segment it c... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract entities from text and return structured JSON."
},
{
"role": "user",
"content": "Extract entities from the following text. Return a JSON array of objects, each with keys: \"name\" (string), \"type\... |
[
{
"role": "system",
"content": "You are a memory compression expert. The question asks about timing, sequence, or chronological order of events.\n\nRules:\n1. Output a numbered list of factual observations in CHRONOLOGICAL ORDER.\n2. Include exact dates, times, and relative ordering (before/after/during).\n... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: How does Mobile App v3 handle authentication?\n\nCandidates:\n[B-7425] Jack Wilson reporte... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory extraction model. You extract factual claims from text and return structured JSON."
},
{
"role": "user",
"content": "Extract factual claims from the following text. Return a JSON array of objects, each with keys: \"claim\" (str... |
[
{
"role": "system",
"content": "You are Mind7B, a specialized memory reranking model. Given a query and candidate memory blocks, score each for relevance (0.0-1.0)."
},
{
"role": "user",
"content": "Query: When was Mobile App v3 last deployed?\n\nCandidates:\n[B-1974] NeuraTech partnership updat... |
End of preview. Expand in Data Studio
No dataset card yet
- Downloads last month
- 36