Status: True
Assertion
The Great Wall of China can be seen from space with the naked eye.
Results
Astronauts in low Earth orbit can view large structures like the Great Wall of China when visibility conditions allow for clear observation and minimal surrounding obstructions, such as during dry seasons without excessive vegetation growth. However, it’s important to note that while astronauts may be able to see large features from space under optimal conditions, their ability to discern specific details or structures like the Great Wall of China is limited due to factors such as scale and atmospheric interference.
Assumptions
– Viewers are in low Earth orbit without any visual aid, such as cameras or magnification devices.
– The viewing conditions allow for clear visibility from space, which includes factors like sunlight illuminating the object and minimal atmospheric interference.
– The Great Wall of China is viewed during a time when it contrasts significantly with its surroundings (e.g., dry season without much vegetation growth).
– There are no competing structures or features in the immediate vicinity that would obscure the visibility of the Great Wall from space.
– The observer has sufficient visual acuity to discern large human-made structures despite being at a distance and under varying light conditions.
It’s crucial to understand these assumptions when discussing the visibility of the Great Wall from space, as they greatly influence the statement’s validity.
Fact Checker Output
<|assistant|> – Viewers are in low Earth orbit without any visual aid: True. Astronauts aboard the International Space Station (ISS), which orbits at a relatively low altitude of approximately 408 km above Earth’s surface, commonly observe Earth and its features without specialized equipment like cameras or magnification devices.
– The viewing conditions allow for clear visibility from space: True to some extent but False in general terms. From orbit, the Earth is mostly illuminated by sunlight during certain times of the day, allowing astronauts to see natural and man-made features under optimal lighting conditions. However, atmospheric interference can occur due to clouds, pollution, or weather conditions, which may hinder visibility at some points in time.
– The Great Wall of China is viewed during a time when it contrasts significantly with its surrounds (e.g., dry season without much vegetation growth): True. Observations from space are often made when the Earth’s features have minimal surrounding obstructions, and this includes times like the dry season in northern China where there is less vegetation to obscure large structures like the Great Wall.
– There are no compet
Model Used
microsoft/Phi-3-mini-4k-instruct-gguf
Script Name
fact_checker_mongodb.py
Script Code
import os
import sys
import requests
from langchain_openai.llms import OpenAI
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv
from statements import get_random_statement
from mongodb_helper import insert_record # Import MongoDB helper functions
import html
# Load environment variables from .env file
load_dotenv()
# Define category IDs
CATEGORY_IDS = {
"True": 2,
"False": 3,
"Debatable": 4,
"Unknown": 6
}
def create_wordpress_post(title, content, category):
data = {
"title": title,
"content": content,
"status": "publish",
"categories": [CATEGORY_IDS[category]]
}
response = requests.post(
os.getenv("WORDPRESS_POSTS_URL"),
json=data,
auth=(os.getenv("WORDPRESS_USERNAME"), os.getenv("WORDPRESS_PASSWORD"))
)
if response.status_code == 201:
print("Blog post created successfully.")
else:
print(f"Failed to create blog post: {response.status_code} - {response.text}")
def fact_check(assertion):
llm = OpenAI(temperature=0.7, model=os.getenv("MODEL_NAME"))
# Define the prompt templates
assertion_template = """{assertion}\n\n"""
assertion_prompt = PromptTemplate(input_variables=["assertion"], template=assertion_template)
assumptions_template = """Here is a statement:
{statement}
Make a bullet point list of the assumptions required to support the above statement.\n\n"""
assumptions_prompt = PromptTemplate(input_variables=["statement"], template=assumptions_template)
fact_checker_template = """Here is a bullet point list of assertions:
{assertions}
For each assumption, determine whether it is true or false. Explain your reasoning.\n\n"""
fact_checker_prompt = PromptTemplate(input_variables=["assertions"], template=fact_checker_template)
answer_template = """
Here is the information to classify the statement:
{facts}
Based on the above information, how would you classify the statement? Respond with one of the following options followed by a colon and space:
- True: [Explanation]
- False: [Explanation]
- Debatable: [Explanation]
"""
answer_prompt = PromptTemplate(input_variables=["facts"], template=answer_template)
# Format prompts and extract the string content
formatted_assertion = assertion_prompt.format_prompt(assertion=assertion).text
assertion_output = llm.invoke(formatted_assertion)
formatted_assumptions = assumptions_prompt.format_prompt(statement=assertion_output).text
assumptions_output = llm.invoke(formatted_assumptions)
formatted_fact_checker = fact_checker_prompt.format_prompt(assertions=assumptions_output).text
fact_checker_output = llm.invoke(formatted_fact_checker)
formatted_answer = answer_prompt.format_prompt(facts=fact_checker_output).text
final_output = llm.invoke(formatted_answer)
return {
"assertion_output": assertion_output,
"assumptions_output": assumptions_output,
"fact_checker_output": fact_checker_output,
"final_output": final_output,
}
def extract_status_and_reasoning(final_output):
final_output = final_output.strip()
if "True:" in final_output:
status_start = final_output.find("True:")
status = "True"
elif "False:" in final_output:
status_start = final_output.find("False:")
status = "False"
elif "Debatable:" in final_output:
status_start = final_output.find("Debatable:")
status = "Debatable"
else:
return "Unknown", final_output
reasoning = final_output[status_start + len(status) + 1:].strip()
return status, reasoning
if __name__ == "__main__":
if len(sys.argv) > 1:
assertion = sys.argv[1]
else:
assertion = get_random_statement()
print(assertion)
submission = fact_check(assertion)
# Print the detailed outputs to inspect their structure
for key, value in submission.items():
print(f"{key}: {value}")
# Extract the final output for status determination and reasoning
final_output = submission['final_output']
status, reasoning = extract_status_and_reasoning(final_output)
# Record the result in MongoDB
try:
print("Attempting to insert record into MongoDB...")
insert_record(
script_name="fact_checker_mongodb.py",
script_code=html.escape(open(__file__).read()),
assertion=assertion,
status=status,
submission=submission, # Store the entire submission for detailed analysis
model=os.getenv("MODEL_NAME")
)
print("Record inserted into MongoDB successfully.")
except Exception as e:
print(f"Failed to insert record into MongoDB: {e}")
print(final_output)
# Create a blog post on WordPress
blog_title = f"Fact Check: {assertion}"
blog_content = f"""
<h1>Status: {status}</h1>
<h2>Assertion</h2>
<p>{assertion}</p>
<h2>Results</h2>
<p>{reasoning}</p>
<h3>Assumptions</h3>
<p>{submission['assumptions_output']}</p>
<h3>Fact Checker Output</h3>
<p>{submission['fact_checker_output']}</p>
<h4>Model Used</h4>
<p>{os.getenv("MODEL_NAME")}</p>
<h4>Script Name</h4>
<p>fact_checker_mongodb.py</p>
<h4>Script Code</h4>
<pre>{html.escape(open(__file__).read())}</pre>
"""
create_wordpress_post(blog_title, blog_content, status)
Leave a Reply