Status: False
Assertion
The equator is the hottest place on Earth.
Reasoning
While the Great Barrier Reef is one of the most prominent natural features in Australia, it’s not typically considered as visible from outer space with the naked eye due to factors like atmospheric interference and its relatively small size compared to other geographical landmarks when seen from such a distance. However, high-resolution images taken by satellites can show large structures like this reef. But in general conversation or casual observation, it is not usually described as visible from outer space. Therefore, the statement might be misleading if understood literally, hence it’s classified as false.
Assumptions
<|assistant|> – The Earth’s climate is primarily influenced by its axial tilt, which causes different regions to receive varying amounts of sunlight throughout the year.
– Equatorial regions consistently receive direct overhead sunlight due to their position relative to the equator.
– Temperature variations are significantly impacted by geographic factors such as altitude and proximity to oceans or seas, which can moderate temperatures through ocean currents and prevailing winds.
– Continental landmasses have less influence from large bodies of water compared to coastal regions, potentially leading to higher average temperatures within equatorial continental areas.
– The statement considers the concept of “hottest place on Earth” in relation to continental landmass temperature averages rather than isolated extreme weather events or microclimates that may result from localized factors.
Fact Checker Output
<|assistant|> – True: The Earth’s climate is primarily influenced by its axial tilt as this causes seasonal variations in sunlight exposure for different regions on the planet throughout the year. This axial tilt results in areas being closer to or farther from the Sun during various times of the year, affecting temperatures and weather patterns.
– True: Equatorial regions consistently receive direct overhead sunlight because they are situated along an imaginary line that circles the globe at 0° latitude (the equator), where the Earth’s axial tilt has minimal impact on the angle of incoming solar radiation throughout the year. This consistent exposure leads to high temperatures and relatively stable climates in these regions.
– True: Temperature variations are significantly influenced by geographic factors such as altitude, proximity to large bodies of water (like oceans), and prevailinas winds which can moderate temperature extremes. For instance, coastal areas often have milder climates due to the heat capacity of water, while high altitudes experience lower temperatures.
– True: Continental landmasses, particularly those in equatorial regions far from large bodies of water (oce
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
from wordpress_helper import create_wordpress_post # Import WordPress helper functions
import html
# Load environment variables from .env file
load_dotenv()
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):
llm = OpenAI(temperature=0.7, model=os.getenv("MODEL_NAME"))
extraction_template = """
Here is a final output of a fact-checking process:
{final_output}
Based on the above text, what is the classification of the statement? Respond with one of the following options followed by a colon and space:
- True: [Explanation]
- False: [Explanation]
- Debatable: [Explanation]
"""
extraction_prompt = PromptTemplate(input_variables=["final_output"], template=extraction_template)
formatted_prompt = extraction_prompt.format_prompt(final_output=final_output).text
extraction_output = llm.invoke(formatted_prompt).strip()
if "True:" in extraction_output:
status = "True"
reasoning = extraction_output.split("True:", 1)[1].strip()
elif "False:" in extraction_output:
status = "False"
reasoning = extraction_output.split("False:", 1)[1].strip()
elif "Debatable:" in extraction_output:
status = "Debatable"
reasoning = extraction_output.split("Debatable:", 1)[1].strip()
else:
status = "Unknown"
reasoning = extraction_output
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)
# Print the final status and reasoning
print(final_output)
print(f"Status: {status}")
print(f"Reasoning: {reasoning}")
# Record the result in MongoDB
try:
print("Attempting to insert record into MongoDB...")
insert_record(
script_name=__file__,
script_code=html.escape(open(__file__).read()),
assertion=assertion,
status=status,
submission=submission, # Store the entire submission for detailed analysis
reasoning=reasoning,
model=os.getenv("MODEL_NAME")
)
print("Record inserted into MongoDB successfully.")
except Exception as e:
print(f"Failed to insert record into MongoDB: {e}")
# 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>Reasoning</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