Status: True
Assertion
The Earth is flat.
Results
The Earth is an oblate spheroid based on various measurements of its shape taken from different angles and using technologies like satellite imagery and GPS data, which aligns with the general scientific understanding that planets are slightly flattened at their poles due to rotation. Scientific methods such as observation and measurement have been proven effective for a wide range of scientific endeavors, including historical observations made by Eratosthenes using shadows cast during solar eclipses. Modern technology like satellites provides highly accurate representations of Earth’s shape, further validating the statement that the Earth is an oblate spheroid.
Assumptions
– The Earth is an oblate spheroid (slightly flattened at the poles and bulging at the equator).
– Scientific methods, such as observation and measurement, accurately represent reality.
– Historical scientific observations, like those by Eratosthenes in the 16th century, are valid and reliable.
– Modern technology (satellites, space missions) provides accurate representations of Earth’s shape.
– The round shadow cast on the Moon during lunar eclipses is an observable phenomenon that supports a spherical Earth.
– Photographs taken from space consistently show a spherical Earth.
– Ships disappearing hull-first over the horizon align with observations of a spherical Earth when traveling long distances.
– The scientific community largely agrees on and upholds evidence-based conclusions about our planet’s shape.
The assumptions listed above are grounded in empirical observation, historical data, and modern technology that together provide strong support for the statement that “The Earth is not flat,” but these points do not directly justify the original false claim; rather, they counter it by providing evidence against a flat Earth model.
Fact Checker Output
<|assistant|> – True: The Earth is an oblate spheroid based on various measurements of its shape taken from different angles and using technologies like satellite imagery and GPS data. This observation aligns with the general scientific understanding that planets are slightly flattened at their poles due to rotation, which causes centrifugal force to bulge outwards along the equator.
– True: Scientific methods such as observation and measurement are designed to accurately represent reality within the limits of current technology and understanding. While they may not always capture every detail perfectly due to limitations or errors in data collection, these methods have proven effective for a wide range of scientific endeavors.
– True: Historical observations like those made by Eratosthenes using shadows cast during solar eclipses are valid and reliable, as demonstrated through the successful application of similar methods today to estimate Earth’s size and shape. These historical accounts have been corroborated by modern measurements and continue to inform our understanding of the planet’s geodetic properties.
– True: Modern technology like satellites and space missions provide highly accurate representations of Earth’s shape, as they can measure its gravitational field, surface features
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