Status: False
Assertion
The Earth is flat.
Results
<|assistant|> The statement “The Earth is flat” can be classified as:
– False
This classification is based on well-established scientific evidence and consensus regarding the spherical shape of the Earth.
Assumptions
– Assumptions for statement A (“The Earth is flat”):
– There exists an alternative explanation for all observed phenomena that would attribute them to a flat Earth model, which has not been proposed or verified by scientific research.
– The curvature of the Earth can only be attributed to its shape due to reasons other than gravitational forces and planetary formation processes (which have already been ruled out).
– All photographs claiming evidence for a spherical Earth are somehow fabricated, manipulated, or misinterpreted.
– The phenomenon of ships disappearing over the horizon is not due to perspective or curvature but rather an optical illusion that has been misunderstood by scientists and observers alike (contrary to evidence).
– Assumptions for statement B (“The Earth is round”):
– Gravity acts as a centripetal force, pulling matter towards the center of mass and causing celestial bodies like planets to adopt spherical shapes.
– Observations from various vantage points (from space or at high altitudes) consistently show curvature that aligns with an oblate spheroid shape due to Earth
Fact Checker Output
<|assistant|> Assumptions for statement A (“The Earth is flat”):
1. There exists an alternative explanation for all observed phenomena that would attribute them to a flat Earth model, which has not been proposed or verified by scientific research.
– False: The overwhelming consensus within the scientific community supports the understanding of Earth as spherical based on extensive observations and evidence. Although alternative explanations are always welcome in science, there is currently no credible alternative explanation that matches all observed phenomena without requiring some form of curvature.
2. The curvature of the Earth can only be attributed to its shape due to reasons other than gravitational forces and planetary formation processes (which have already been ruled out).
– False: Gravitational forces and planetary formation processes are widely accepted as natural causes for the spherical shape of celestinate bodies, including Earth. These concepts are backed by strong scientific evidence and research.
3. All photographs claiming evidence for a spherical Earth are somehow fabricated, manipulated, or misinterpreted.
– False: The vast majority of photographs that show the curvature of the Earth have been taken from various locations on Earth’s
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
}
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)
# 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:
- True
- False
- Debatable
"""
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(final_output):
final_output = final_output.lower().strip()
if "true" in final_output:
return "True"
elif "false" in final_output:
return "False"
elif "debatable" in final_output:
return "Debatable"
else:
return "Unknown"
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
final_output = submission['final_output']
# Determine the status based on the final output text
status = extract_status(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>{final_output}</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