Status: True
Assertion
The Earth’s largest mountain range, the mid-ocean ridge, is underwater.
Results
The Mid-Atlantic Ridge is indeed recognized as one of the world’s longest mountain ranges underwater due to its extensive length across the Atlantic Ocean. It forms a continuous range that spans from the Arctic near Gakkel Ridge, through both North and South Atlantic oceans, extending southwards until it meets with the East Pacific Rise.
– True: The Mid-Atlantic Ridge is located in the middle of the Atlantic Ocean, covering an extensive distance over 10,00e6 miles (approximately 19,500 kilometers), from Gakkel Ridge near the Arctic to where it meets the East Pacific Rise.
– True: The Mid-Atlantic Ridge is considered active because it marks a divergent tectonic plate boundary between the Eurasian and North American plates in the north, and the African and South American plates in the south. At these boundaries, new oceanic crust is created by seafloor spreading as magma rises from beneath the Earth’s surface.
– True: Seafloor spreading occurs at the Mid-Atlantic Ridge where
Assumptions
<|assistant|> – The Mid-Atlantic Ridge is indeed the world’s longest mountain range.
– It lies in the middle of the Atlantic Ocean, spanning over 10,000 miles from Gakkel Ridge near Arctic, through North and South Atlantic to its meeting point with East Pacific Rise.
– The Mid-Atlantic Ridge is an active divergent tectonic plate boundary.
– Seafloor spreading occurs at the ridge, where new oceanic crust forms from upwelling magma that cools and solidifies.
– Hydrothermal vents exist within the depths of the Mid-Atlantic Ridge.
– Unique ecosystems are present in these hydrothermal environments, contributing to our understanding of life’s resilience under extreme conditions.
– The statement relies on accepted scientific theories and findings related to plate tectonics, oceanography, geology, and biology.
– Accurate measurement tools and data collection methods have been used to establish the length and features of the Mid-Atlantic Ridge.
– The sources cited for this information are reliable, reputable scientific
Fact Checker Output
output>
– True: The Mid-Atlantic Ridge is indeed recognized as one of the world’s longest mountain ranges underwater due to its extensive length across the Atlantic Ocean. It forms a continuous range that spans from the Arctic near Gakkel Ridge, through both North and South Atlantic oceans, extending southwards until it meets with the East Pacific Rise.
– True: The Mid-Atlantic Ridge is located in the middle of the Atlantic Ocean, covering an extensive distance over 10,00e6 miles (approximately 19,500 kilometers), from Gakkel Ridge near the Arctic to where it meets the East Pacific Rise.
– True: The Mid-Atlantic Ridge is considered active because it marks a divergent tectonic plate boundary between the Eurasian and North American plates in the north, and the African and South American plates in the south. At these boundaries, new oceanic crust is created by seafloor spreading as magma rises from beneath the Earth’s surface.
– True: Seafloor spreading occurs at the Mid-Atlantic Ridge where tect
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