Status: True

Assertion

The Earth’s atmosphere extends roughly 10,000 kilometres into space.

Reasoning

The Kármán line at 100 km altitude serves as a commonly used boundary for distinguishing between Earth’s atmosphere and outer space, but this distinction isn’t universally accepted due to the gradual transition of gases into space and lack of an internationally agreed-upon standard. The definition of where atmospheric gases become too thin doesn’t have a clear, scientifically established international standard. While there is no universally agreed upper limit for Earth’s atmosphere, it is generally understood that the gases thin out significantly past approximately 700 km altitude, with the exosphere extending up to around 10,000 km, demonstrating a gradual transition from our atmosphere into outer space. [Explanation:] The given information supports this statement and acknowledges both perspectives: while there is no consensus on an exact boundary between Earth’s atmosphere and outer space, the Kármán line at 100 km altitude is commonly used as a reference point despite its lack of universal acceptance.

Assumptions

Here’s a list of assumptions supporting the statement:

– There is a clear distinction between Earth’s atmosphere and outer space, which is represented by the Kármán line at 100 km altitude.

– The definition of where atmospheric gases become too thin to be considered part of the atmosphere and instead merge with outer space does not have an internationally agreed-upon scientific standard.

– Earth’s atmosphere has a well-defined upper limit (approximately 700 km) beyond which it transitions into outer space, as evidenced by the exosphere extending up to around 10,000 km.

– The transition from atmospheric gases to outer space is gradual and not abrupt at a specific altitude; thus, there isn’t an exact point where the atmosphere ends.

– The Kármán line (or similar demarcations) are used for practical purposes such as aviation and space law rather than strictly scientific reasons.

It should be noted that these assumptions are based on current understanding and definitions within international organizations, but they may evolve with new research and consensus in the future.

Fact Checker Output

<|assistant|> – True: The Kármán line at 100 km altitude serves as a commonly used boundary for distinguishing between Earth’s atmosphere and outer space. However, this distinction isn’t universally accepted due to the gradual transition of gases into space and lack of an internationally agreed-upon standard.

– True: The definition of where atmospheric gases become too thin does not have a clear, scientifically established international standard for determining the end of Earth’s atmosphere. This ambiguity arises from the gradual nature of this transition and varying conditions in different parts of the atmosphere.

– True: While there isn’t a universally agreed-upon upper limit to Earth’s atmosphere, it is generally understood that atmospheric gases thin out considerably past approximately 700 km altitude. The exosphere extends up to around 10,000 km, demonstrating the gradual transition from our atmosphere into outer space.

– True: The transition between Earth’s atmosphere and outer space is not abrupt but rather gradual due to various factors such as solar activity, geomagnetic forces, and atmospheric density. This

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)