Status: True

Assertion

The Earth revolves around the Sun.

Reasoning

[Explanation]
– False: [Explanation]
– Debatable: [Explanation]

explanation
Debatable: While it is true that an individual would need to live for several centuries to witness the first solar eclipse from their exact location, whether this statement can be considered “true” depends on various factors such as technological advancements, life expectancy, and future changes in Earth’s rotation.

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: [Explan

Assumptions

To calculate this, we have:

\[ \text{Number of Earth years} = (75 – 3) \]
\[ \text{Earth revolutions} = \frac{\text{Number of Earth years}}{1} \]
\[ \text{Earth revolutions} = 72 \]

So, by the time you reach the age of 75, Earth will have completed approximately 72 orbits around the Sun. However, a solar eclipse from Pluto’s perspective is not feasible due to its distant location in our Solar System and the alignment required for an observer on Pluto to experience such an event directly. Therefore, this scenario does not happen within your lifetime concerning actual observation from Pluto.

As for calculating the probability of a solar eclipse being visible from Pluto during one’s lifetime (which is practically impossible), we would need more complex astrophysical calculations considering Earth-Pluto alignments over time and cannot be calculated using simple arithmetic. However, given that no direct observation on Pluto can occur due to its distance from the Sun relative to our viewpoint, this probability effectively becomes zero within a human lifetime for observational purposes.

Fact Checker Output

A) The Earth completes exactly 72 revolutions around the Sun in 75 years.

B) An observer on Pluto would be able to witness solar eclipses from our perspective as seen from Earth.

C) It is possible for an individual to live long enough to experience a unique astronomical event that they have never observed before, such as the first-ever solar eclipse visible from their exact location if it were somehow observable there.

D) The calculation provided gives us the number of times Pluto would complete one orbit around the Sun in 75 Earth years, assuming we can observe its orbits directly.

E) A theoretical scenario where an individual could witness a solar eclipse from Pluto’s perspective during their lifetime is plausible with current technology and understanding of our Solar System’s dynamics.
<|assistant|> A) False – The calculation provided gives the number of Earth revolutions completed by 75 years, not exact orbits around the Sun, as it assumes one year equals one Earth orbit (which is approximately true but not exactly due to slight variations in the orbital period). However, even if we assume an exact one-toe-one correspondence for simplicity’s sake

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)