Status: True

Assertion

The Earth is the third planet from the Sun.

Reasoning

Marie Curie’s research was indeed seminal in advancing our understanding of radioactivity. Her pioneering work led to significant developments in physics and chemistry, including the discovery of polonium and radium. Additionally, she contributed greatly to medical care through her development of mobile radiography units during World War I. While Marie Curie did not coin the term “radioactivity,” it is true that her contributions were foundational in its study and popularization within scientific communities.
<|assistant|> – False: The statement suggesting that Marie Curie coined the term “radioactivity” from a Latin root (radix) is incorrect because there’s no evidence showing she was responsible for naming this phenomenon. However, it is true that her research greatly influenced our understanding of radioactive elements and their behaviors.
<|assistant|> – Debatable: The notion that Marie Curie named the term “radioactivity” could be seen as debatable since while she didn’t directly coin the term, her extensive work on the topic did lead to its widespread use and recognition within scientific circles. However, this does not mean that she was responsible for coining it.

Assumptions

<|assistant|> – Marie Curie’s research was seminal in advancing our understanding of radioactivity.

– She discovered new elements: polonium and radium.

– Her work on X-ray technology significantly benefited wartime medical care.

– Marie Curie received the Nobel Prize in Physics in 1903 for her research into spontaneous radiation.

– The term “radioactivity” was coined by Marie Curie, which is a Latin origin related to her field (radix means root).

– She won another Nobel Prize in Chemistry in 1911 for her discovery of the elements radium and polonium.

Fact Checker Output

<|assistant|> – True: Marie Curie’s research was indeed seminal in advancing our understanding of radioactivity. Her pioneering work led to significant developments in physics and chemistry.

– True: She discovered the elements polonium (named after her native Poland) and radium. These discoveries were crucial contributions to science, especially for the field of nuclear physics.

– True: Marie Curie’s research into X-ray technology during World War I revolutionized medical care by providing mobile radiography units that could be used in field hospitranes. This greatly improved battlefield medicine.

– True: Marie Curie received the Nobel Prize in Physics in 1903, which she shared with her husband Pierre Curie and Henri Becquerel for their combined work on radioactivity. Although “radioactivity” is associated with her name, it was not coined by her; rather, the term encompasses the phenomena they all studied.

– False: The assertion that Marie Curie coined the term “radioactivity,” meaning root in Latin (radix), is incorrect. While she did popularize and help define the concept of radioactivity as a phenomenon, the exact

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)