Status: True

Assertion

Inequality is inevitable in any society.

Reasoning

The statement reflects widely acknowledged social issues such as economic inequalities, social stratification, uneven access to resources, systemic biases, and historical contexts that contribute to societal inequality. These phenomena are observed globally across different cultures and countries, making the classification of this statement true. Economic disparities exist due to factors like wealth distribution, income levels, education opportunities, and social mobility. Social stratification is evident in how individuals or groups within a society are ranked based on various criteria such as class, race, gender, etc. Uneven access to resources can be seen in the unequal availability of essential services (healthcare, education) across different demographics. Systemic biases refer to ingrained prejudices and discriminatory practices that perpetuate inequality within societal structures. Historical contexts play a significant role as past events and policies continue to impact present-day social dynamics and disparities.

Assumptions

– Economic inequalities: Differences in income, wealth distribution, and opportunities for economic advancement.
– Social stratification: Hierarchies based on social class, race, ethnicity, or other characteristics that can lead to unequal treatment and access to resources.
– Access to resources: Uneven access to education, healthcare, employment, housing, and other essential services.
– Systemic biases: Prejudices and discrimination embedded within institutions, policies, and social structures that perpetuate inequality.
– Historical contexts: The impact of historical events, such as colonization, slavery, or oppression, which can contribute to longstanding disparities among different groups in society.
– Governmental policies: Laws, regulations, and public policies that may either directly or indirectly reinforce existing inequalities.
– Global context: The influence of global economic systems, trade agreements, and international relations on domestic inequality within a nation.
– Cultural factors: Societal norms, attitudes, and beliefs that can contribute to discrimination or marginalization of certain groups based on their identity (e.g., gender, sexual orientation, religion).
– Technological

Fact Checker Output

<|assistant|> – Economic inequalities: True. Economic inequalities are widely recognized and observed across various societies around the world. These differences manifest as disparities in income, wealth distribution, and opportunities for economic advancement among different groups of people.

– Social stratification: True. Social stratification is a common phenomenon where hierarchies based on factors such as social class, race, ethnicity, or other characteristics exist within societies. This can lead to unequal treatment and access to resources for individuals belonging to these various strata.

– Access to resources: True. Uneven access to essential services like education, healthcare, employment, housing, etc., is a well-documented issue in many parts of the world, contributing to societal inequality.

– Systemic biases: True. Prejudices and discrimination embedded within institutions, policies, and social structures are pervasive across various cultures and countries. These systemic biases can perpetuate existing inequalities among different groups in society.

– Historical contexts: True. The impact of historical events such as colonization, slavery, or oppression has contributed to longstanding disparities between different ra

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)