Status: True

Assertion

Cryptocurrencies will replace traditional currencies.

Reasoning

All five statements are true based on the provided explanations. The cryptocurrency market is relatively young, lacking widespread infrastructure for mass adoption (explanation 1). A significant transition in the near term is unlikely due to technical and regulatory challenges (explanation 2), while decentralization poses a challenge to existing regulations (explanation 3). The absence of proper regulation may lead to more fraudulent activities (explanation 4), and cryptocurrencies are not suitable for daily transactions due to high volatility (explanation 5)

However, it’s important to note that the classification as “true” is based on the provided information. While these explanations provide a solid basis for classifying each statement as true, further research and analysis may reveal additional factors or perspectives that could make some aspects debatable in specific contexts.

Assumptions

<|assistant|> – Cryptocurrency market is in its early stages and lacks necessary infrastructure for large-scale transition.
– Future potential for such transition exists, but not imminent within the near term.
– Decentralization and blockchain technology present challenges to governmental and financial institution regulation.
– Lack of proper oversight increases risk of market manipulation and fraud in cryptocurrency markets.
– High price volatility makes cryptocurrencies less suitable as stable value stores or for everyday transactions.
– Limited access to necessary technology, like smartphones and internet connectivity, restricts widespread adoption among the general population.
– While some countries consider central bank digital currencies (CBDC), there is no immediate likelihood of abandoning traditional fiat currencies in favor of CBDCs.
– The existing financial ecosystem and public trust in established monetary systems may slow down or hinder the adoption rate of cryptocurrencies as mainstream currency options.
– Technological advancements required to support a large scale transition might take significant time for development, testing, and implementation.
– Economic stability and consumer confidence

Fact Checker Output

explanation: 1. True – The cryptocurrency market is relatively young with many projects still in their infancy, lacking widespread infrastructure to support large-scale transitions, such as payment systems and regulatory frameworks that are necessary for mass adoption.

2. True – While the potential for a significant transition exists due to technological advancements, it is not likely to occur in the near term as more work needs to be done on scalability, interoperability, and legal/regulatory issues.

3. True – Decentralization and blockchain technology do indeed challenge current regulatory frameworks since these systems operate outside of traditional financial institutions’ control, making it difficult for governments and financial institutions to apply existing rules effectively.

4. True – The lack of proper regulation in the cryptocurrency markets can create an environment where fraudulent activities and market manipulation may occur more frequently due to fewer safeguards against such practices.

5. True – Cryptocurrencies, particularly those not designed for daily transactions like Bitcoin, exhibit high price volatility which makes them unsuitable as stable value stores or tools for everyday purch

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)