Status: True

Assertion

The blood in your veins is blue until it hits the air.

Reasoning

Although the statement on light interaction and brain interpretation is scientifically accurate, the claim about human veins being universally blue is incorrect from a biological standpoint. Yet, this point’s inclusion may shape discussions on misconceptions in anatomy education or visual perception.

– False: The statement contains elements of truth regarding light interaction and brain interpretation but fails to accurately describe blood color inside the body as blue; however, it highlights a potential misunderstanding that could be explored further in educational contexts.

– Debatable: While the facts about light-tissue interaction are correct, the claim about veins being universally blue is biologically false, but this misconception can still spark discussions on public perception and scientific literacy; hence it’s debatable due to

Assumptions

1. Light interaction with tissues and perception by the human eye: The statement assumes that light behaves as it does when passing through different media (skin, muscle, etc.) and is perceived by our eyes based on its wavelengths within a certain range.

2. Brain interpretation of visual signals: It assumes that our brain processes and interprets the incoming light signals to give rise to the perception of colors as blue for veins.

3. Color misconception about human blood: The statement relies on the common but incorrect belief that human blood is blue, which might lead people to think it retains its color when exposed to air (though this isn’t true).

4. Vein visibility through skin: It assumes that veins are visible through the skin and their perceived color can be attributed to factors other than their actual hue, such as light interaction with tissue layers.

It’s important to clarify these assumptions when discussing this topic to dispel misconceptions about the true color of blood in human physiology. In reality, oxygenated blood is bright red and deoxygenated (venous) blood appears darker due to a

Fact Checker Output

<|assistant|> 1. True – Light interaction with tissues and perception by the human eye: This assertion is true because light does indeed behave according to the principles of optics when passing through different media such as skin, muscle, etc. The way light interacts with these tissues can affect its wavelengths and intensity, which are then perceived by our eyes within a certain range (approximately 380-750 nanometers for visible light).

2. True – Brain interpretation of visual signals: This assumption is true as well. Our brain processes the incoming light signals from the retina and interprets them to give rise to color perception. However, it’s important to note that our perception of colors like blue veins can be influenced by several factors including contextual cues (e.g., surrounding skin tones), cognitive biases, or even misperception due to optical illusions.

3. False – Color misconception about human blood: The belief that human blood is blue inside the body is false; however, this common misconception might contribute to people thinking veins appear bluish when they are exposed to air (deoxygenated

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)