Status: True

Assertion

You lose most of your body heat through your head.

Reasoning

The initial premise that most body heat is lost through the head has been widely accepted in many cultures, but this belief oversimplifies the complex processes involved in thermoregulation. While it’s true that the head can lose a significant amount of heat due to its high surface area and exposure (making the statement partially true), modern understanding acknowledges additional factors like clothing, metabolic rate, individual differences, and environmental conditions which influence body heat loss priorities (making the statement partly accurate). Therefore, considering these nuances, the statement is True but with important caveats.

True: The concept that most body heat is lost through the head has been debunked by modern scientific understanding of thermoregulation; however, the belief persists in many cultures due to historical notions and oversimplifications (making the statement partially false). Although it’s true that the head can lose a significant amount of heat because of its large surface area exposed to external temperatures, this idea doesn’t fully capture how body heat loss is regulated by various physiological mechanisms (making the statement partly inaccurate but still retaining some truth). Therefore, considering these details, the classification would

Assumptions

– Early beliefs about body heat loss: Earlier theories posited significant heat loss from the head due to its high surface area.
– Misunderstanding of human thermoregulation: The idea that most body heat is lost through the head oversimplifies how the body regulates temperature.
– Influence of environmental conditions: Certain cold environments may exacerbate the perceived importance of protecting the head, but this doesn’t mean it’s universally true for all situations or individuals.
– Varied individual responses to cold: Different people might lose heat at different rates from various parts of their bodies due to factors like metabolism, clothing insulation, and personal physiology.
– Lack of comprehensive studies: The original statement may have been based on limited research that didn’t account for the complexity of human thermoregulation in diverse conditions.
– Need for updated guidelines: As understanding improves, so should recommendations for cold weather safety and insulation practices to reflect current knowledge about body heat loss.

Remember, these assumptions do not make the statement true; instead, they illustrate why further investigation into human thermoregulation is necessary.

Fact Checker Output

<|assistant|> True: Early beliefs about body heat loss did posit significant heat loss from the head due to its high surface area. This has been a widely held notion for many years before more nuanced understandings of thermoregulation were developed.

True: The idea that most body heat is lost through the head does indeed oversimplify how the human body regulates temperature, as it doesn’t account for factors like clothing and metabolic differences among individuals.

True: Environmental conditions can influence perceived importance of protecting certain parts of the body; however, this perception varies with context, indicating that it is not universally true across all situations or people.

True: Varied individual responses to cold are evident as some people may experience different rates of heat loss from various areas due to personal physiology and other factors such as clothing insulation and metabolism.

True: The original statement might have been based on limited research, which is a common limitation in early scientific studies before advancements allowed for more comprehensive understanding of human thermoregulation.

True: As the understanding of body heat loss improves, it’s important that safety guidelines and insulation recommend

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)