Status: True

Assertion

Hair can turn white due to fright.

Results

<|assistant|> The classification of the statement is “Debatable” since while there could be a connection between intense emotions and changes in hair color due to stress responses, this relationship is not definitive or immediate. Most graying occurs over time due to age-related processes and genetics rather than singular events like experiencing fright. However, without specific empirical evidence directly linking such an event with instantaneous whitening of hair across all individuals, the statement can’t be universally affirmed as true but also isn’t conclusively false.

Here is how you would structure your response:
<|assistant|> – Debatable

The classification stems from understanding that while emotions and stress may have an indirect effect on physiological changes including hair health, the direct connection implied in the statement between experiencing fright and immediate whitening of hair does not align with scientific consensus. The gradual nature of graying due to aging or genetics overshadows any instantaneous effects that might be suggested by a single intense event like fear.

Assumptions

– The assumption might be that an intense emotion like fright directly triggers complete white hair within minutes or hours.
– The assumption could be that fright universally causes the cessation of melanin production in all individuals, leading to immediate whitening of hair.
– There’s a presumption that graying is always linked with emotional stress and not just aging or genetics.
– It assumes the process by which hair turns white due to fright can be observed as an isolated event rather than a gradual change over time.

Fact Checker Output

<|assistant|> – The assumption that an intense emotion like fright directly triggers complete white hair within minutes or hours: False. While stress and emotions can affect the aging process of hair, there’s no scientific evidence to suggest they cause immediate whitening of hair in such a short timeframe. Hair color changes are typically slow processes influenced by genetics and age rather than sudden events.

– The assumption that fright universally causes the cessation of melanin production in all individuals, leading to immediate whitening of hair: False. Fear might impact an individual’s physiological response temporarily (like increased heart rate), but it does not uniformly stop melanin production in everyone’s hair follicles instantly. Melanin production cessation and resulting graying occur over a longer period, mostly due to the natural aging process.

– The presumption that graying is always linked with emotional stress and not just aging or genetics: False. While intense emotions can contribute to stress that may affect overall health, including hair, graying predominantly results from biological factors like aging and genetics. Emotional stress might exacerbate the

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
import html

# Load environment variables from .env file
load_dotenv()

# Define category IDs
CATEGORY_IDS = {
    "True": 2,
    "False": 3,
    "Debatable": 4
}

def create_wordpress_post(title, content, category):
    data = {
        "title": title,
        "content": content,
        "status": "publish",
        "categories": [CATEGORY_IDS[category]]
    }

    response = requests.post(
        os.getenv("WORDPRESS_POSTS_URL"),
        json=data,
        auth=(os.getenv("WORDPRESS_USERNAME"), os.getenv("WORDPRESS_PASSWORD"))
    )

    if response.status_code == 201:
        print("Blog post created successfully.")
    else:
        print(f"Failed to create blog post: {response.status_code} - {response.text}")

def fact_check(assertion):
    llm = OpenAI(temperature=0.7)

    # 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:
    - True
    - False
    - Debatable
    """
    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(final_output):
    final_output = final_output.lower().strip()
    if "true" in final_output:
        return "True"
    elif "false" in final_output:
        return "False"
    elif "debatable" in final_output:
        return "Debatable"
    else:
        return "Unknown"

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
    final_output = submission['final_output']
    
    # Determine the status based on the final output text
    status = extract_status(final_output)
    
    # Record the result in MongoDB
    try:
        print("Attempting to insert record into MongoDB...")
        insert_record(
            script_name="fact_checker_mongodb.py",
            script_code=html.escape(open(__file__).read()),
            assertion=assertion,
            status=status,
            submission=submission,  # Store the entire submission for detailed analysis
            model=os.getenv("MODEL_NAME")
        )
        print("Record inserted into MongoDB successfully.")
    except Exception as e:
        print(f"Failed to insert record into MongoDB: {e}")
    
    print(final_output)
    
    # 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>Results</h2>
    <p>{final_output}</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)