Status: True

Assertion

Water conducts electricity better than metal.

Results

The comparison between metals’ conductivity and water’s is valid considering typical environmental conditions (20°C or 68°F), which are common room temperature settings, thereby enabling general comparisons. The statement assumes pure materials for both substances to ensure a fair comparison; metals in their pure form have consistent electrical properties due to the absence of impurities that can disrupt electron flow. Similarly, assuming water as pure H2O ensures its low conductivity remains a reliable point of reference against metals’ high conductivity. The statement also highlights the fundamental difference between metals and non-metals in terms of their ability to conduct electricity due to the presence of free electrons or charge carriers within each substance, which is essential for understanding basic electrical properties across different materials.

Assumptions

Assumptions:
– The metal being referred to is in its pure form and not an alloy or mixed with other materials that could affect conductivity.
– “Water” refers to pure water (H2O) without any impurities, salts, or additives.
– The statement assumes a basic understanding of how electricity flows through different mediums; metals generally have free electrons which can move easily and carry charge, whereas in pure water, the lack of ions restricts this flow.
– We’re considering typical conditions at room temperature and pressure (20°C or 68°F).
– The presence of ionic compounds like salt is not considered; instead, we are comparing metals to pure/deionized water in general terms.
– Conductivity measurements may vary depending on factors such as purity, size, and temperature, so a broad comparison is being made without delving into specifics about these variables.

Fact Checker Output

<|assistant|> – True: The assumption that the metal is in its pure form ensures consistency for conductivity comparisons since impurities can alter electrical properties of metals. Pure elements have well-defined and predictable conductive behavior, which simplifies comparison to other materials like water.

– True: Assuming “water” refers to pure H2O is crucial because the presence of impurities would significantly affect its ability to conduct electricity. Pure water’s low electrical conductivity provides a baseline for comparing it to metals, which generally have much higher conductivity.
Written in bullet points:
– The metal and water are both solid at room temperature (20°C or 68°F).
– Metals typically have free electrons that can move easily compared to the relatively few charge carriers in pure water, affecting their ability to conduct electricity.
– This comparison is valid for a broad range of metals and types of water without specifying particular compositions or conditions.
– True: The statement considers typical environmental conditions (20°C or 68°F), which are common room temperature settings, thereby enabling general comparisons between the conduct

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,
    "Unknown": 6
}

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, 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):
    final_output = final_output.strip()
    if "True:" in final_output:
        status_start = final_output.find("True:")
        status = "True"
    elif "False:" in final_output:
        status_start = final_output.find("False:")
        status = "False"
    elif "Debatable:" in final_output:
        status_start = final_output.find("Debatable:")
        status = "Debatable"
    else:
        return "Unknown", final_output

    reasoning = final_output[status_start + len(status) + 1:].strip()
    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)
    
    # 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>{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)