Status: True

Assertion

The equator is the hottest place on Earth.

Results

Earth’s axial tilt does influence sunlight exposure across latitudes, leading to seasons. Sunlight is a primary factor affecting average temperatures in various regions. The equator generally receives more direct solar radiation due to its location, despite other local factors that might cause variations within general conditions. However, while the Earth’s axial tilt changes over long timescales (approximately 26,000 years), it is not a significant factor affecting daily or short-term weather patterns and climate observations.
t: True: The statement aligns with scientific understanding of how Earth’s axial tilt influences sunlight exposure across different latitudes and its effects on seasons and average temperatures, while also considering the general conditions experienced at the equator compared to other regions. Though it is noted that changes in Earth’s axial tilt occur over long timescales (approximately 26,000 years), these alterations have minimal impact on daily or short-term weather and climate observations.

If you need a more detailed explanation for each classification point, please let me know!

Assumptions

<|assistant|> Assumptions supporting the statement:

– Earth’s axial tilt causes varying angles of sunlight exposure across different latitudes.
– Sunlight is a primary factor influencing average temperatures in various regions.
– The equator generally experiences consistently warm temperatures throughout the year due to its geographical location and direct exposure to sunlight.
– Other factors such as altitude, weather patterns, and proximity to large bodies of water do not negate the general warming effect experienced by areas near the equator.

<|assistant|> – The statement assumes that Earth’s axial tilt remains constant over time (which is a generally accepted scientific fact).
– It assumes direct exposure to sunlight has a significant impact on temperature compared to other factors, which may not always be true due to local climate variations and weather patterns.
– The statement implies that the equatorial region’s consistent warm temperatures are solely attributed to its geographical location without considering potential changes in global climate or long-term trends.
– It assumes a direct correlation between sunlight exposure and temperature, not accounting for other factors such as atmospheric conditions (e.g., greenhouse gases) that

Fact Checker Output

<|assistant|> 1. True – Earth’s axial tilt does indeed cause varying angles of sunlight exposure across different latitudes. This tilt leads to the seasons and affects the intensity and duration of sunlight received by various regions throughout the year.

2. True – Sunlight is a primary factor influencing average temperatures in various regions. The amount, angle, and duration of sunlight that reaches Earth’s surface directly impact how warm or cool an area feels on average over time.

3. Generally True – While other factors like altitude, proximity to water bodies, and weather patterns influence local climates, the equator does receive more direct solar radiation due to its location, which generally results in consistently warm temperatures throughout the year. However, it’s important to note that there can be variations within these general conditions based on specific microclimates or short-term events.

4. False – While Earth’s axial tilt remains relatively constant over a human timescale (approximately 26,000 years), slight changes in the tilt itself occur due to gravitational forces from other celestinas like the moon and nearby planets. However, these

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)