Status: True

Assertion

The equator is the hottest place on Earth.

Results

The Earth’s geographical positioning near the equator causes more direct sunlight exposure, leading to higher temperatures. While local weather patterns and altitude can influence temperature variations, they do not significantly change the overall trend of high equatorial temperatures. Ocean currents may have a minor impact on coastal regions, but their effect is less significant than other factors like latitude or solar radiation intensity. Temporary fluctuations in temperature at the equator can occur due to natural climate phenomena such as El Niño and La Niña events.

Therefore, based on the information provided, the statement can be classified as true: The Earth’s geographical positioning near the equator contributes to higher temperatures primarily because of increased solar radiation absorption by land and water surfaces in that region.

Assumptions

<|assistant|> – The Earth’s geographical positioning plays a significant role in temperature distribution, with regions along the equator receiving more consistent sunlight throughout the year.
– Local weather patterns and atmospheric conditions can impact temperatures at specific locations near the equator but do not negate the general trend of high temperatures.
– Altitude does not significantly affect temperatures near the equator, as this factor becomes more relevant in higher latitudes where temperature changes with elevation are more pronounced.
– Ocean currents have a minor influence on equatorial climate compared to other factors but can still contribute to localized variations in temperature (e.g., cold oceanic currents bringing cooler temperatures).
– The statement takes into account the overall pattern of high temperatures near the equator while acknowledging that there may be occasional fluctuations due to natural climate phenomena like El Niño and La Niña events.
– It assumes a broad understanding of Earth’s climate system, including its geophysical features, atmospheric processes, and the influence of solar radiation on temperature distribution.

Fact Checker Output

<|assistant|> 1. True – The Earth’s geographical positioning near the equator means that sunlight hits these regions more directly throughout the year, leading to higher temperatures due to increased solar radiation and heat absorption by land and water surfaces.
2. True – Local weather patterns such as monsoons or trade winds can influence short-term temperature variations at specific locations but do not significantly alter the overall trend of high equatorial temperatures.
3. False – Altitude does have a more noticeable effect on temperatures in higher latitudes, where changes with elevation are more pronounced. Near the equator, temperature differences due to altitude alone are less significant compared to other factors like latitude and solar radiation.
4. True – Ocean currents can indeed affect localized equatorial climates; however, their impact is generally smaller than that of proximity to the Equator or solar radiation intensity. For example, cold oceanic currents may slightly reduce temperatures in coastal regions near the equator but do not dominate over other factors.
5. True – Temporary fluctuations in temperature around the equator can occur due to natural climate phenomena like El Niño and La Niña events

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)