Status: False

Assertion

The Great Barrier Reef is the largest living structure on Earth.

Results

While the assumption that “True” refers to size comparison between entities is generally accurate, it oversimplifies certain contexts where exceptions might exist (e.g., comparing coral reefs with underwater features). Additionally, though considering overall area covered when comparing sizes is commonly relevant, specific circumstances may warrant more nuanced evaluations based on unique criteria. Therefore, the statement should be considered as having some false elements due to these potential exceptions and context-dependent considerations.

For further clarification:
– The assumption that “True” refers to size comparison between entities is generally accurate but might not encompass all possible scenarios where specific conditions or factors affect how sizes are compared (e.g., comparing coral reefs with other underwater structures).

– Assuming total area coverage as a relevant factor for size comparisons aligns with general practices, although there could be cases when focusing on individual components may provide more detailed insights depending on the context and purpose of comparison.

– The assertion that no exceptions exist in comparing sizes is false since specific circumstances or criteria might influence how entities are compared (e.g., size comparisons involving unique underwater features). While it’s

Assumptions

* The assumption that “True” refers to the size comparison between the Great Barrier Reef and other structures or ecosystems.
* Assuming that when comparing sizes, one is referring to total area covered rather than individual structural components.
* That there are no exceptions where coral reefs might be considered larger structures in a specific context (e.g., as part of an underwater mountain range).
* The assumption that “False” indicates the Great Barrier Reef should not be classified as a structure, despite its complexity and significance.
* Recognition that the term “structure” typically refers to man-made constructions or physical formations rather than ecosystems like coral reefs.

Fact Checker Output

<|assistant|> 1. The assumption that “True” refers to the size comparison between the Great Barrier Reef and other structures or ecosystems: True. This statement assumes a general understanding of comparing sizes, which typically involves evaluating one entity against another in terms of area, volume, or some measure of magnitude.

2. Assuming that when comparing sizes, one is referring to total area covered rather than individual structural components: True. When making comparisons between different entities, it’s common to consider the overall size (area) they cover as a relevant factor for comparison. While specific parts can contribute to this total area, focusing on them individually might not provide an accurate or meaningful context for comparison.

3. That there are no exceptions where coral reefs might be considered larger structures in a specific context: False. There could indeed be exceptions based on certain criteria, such as when considering the Great Barrier Reef’s size relative to other underwater features (e.g., an extensive seamount system). In these cases, comparing its size to individual components of those systems may reveal it as larger than anticipated by focusing only on coral reefs in general.

4. The assumption

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)