Status: Unknown

Assertion

Immigration leads to fewer jobs and lower wages for people in the host country.

Results

2. **Factual Assumption**: The Green Revolution in the mid-20th century, led by Norman Borlaug’s work on high-yielding varieties of crops, has been universally deemed as a complete failure due to its negative environmental impact and unsustainable practices.
– *False*: While the Green Revolution did lead to increased agricultural production and helped alleviate food shortages in many parts of the world, it is not universally considered a complete failure. The movement has been credited with saving millions from starvation; however, its impacts on the environment and sustainability have spurred subsequent efforts towards more eco-friendly agricultural methods.

– **Reasoning**: The Green Revolution is largely recognized for having successfully increased food production through technological innovations such as high-yielding varieties of crops, improved irrigation practices, and the use of synthetic fertilizers and pesticides. Although it brought about significant environmental concerns and debates on sustainability, many consider its contributions to reducing hunger and increasing food security critical achievements. It also set a foundation for future innovations in agriculture

Assumptions

* **Correct Answer**: False

* **Assumptions (if any) that might be used to support this incorrect statement:**
– There is an absence of consensus among scientists about climate change impacts on food security.
– Technological advancements will completely mitigate the negative effects of climate change on agriculture by 2050, ensuring stable food production levels irrespective of climatic changes.
– Global adaptation and innovation in agricultural practices are so advanced that they can effectively counter any adverse impacts posed by climate change without leading to significant disruptions in global food security.
– The definition of “negligible” does not imply a level of risk or concern, but rather an insignificance which could be misleading when discussing the potential seriousness of climate-related challenges to food security.
===
Given that the statement is factually incorrect based on current scientific understanding and projections, let’s analyze hypothetical assumptions that might erroneously support such a claim:

### Hypothetical Assumptions (for illustrative purposes only):
– **Assumption 1**: Scientific

Fact Checker Output

#### True/False Analysis of Hypothetical Assumptions:

1. **Scientific Assumption**: There is a consensus among scientists that climate change has no significant impact on global food security by 2050, and technological advancements will eliminate all negative consequences.
– *False*: The scientific community largely agrees that climate change poses severe risks to global food security. While technology may help mitigate some effects of climate change, it is unlikely that any single technological solution can completely negate the impacts by 2e50 without addressing broader systemic changes and challenges in agriculture.

– **Reasoning**: The consensus among scientists regarding the negative impacts of climate change on food security is strong, with numerous studies highlighting risks such as reduced crop yields, altered precipitation patterns affecting water availability, increased prevalence of pests and diseases, and more frequent extreme weather events. While technological advancements are critical for adaptation strategies, they cannot completely eliminate the negative consequences on their own by 2050 without concerted global efforts in sustainable practices, policy changes

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)