Status: True

Assertion

Genetically modified foods are harmful to human health.

Results

The statement can be considered true as regulatory bodies like the FDA and EFSA conduct thorough risk assessments of GM foods, examining both short-term and long-term effects. However, it’s important to note that the process is complex and involves multiple stages, including laboratory tests, animal feeding studies, and environmental impact evaluations.
– False: The statement can be considered false because while safety assessments are performed on GM foods, they may not always be comprehensive or universally rigorous for every individual case. Regulatory bodies aim to ensure public health but the process is continuously evolving as new research emerges.
– Debatable: The statement could be considered debatable, as opinions vary regarding the thoroughness and consistency of safety assessments across different regions and regulatory agencies. While some organizations conduct rigorous evaluations, others may have differing approaches or face challenges in keeping up with advancing technology and emerging risks.

* Assumption

Assumptions

* Assumption 1: …
* Assumption 2: …
* Assumption 3: …

<|assistant|> * Assumption 1: The existing body of scientific research, including studies conducted by reputable organizations like WHO and AMA, provides a comprehensive understanding of the health impacts associated with genetically modified (GM) foods.
* Assumption 2: GM foods are subjected to rigorous safety assessments on an individual basis before reaching consumers, taking into account potential long-term effects and environmental consequences.
* Assumption 3: The current debate around the topic of GM foods reflects a scientifically informed discourse rather than being predominantly influenced by misinformation or unverified claims.
* Assumption 4: The health risks associated with GM food consumption are primarily concerned with potential long-term effects and environmental impact, rather than immediate adverse reactions in consumers.
* Assumption 5: There is no conclusive evidence linking the consumption of genetically modified foods to antibiotic resistance or allergenic responses when examined through existing studies on currently available GM products.
* Assumption 6: The

Fact Checker Output

For example:
1. True – This assumption is based on the consensus among scientific organizations like WHO and AMA that have conducted extensive research on GM foods’ health impacts.
2. False – While safety assessments are performed, it cannot be universally assumed to be rigorous without specific evidence for each case.
3. True/False (with explanation) – This depends on the sources of information considered and whether they represent a balanced view based on scientific findings.

* Assumption 1: The existing body of scientific research, including studies conducted by reputable organizations like WHO and AMA, provides a comprehensive understanding of the health impacts associated with genetically modified (GM) foods.
– True – Reputable organizations such as WHO and AMA have conducted extensive research on GM foods, providing insights into their potential health effects. However, it’s important to note that scientific consensus evolves over time, so while comprehensive at the moment, there may be new findings in the future.
* Assumption 2: GM foods are subjected to rigorous safety assessments on an individual basis before reaching consumers, taking into

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)