Status: True

Assertion

Shark attacks are common.

Results

<|assistant|> – True
– True
– False
– True
– True

The classification of the statement is as follows:
1. True
2. True
3. False (Although perceptions can be influenced by media representation, this does not directly address frequency comparison with common threats)
4. True
5. True

Assumptions

To support the statement that “shark attacks are often sensationalized and not as common as perceived,” we can make the following assumptions:

– The media tends to focus on rare, high-profile incidents rather than the more frequent but less dramatic occurrences.
– Public perception is influenced by a disproportionate representation of shark attacks in popular culture and news outlets.
– People may not be aware of the actual statistics regarding the frequency of these events compared to their perceived commonality.
– The psychological impact of fearing rare but highly publicized events can overshadow the reality that such incidents are infrequent.
– There is a difference between being attacked by a shark and the conditions surrounding an attack (e.g., location, time, circumstances), which may contribute to sensationalism in reporting.
– Education on marine life and safety measures for swimmers can help reduce fear without overstating risks.

These assumptions aim to explain why the perception of shark attacks being common is often not aligned with reality. It’s crucial to approach such topics based on scientific evidence rather than sensationalism, which can lead to misinformed public att

Fact Checker Output

<|assistant|> 1. True – Media organizations are known for prioritizing stories that capture the audience’s attention, and high-profile incidents like shark attacks often make headlines due to their unusual nature and dramatic elements. This leads to a focus on these events over more mundane but statistically significant occurrences.

2. True – Shark attack narratives are frequently depicted in movies, television shows, books, and news articles, which can influence public perception by amplifying the fear factor. These representations tend to be sensationalized for entertainment or engagement purposes.

3. False – While it’s true that many people might not have access to accurate statistics regarding shark attacks, research indicates that awarenes of actual frequencies is generally low. The perception can still be influenced by media representation and cultural narratives more than specific data on frequency.

4. True – Fearing rare events (like shark attacks) often has a stronger psychological impact on individuals compared to worrying about commonplace threats. This phenomenon, known as availability heuristic, can skew perceptions of risk associated with such incidents.

5. True – The context surrounding

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
}

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)

    # 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:
    - True
    - False
    - Debatable
    """
    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(final_output):
    final_output = final_output.lower().strip()
    if "true" in final_output:
        return "True"
    elif "false" in final_output:
        return "False"
    elif "debatable" in final_output:
        return "Debatable"
    else:
        return "Unknown"

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
    final_output = submission['final_output']
    
    # Determine the status based on the final output text
    status = extract_status(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>{final_output}</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)