Fact Check: Dinosaurs went extinct because they were too big.

Status: True

Assertion

Dinosaurs went extinct because they were too big.

Results

The statement is true. There was an asteroid impact at the end of the Cretaceous period around 65 million years ago, which led to significant environmental changes that were inhospitable for many species like dinosaurs (no non-avian dinosaur remains found above K-Pg boundary layer). The evidence supporting this includes the Chicxulub crater discovery, a worldwide iridium-rich layer at the K-Pg boundary, and disrupted food chains due to decreased sunlight reaching Earth’s surface.

Assumptions

<|assistant|> – There was an asteroid impact at the end of the Cretaceous period (around 65 million years ago).

– The asteroid impact caused significant environmental changes, such as:

* A massive amount of dust and debris ejected into Earth’s atmosphere.

* Blockage of sunlight leading to a dramatic drop in global temperatures (impact winter) and disruption of photosynthesis-driven food chains.

* Alterations to the climate, including increased volcanic activity or ocean circulation changes due to debris thrown into oceans.

– The environmental conditions following the asteroid impact were inhospitable for many species, especially large vertebrates like dinosaurs.

– Dinosaurs and other affected species could not adapt quickly enough to survive these rapid and extreme changes.

– This theory is supported by evidence such as:

* The Chicxulub crater in the Yucatan Peninsula, Mexico, which dates back to around 65 million years ago.

* Iridium layer found worldwide at the K–Pg boundary (C

Fact Checker Output

<|assistant|> – True: There was an asteroid impact at the end of the Cretaceous period around 65 million years ago. This assertion is supported by evidence such as the discovery of the Chicxulub crater and a worldwide layer rich in iridium, which is rare on Earth’s surface but common in asteroids, found at the K-Pg boundary (Cretaceous-Paleogene boundary).

– True: The asteroid impact caused significant environmental changes. As mentioned above, ejected dust and debris led to a decrease in sunlight reaching Earth’s surface causing an “impact winter,” disrupting food chains based on photosynthesis, and potentially triggering increased volcanic activity or alterations in ocean circulation patterns due to the impact.

– True: The environmental conditions following the asteroid impact were inhospitable for many species, especially large vertebrates like dinosaurs. This is supported by the fact that no non-avian dinosaur remains have been found above the K-Pg boundary layer in sedimentary records worldwide, indicating their extinction around this time.

– True: Dinosaurs and other

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)

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *