Status: True

Assertion

Albert Einstein failed maths in school.

Results

The provided text indicates that Einstein struggled in school due to traditional teaching methods, which can be interpreted as an indication that these methods were not effective for him. However, it should be noted that the statement is partially supported and does not capture the full complexity of his academic journey. Therefore, a nuanced classification would suggest “Debatable” considering Einstein’s later success despite early challenges:

– Debatable: The text suggests that Albert Einstein did face difficulties with traditional teaching methods during his education, which might imply these methods were not effective for him. However, it does not definitively conclude the effectiveness of all traditional teaching methods for every student and recognizes that other factors, such as his unique learning style or external influences, contributed to his academic challenges. Therefore, while there is an indication that he struggled with these methods, we cannot categorically state they were universally ineffective based on this information alone:

– Debatable: The statement implies Einstein’s academic difficulties stemmed from traditional teaching methods; however, the text also acknowledges his unique learning style and individual factors contributing to those challenges. Therefore, while it suggests a certain effectiveness of these methods

Assumptions

* Albert Einstein struggled academically, particularly in conventional educational settings.
* Einstein’s academic challenges were specifically related to mathematics.
* The narrative that Einstein failed math is an accurate representation of his schooling experience.
* Traditional teaching methods are effective for all students, including those like Einstein who might struggle with them.
* Albert Einstein’s inability to succeed academically had no positive outcomes or contributions to science and society.

Support each bullet point based on the information provided earlier:

* Albert Einstein struggled academically, particularly in conventional educational settings: This assumption is partially supported by the statement. It mentions that he faced challenges due to his behavioral issues leading to school transfers rather than academic failure per se. However, it does acknowledge that Einstein had difficulty with certain subjects at times.
* Einstein’s academic challenges were specifically related to mathematics: The statement acknowledges that while Einstein did have difficulties in math, the popular narrative of him failing is misleading and oversimplified. It suggests his struggles may not solely be attributed to math but rather an aversion to rote learning methods prevalent at the time.

Fact Checker Output

<|assistant|> * Albert Einstein struggled academically, particularly in conventional educational settings: True (partially supported). The statement acknowledges that he had behavioral issues which led to school transfers and difficulties with certain subjects but doesn’t explicitly state academic failure across all areas.

* Einstein’s academic challenges were specifically related to mathematics: False. While the original statement does imply his struggles in math, it also suggests that these may have been due to teaching methods rather than an inherent difficulty with the subject itself. Thus, claiming his issues are “specifically” related to math is too narrow and not fully supported by the given information.

* The narrative that Einstein failed math is an accurate representation of his schooling experience: False. According to the provided text, while there was a common misconception about him failing math, it’s clear from the context that this perception doesn’t accurately reflect reality. It instead points out flaws in teaching methods and rote learning as potential factors for Einstein’s struggles rather than simply stating he failed.

* Traditional teaching methods are effective for all students, including those like Einstein who might struggle with them: False. The text implies that

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)