Status: True

Assertion

Water drains backwards in the Southern Hemisphere due to the Coriolis effect.

Reasoning

The statement accurately differentiates between large-scale geophysical flows, where the Coriolis effect is significant due to Earth’s rotation impacting moving fluids over extensive distances, and small-scale scenarios like water draining in a sink or bathtub, which are influenced by local conditions instead of the Coriolis force. This classification reflects factual information that aligns with scientific understanding regarding fluid dynamics and geophysical flows.

Assumptions

<|assistant|> – The statement addresses the influence of the Coriolis effect on large-scale geophysical flows such as ocean currents and wind patterns.
– Water draining behavior in small-scale scenarios like sinks or toilets is influenced by local factors rather than the Coriolis force.
– Factors affecting water drainage direction include initial conditions, shape of the basin, presence of impurities, and turbulence within the basin.
– The Coriolis effect becomes significant only on large scales where it impacts geophysical flows over extensive areas like continents or oceans.
– Misconception exists that water does not drain backward due to the Coriolis force alone, which is incorrect for small-scale situations.
– The statement implies a distinction between macroscopic and microscopic phenomena (large-scale versus local factors) in fluid dynamics.
– It suggests an understanding of how various physical forces and conditions come into play at different scales when observing fluid behavior.

Fact Checker Output

<|assistant|> – True: The statement correctly identifies that the Coriolis effect influences large-scale geophysical flows such as ocean currents and wind patterns due to the rotational influence of Earth on moving fluids over vast distances.

– True: Water draining behavior in small-scale scenarios is predominantly governed by local factors, including the shape of the basin where water drains or initial conditions. The Coriolis force has a negligible effect at this scale because its influence diminishes with smaller spatial dimensions.

– True: Factors like initial conditions (e.g., starting position), shape of the drainage basin, impurities in the fluid, and turbulence within the basin are indeed responsible for determining water drainage direction at small scales where the Coriolis effect is insignificant.

– True: The statement distinguively highlights that large-scale effects like those of the Coriolis force become relevant when observing phenomena across extensive areas, such as continents or oceans, whereas small-scale scenarios do not exhibit this influence due to its weak strength at these scales.

– True: The misconception mentioned in

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
from wordpress_helper import create_wordpress_post  # Import WordPress helper functions
import html

# Load environment variables from .env file
load_dotenv()

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):
    llm = OpenAI(temperature=0.7, model=os.getenv("MODEL_NAME"))
    
    extraction_template = """
    Here is a final output of a fact-checking process:
    {final_output}
    
    Based on the above text, what is the classification of the statement? Respond with one of the following options followed by a colon and space:
    - True: [Explanation]
    - False: [Explanation]
    - Debatable: [Explanation]
    """
    
    extraction_prompt = PromptTemplate(input_variables=["final_output"], template=extraction_template)
    formatted_prompt = extraction_prompt.format_prompt(final_output=final_output).text
    extraction_output = llm.invoke(formatted_prompt).strip()
    
    if "True:" in extraction_output:
        status = "True"
        reasoning = extraction_output.split("True:", 1)[1].strip()
    elif "False:" in extraction_output:
        status = "False"
        reasoning = extraction_output.split("False:", 1)[1].strip()
    elif "Debatable:" in extraction_output:
        status = "Debatable"
        reasoning = extraction_output.split("Debatable:", 1)[1].strip()
    else:
        status = "Unknown"
        reasoning = extraction_output
    
    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)
    
    # Print the final status and reasoning
    print(final_output)
    print(f"Status: {status}")
    print(f"Reasoning: {reasoning}")

    # Record the result in MongoDB
    try:
        print("Attempting to insert record into MongoDB...")
        insert_record(
            script_name=__file__,
            script_code=html.escape(open(__file__).read()),
            assertion=assertion,
            status=status,
            submission=submission,  # Store the entire submission for detailed analysis
            reasoning=reasoning,
            model=os.getenv("MODEL_NAME")
        )
        print("Record inserted into MongoDB successfully.")
    except Exception as e:
        print(f"Failed to insert record into MongoDB: {e}")
    
    # 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>Reasoning</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)