Status: True

Assertion

Humans are not responsible for climate change.

Reasoning

The statement aligns with scientific consensus on climate change, as there is strong agreement among scientists about the role of human activities in causing global warming. This includes recognition that burning fossil fuels contributes significantly to greenhouse gas emissions and acknowledgment of their increased levels since the industrial revolution. Scientists generally agree on these issues due to extensive research and evidence gathered over decades, which consistently point towards human impact as a major driver for climate change.
– True: The statement accurately reflects scientific understanding and data on climate change, as there is overwhelming evidence from various sources confirming human activities as major contributors to this global issue. Scientific studies across disciplines such as atmospheric science, oceanography, ecology, and climatology all support the claim that human actions—especially fossil fuel consumption—play a substantial role in climate change.
– False: The statement is not supported by scientific consensus or research findings; however, it’s important to note that while there might be some nuanced discussions on specific aspects of climate science within individual disciplines, the general agreement among scientists about human contributions to global warming and increased greenhouse gas emissions

Assumptions

<|assistant|> – A consensus among scientists exists regarding human activities contributing significantly to climate change.
– The majority of climate scientists agree on this issue, indicating a strong scientific consensus.
– Burning fossil fuels is one specific human activity that contributes to climate change.
– Greenhouse gas emissions have increased dramatically since the industrial revolution began around 200 years ago.
– Scientific evidence correlates greenhouse gas emissions with current climate changes.
– Natural factors such as solar radiation and volcanic activity do influence climate, but they don’t account for all observed warming trends.
– The Intergovernmental Panel on Climate Change (IPCC) reports that human activities are estimated to be responsible for approximately 100% of the observed temperature increase since 1950.

Fact Checker Output

<|assistant|> – True: A consensus among scientists does exist regarding human activities contributing significantly to climate change. The evidence from various scientific studies and organizations indicates a strong agreement (e.g., the National Academy of Sciences).
– True: The majority of climate scientists agree on this issue, indicating a strong scientific consensus. Surveys and assessments like those conducted by NASA’s Goddard Institute for Space Studies have shown that over 97% of climatologists agree humans are causing global warming (as per the statement from Naomi Oreskes in her paper).
– True: Burning fossil fuels is one specific human activity that contributes to climate change. The combustion of coal, oil, and natural gas releases large amounts of carbon dioxinate (CO2) into the atmosphere, which enhances the greenhouse effect.
– True: Greenhouse gas emissions have increased dramatically since the industrial revolution began around 200 years ago. Historical data clearly shows a significant rise in CO2 levels from about 280 parts per million during pre-industrial times to over 415 ppm today (as reported by NASA’s Goddard Institute for Space Studies

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)