Status: True

Assertion

The death penalty is a deterrent to crime.

Reasoning

The statement aligns with research findings that suggest limited deterrence effect, acknowledges the methodological challenges in measuring long-term effects of capital punishment on crime rates, recognizes broader socio-economic influences on criminal behavior, highlights ethical concerns regarding taking human life as a form of punishment, and notes the existence of alternative forms of punishment.
TA: – True: The statement aligns with research findings that suggest limited deterrence effect, acknowledges the methodological challenges in measuring long-term effects of capital punishment on crime rates, recognizes broader socio-economic influences on criminal behavior, highlights ethical concerns regarding taking human life as a form of punishment, and notes the existence of alternative forms of punishment.

Assumptions

<|assistant|> – Research suggests limited deterrence effect: The statement assumes that existing studies provide evidence suggesting the death penalty may have a limited impact on preventing serious crimes like murder as a deterrent.
– Methodological challenges in measuring long-term effects: It’s assumed that accurately determining the direct influence of the death penalty on crime rates is difficult due to factors such as data limitations, time lags between policy changes and observable effects, and potential confounding variables.
– Broader socio-economic influences play a role in criminal behavior: The statement assumes that factors like poverty, education, social inequality, mental health, and cultural norms may have more significant impacts on crime rates than the death penalty itself.
– Ethical concerns regarding taking human life as punishment: It’s assumed that there are ethical considerations surrounding capital punishment, which affect its evaluation in terms of deterrence and overall effectiveness.
– Alternative forms of punishment exist: The statement assumes that other sentencing options (e.g., imprisonment) can potentially address crime prevention more effectively or humanely than the death penalty.
– Debate requires careful consideration of various factors: It’s

Fact Checker Output

<|assistant|> – Research suggests limited deterrence effect: True. Numerous studies have shown mixed results regarding the death penalty’s impact on crime rates, with some indicating a minimal deterrent effect compared to other factors affecting criminal behavior.
– Methodological challenges in measuring long-term effects: True. Measuring the direct influence of the death penalty on crime is complex due to various reasons like data limitations and confounding variables that make it difficult to isolate its specific impact over time.
– Broader socio-economic influences play a role in criminal behavior: True. Research consistently shows that factors such as poverty, education, social inequality, mental health, and cultural norms have significant effects on crime rates, often outweighing the potential deterrent effect of capital punishment alone.
– Ethical concerns regarding taking human life as punishment: True. The death penalty raises ethical issues related to state-sanctioned killing, rehabilitation versus retribution, and potential wrongful executions, which contribute to ongoing debates about its justification.
– Alternative forms of punishment exist: True. Various alternative sentencing options like imprisonment, community service,

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)