Status: False

Assertion

Goldfish have a three-second memory.

Reasoning

The provided information indicates that scientific evidence contradicts the claim about goldfish having only three seconds of short-term memory. Studies have demonstrated their ability to learn tasks after several minutes or even hours, suggesting more advanced cognitive abilities than commonly believed. However, it is also acknowledged that research on goldfish’s memory capabilities isn’t fully comprehensive due to existing limitations. Hence, while the specific claim about three-second short-term memory span being accurate for goldfish is false based on available evidence, a more complete understanding of their cognitive abilities would require further investigation.

Assumptions

<|assistant|> – Goldfish are commonly believed to have a short-term memory span of only three seconds due to popular myths.
– Scientific evidence contradicts this belief, showing that goldfish can learn tasks after just one trial lasting several minutes or even hours.
– Studies on goldfish demonstrate their ability to be conditioned to respond to specific stimuli, such as associating light with food rewards.
– Goldfish exhibit habituation and sensitization behaviors, which suggests some level of short-term memory capabilities.
– The duration or complexity of goldfish’s memory is not well understood due to limitations in current research methods, but they display more sophisticated cognitive abilities than commonly believed.
– The myth about goldfish having a three-second memory likely arose from misunderstandings regarding human short-term and long-term memory processes.
– Goldfish’s complex behaviors and learning capabilities are often underestimated, despite existing scientific evidence disproving the myth of their limited memory span.

Fact Checker Output

<|assistant|> – True: Scientific evidence contradicts the belief that goldfish have a short-term memory span of only three seconds due to studies demonstrating their ability to learn tasks after just one trial lasting several minutes or even hours. This indicates that they possess more sophisticated cognitive abilities than commonly believed.

– True: Studies on goldfish showing the conditioning of responses to specific stimuli (like associating light with food rewards) imply their ability for short-term memory, as they need to remember which cue leads to a reward after initial learning.

– True: Goldfish exhibiting habituation and sensitization behaviors suggests some level of short-term memory capabilities since these processes require an organism to recognize changes in stimuli over brief periods.

– False (current understanding): While there is evidence pointing towards goldfish’s memory abilities, the exact duration or complexity of their memory remains unclear due to research limitations. However, this doesn’t imply that they have a three-second memory span; it merely states our current knowledge isn’t fully comprehensive about these fishes’ cognitive capabilities.

– True: The myth likely arose from misunderstandings regarding human short-

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)