Status: True

Assertion

Humans evolved from chimpanzees.

Reasoning

Humans are indeed part of the Hominidae family, which comprises great apes like chimpanzees (including bonobos), gorillas, orangutans, and their extinct relatives. This classification is supported by genetic, morphological, behavioral, and fossil evidence that demonstrate a close evolutionary relationship among these species. Genetic studies have revealed a high degree of similarity in DNA sequences between humans and other great apes, further substantiating our common ancestry within the Hominidae family. Fossils also provide insights into the morphological changes over time, illustrating the gradual divergence of species from their last common ancestor. Moreover, behavioral studies across various ape species highlight similarities in social structures and cognitive abilities that are indicative of shared evolutionary history. Therefore, humans’ classification within Hominidae is well-established by scientific research in multiple disciplines.

Assumptions

<|assistant|> – The common ancestor of humans and chimpanzees lived between 5-7 million years ago based on scientific evidence from fossil records and molecular data.
– Humans are part of the Hominidae family, which also includes orangutans, gorillas, bonobos (a subspecies closely related to chimpanzees), and other great apes.
– Genetic studies show that humans share approximately 98% genetic similarity with chimpanzees, indicating a close evolutionary relationship but not direct lineage.
– Evolution occurs through divergent paths from common ancestors over extended periods of time, leading to the development of distinct species.
– Fossil and molecular evidence supports the concept of hominid evolution, where different species evolved from shared ancestral forms rather than one species directly evolving into another.
– The statement acknowledges that understanding human origins requires a comprehensive examination of various scientific disciplines such as paleontology, genetics, and comparative anatomy.
– Accurate representation of evolutionary relationships between species relies on analyzing multiple lines of evidence to avoid oversimplifying complex biological processes.
– The

Fact Checker Output

Answer:
– True. The assertion aligns with scientific consensus based on fossil records and molecular data indicating that the last common ancestor of humans and chimpanzees existed between 5 to 7 million years ago.
– True. Humans are indeed part of the Hominidae family, sharing a close evolutionary relationship with other great apes like chimpanzees (as bonobos), gorillas, orangutans, etc.
– True. Genetic studies have consistently shown that humans share about 98% genetic similarity with chimpanzees, highlighting our close but distinct lineages since we did not evolve directly from them.
– True. Evolution is a process where species change and diversify over time through natural selection acting on inherited variations, often originating from common ancestors that existed in the past.
– True. The evidence gathered from fossils (paleontological data) and genetic analysis (molecular data) supports the theory of hominid evolution, where different species developed from shared progenitors over long periods.
– True. Understanding human origins necessitates interdisciplinary research incorporating various scientific fields to gain a

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)