Status: False
Assertion
A coin dropped from a tall building can kill someone.
Reasoning
The statement that “a falling coin could kill you if it fell from above while you were walking” is false. This conclusion arises from the analysis of several factors. First, although a rapidly descending object can cause injuries upon impact with someone’s face or head, such an occurrence would be highly improbable in typical circumstances due to the size and velocity of a coin. Secondly, human reaction times generally aren’t fast enough to evade an unexpected falling object without warning from above. Lastly, even considering terminal velocity—the maximum speed an object can reach as it falls through air resistance—it remains unlikely for a free-falling coin to achieve this speed unimpeded by environmental factors such as wind or the ground before reaching its potential target.
Assumptions
– The height from which the coin is dropped would be significant enough to cause fatal harm.
– The person being struck by the coin could not dodge it in time, which under normal circumstances is highly unlikely due to human reaction times and space considerations.
– There’s an assumption that a coin can reach terminal velocity (the speed at which falling objects fall no faster because their acceleration has been cancelled by the drag) without hitting other obstacles first.
– The assumption ignores safety measures typically in place around buildings, such as barriers or distance from pedestrian areas, designed to prevent accidents of this nature.
Fact Checker Output
<|assistant|> – **The height from which the coin is dropped would be significant enough to cause fatal harm.**
* False. While falling objects can potentially cause injury, a common coin dropped from typical building heights (e.g., less than 30 meters) does not usually reach speeds that could result in fatal injuries upon impact with a person, due to gravitational acceleration and air resistance acting together over the distance of fall.
– **The person being struck by the coin could not dodge it in time, which under normal circumstances is highly unlikely due to human reaction times and space considerations.**
* True. Human reaction times typically range from 0.25 seconds for a light stimulus up to around 0.37 seconds for more complex tasks, and the average person cannot move that fast in response to a falling object. Additionally, there isn’t usually much room between a building and pedestrian areas where such an event could occur without warning.
– **There’s an assumption that a coin can reach terminal velocity without hitting other obstacles first.**
* False. While it’s theoretically possible for a coin to accelerate due to gravity, the likelihood of reaching
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)
Leave a Reply