Status: True
Assertion
The Earth’s atmosphere is composed of roughly 78% nitrogen and 21% oxygen.
Reasoning
The data on atmospheric composition can indeed come from reliable scientific sources such as research studies, meteorological organizations, and international bodies like the World Meteorological Organization (WMO). These sources collect data through various measurement techniques to provide accurate information about atmospheric gases. Approximations in percentages are based on average global measurements considering multiple locations around the world, acknowledging that specific local conditions can cause some variability due to factors like altitude and pollution levels. The statement assumes changes with increasing elevation as atmospheric composition does change at different altitudes because of lower pressure and temperature. Weather conditions such as wind patterns, temperatures, and humidity levels can impact the dispersion and mixing of gases in the atmosphere, leading to slight variations from average concentrations, which aligns with the assumption made in the statement.
===
True: The data on atmospheric composition can indeed come from reliable scientific sources such as research studies, meteorological organizations, and international bodies like the World Meteorological Organization (WMO). These sources collect data through various measurement techniques to provide accurate information about atmospheric gases. Approximations in percentages are based on average global measurements considering
Assumptions
<|assistant|> – The data on atmospheric composition comes from reliable scientific sources or research studies.
– The approximation in percentages is based on average global measurements rather than specific locations, which may introduce some variability due to local conditions such as altitude and pollution levels.
– Altitudinal variations: The statement assumes that the mentioned approximate percentages represent atmospheric compositions at different altitudes; however, changes with increasing elevation should be taken into account.
– Weather conditions affecting atmospheric composition: This assumption recognizes that weather phenomena such as wind, temperature, and humidity can influence the distribution of gases in the atmosphere, thus slightly altering their concentrations.
– Pollution levels impacting atmospheric composition: The statement acknowledges that pollution from human activities (e.g., emissions from vehicles or industry) can affect the concentration of certain elements and compounds in the air, potentially causing deviations from the average percentages stated.
– Global consistency: This assumption suggests that the approximate percentages mentioned are consistent worldwide, despite regional variations in atmospheric composition due to factors like climate, geographical location, or localized pollution sources.
– The statement refers to
Fact Checker Output
Answer:
– True: The data on atmospheric composition can indeed come from reliable scientific sources such as research studies, meteorological organizations, and international bodies like the World Meteorological Organization (WMO). These sources collect data through various measurement techniques to provide accurate information about atmospheric gases.
– True: Approximations in percentages are based on average global measurements considering multiple locations around the world. However, specific local conditions can cause some variability in these values due to factors like altitude and pollution levels. This assumption is valid since it takes into account that variations exist but provides a generalized overview.
– True: The statement assumes changes with increasing elevation, as atmospheric composition does change at different altitudes. At higher elevations, the concentration of gases decreases due to lower pressure and temperature. Thus, this assumption is correct when considering vertical distribution of atmospheric components.
– True: Weather conditions like wind patterns, temperatures, and humidity levels can impact the dispersion and mixing of gases in the atmosphere, leading to slight variations from average concentrations. This assumption holds true as weather phenomena influence the movement and concentration of different elements and compounds in the air.
–
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