| import gradio as gr | |
| import pandas as pd | |
| import plotly.express as px | |
| data = pd.read_csv('data/env_disclosure_data.csv') | |
| data = data.drop('Unnamed: 0', axis=1) | |
| data['Environmental Transparency'] = data['Environmental Transparency'].fillna('None') | |
| data.Organization = data.Organization.replace('University of Montreal / Université de Montréal', 'University of Montreal') | |
| data.Organization = data.Organization.replace('University of Washington,Allen Institute for AI', 'Allen Institute for AI') | |
| data.Organization = data.Organization.replace('Allen Institute for AI,University of Washington', 'Allen Institute for AI') | |
| data.Organization = data.Organization.replace(['Google', 'DeepMind', 'Google DeepMind','Google Brain','Google Research'], 'Alphabet') | |
| data.Organization = data.Organization.replace(['Meta AI','Facebook AI Research','Facebook AI', 'Facebook'], 'Meta') | |
| data.Organization = data.Organization.replace(['Microsoft','Microsoft Research'], 'Microsoft') | |
| organizations=['Alphabet', 'OpenAI', 'Alibaba', 'Stanford University', 'University of Toronto','University of Toronto', 'Microsoft', 'NVIDIA', | |
| 'Carnegie Mellon University (CMU)', 'University of Oxford','University of California (UC) Berkeley','Baidu','Anthropic', | |
| 'Salesforce Research', 'Amazon', 'University of Montreal', 'Apple', 'Mistral AI', 'DeepSeek', 'Allen Institute for AI'] | |
| def generate_figure(org_name): | |
| org_data = data[data['Organization'] == org_name] | |
| fig = px.histogram(org_data, x="Year", color="Environmental Transparency") | |
| fig.update_layout(xaxis_type='category') | |
| return fig | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Environmental Transparency Explorer Tool") | |
| gr.Markdown("## Explore the data from 'Misinformation by Omission: The Need for More Environmental Transparency in AI'") | |
| with gr.Accordion('Methodology', open=False): | |
| gr.Markdown('We analyzed Epoch AI\'s "Notable AI Models" dataset, which tracks information on “models that were state of the art, highly cited, \ | |
| or otherwise historically notable” released over time. We selected the time period starting in 2010 as this is the beginning of the modern “deep learning era” \ | |
| (as defined by Epoch AI), which is representative of the types of AI models currently trained and deployed, including all 754 models from 2010 \ | |
| to the first quarter of 2025 in our analysis. We examined the level of environmental impact transparency for each model based on key information \ | |
| from the Epoch AI dataset (e.g., model accessibility, training compute estimation method) as well as from individual model release content \ | |
| (e.g., paper, model card, announcement).') | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| org_choice= gr.Dropdown(organizations, value="Alphabet", label="Organizations", info="Pick an organization to explore their environmental disclosures", interactive=True) | |
| gr.Markdown('The 3 transparency categories are:') | |
| gr.Markdown('**Direct Disclosure**: Developers explicitly reported energy or GHG emissions, e.g., using hardware TDP, country average carbon intensity or measurements.') | |
| gr.Markdown('**Indirect Disclosure**: Developers provided training compute data or released their model weights, allowing external estimates of training or inference impacts.') | |
| gr.Markdown('**No Disclosure**: Environmental impact data was not publicly released and estimation approaches (as noted in Indirect Disclosure) were not possible.') | |
| with gr.Column(scale=4): | |
| gr.Markdown("### Data by Organization") | |
| fig = generate_figure(org_choice) | |
| plt = gr.Plot(fig) | |
| with gr.Row(): | |
| with gr.Column(): | |
| gr.Markdown("### All Data") | |
| fig2 = px.histogram(data, x="Year", color="Environmental Transparency") | |
| fig2.update_layout(xaxis_type='category') | |
| plt2 = gr.Plot(fig2) | |
| org_choice.select(generate_figure, inputs=[org_choice], outputs=[plt]) | |
| demo.launch() | |