Spaces:
Runtime error
Runtime error
Commit
Β·
458cf5b
1
Parent(s):
a988195
readme, agreements, terms, privacy, checkboxes priort to submission
Browse files- README.md +19 -26
- SECURITY.md +4 -0
- TRADEMARKS.md +5 -0
- app.py +34 -1
- docs/privacy-policy.md +56 -0
- src/display/css_html_js.py +37 -0
- terms/submission-agreement.md +66 -0
README.md
CHANGED
|
@@ -13,35 +13,28 @@ sdk_version: 5.42.0
|
|
| 13 |
python_version: 3.12.0
|
| 14 |
---
|
| 15 |
|
| 16 |
-
# Start the configuration
|
| 17 |
|
| 18 |
-
|
| 19 |
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
-
|
| 23 |
-
{
|
| 24 |
-
"config": {
|
| 25 |
-
"model_dtype": "torch.float16", # or torch.bfloat16 or 8bit or 4bit
|
| 26 |
-
"model_name": "path of the model on the hub: org/model",
|
| 27 |
-
"model_sha": "revision on the hub",
|
| 28 |
-
},
|
| 29 |
-
"results": {
|
| 30 |
-
"task_name": {
|
| 31 |
-
"metric_name": score,
|
| 32 |
-
},
|
| 33 |
-
"task_name2": {
|
| 34 |
-
"metric_name": score,
|
| 35 |
-
}
|
| 36 |
-
}
|
| 37 |
-
}
|
| 38 |
-
```
|
| 39 |
|
| 40 |
-
|
| 41 |
|
| 42 |
-
|
|
|
|
|
|
|
| 43 |
|
| 44 |
-
You'll find
|
| 45 |
-
- The main table columns names and properties in `src/display/utils.py`
|
| 46 |
-
- The logic to read all results and request files, then convert them in dataframe lines, in `src/populate.py`
|
| 47 |
-
- The logic to allow or filter submissions in `src/submission/submit.py`.
|
|
|
|
| 13 |
python_version: 3.12.0
|
| 14 |
---
|
| 15 |
|
|
|
|
| 16 |
|
| 17 |
+
### Competition terms
|
| 18 |
|
| 19 |
+
- By submitting, you agree to the **FormulaOne Submission Agreement
|
| 20 |
+
(v1.2)** and our **Privacy Notice**.
|
| 21 |
+
- Your uploaded file remains yours; we only use it to evaluate, score,
|
| 22 |
+
and contact you about your result.
|
| 23 |
+
**Licensing for the public benchmark assets (informational)**
|
| 24 |
+
- **Evaluator code:** Apache License 2.0
|
| 25 |
+
- **Problem statements & public tests:** Creative Commons **CC BY 4.0**
|
| 26 |
+
See the project's **README licence section** and full texts: `LICENSE-
|
| 27 |
+
APACHE2`, `LICENSE-CC-BY` in our GitHub repo.
|
| 28 |
+
**Platform**
|
| 29 |
+
- Your use of Hugging Face is also governed by Hugging Face's Terms and
|
| 30 |
+
Privacy Policy.
|
| 31 |
+
-
|
| 32 |
|
| 33 |
+
# FormulaOne: Measuring the Depth of Algorithmic Reasoning Beyond Competitive Programming
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
+
This is the official Hugging Face space for the paper:
|
| 36 |
|
| 37 |
+
**FormulaOne: Measuring the Depth of Algorithmic Reasoning Beyond Competitive Programming** <br>
|
| 38 |
+
*Gal Beniamini, Yuval Dor, Alon Vinnikov, Shir Granot Peled, Or Weinstein, Or Sharir, Noam Wies, Tomer Nussbaum, Nadav Schweiger, Ido Ben Shaul, Tomer Zekharya, Yoav Levine, Shai Shalev-Shwartz, Amnon Shashua* <br>
|
| 39 |
+
**AAI, July 2025**
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
SECURITY.md
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
To report a vulnerability or security concern, email
|
| 2 | |
| 3 |
+
Please include steps to reproduce and any relevant logs. We will
|
| 4 |
+
acknowledge receipt within 3 business days.
|
TRADEMARKS.md
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"FormulaOne" is used solely to identify this research benchmark.
|
| 2 |
+
You may use the name to refer to the benchmark, but you may not use it:
|
| 3 |
+
- to imply sponsorship or endorsement of your project or results, or
|
| 4 |
+
- as part of your own product or service name without written
|
| 5 |
+
permission.
|
app.py
CHANGED
|
@@ -536,10 +536,43 @@ with blocks:
|
|
| 536 |
org_textbox = gr.Textbox(label=AutoEvalColumn.organization.name)
|
| 537 |
submission_file = gr.File(label="JSONL solutions file", file_types=[".jsonl"])
|
| 538 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 539 |
logger.info("Submit button")
|
| 540 |
-
submit_button = gr.Button("Submit", variant="primary")
|
| 541 |
submission_result = gr.Markdown()
|
| 542 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 543 |
submit_button.click(
|
| 544 |
add_solution_cbk,
|
| 545 |
[
|
|
|
|
| 536 |
org_textbox = gr.Textbox(label=AutoEvalColumn.organization.name)
|
| 537 |
submission_file = gr.File(label="JSONL solutions file", file_types=[".jsonl"])
|
| 538 |
|
| 539 |
+
# Required checkboxes
|
| 540 |
+
agreement_checkbox = gr.Checkbox(
|
| 541 |
+
label="I agree to the FormulaOne Submission Agreement (v1.2).",
|
| 542 |
+
value=False,
|
| 543 |
+
elem_classes="markdown-text",
|
| 544 |
+
)
|
| 545 |
+
|
| 546 |
+
privacy_checkbox = gr.Checkbox(
|
| 547 |
+
label="I have read the Privacy Notice.", value=False, elem_classes="markdown-text"
|
| 548 |
+
)
|
| 549 |
+
|
| 550 |
+
security_checkbox = gr.Checkbox(
|
| 551 |
+
label="I confirm this submission does not attempt to access private tests or exfiltrate data.",
|
| 552 |
+
value=False,
|
| 553 |
+
elem_classes="markdown-text",
|
| 554 |
+
)
|
| 555 |
+
|
| 556 |
+
gr.Markdown(
|
| 557 |
+
"[Privacy Notice](docs/privacy-policy.md); [Submission Agreement](docs/submission-agreement.md)",
|
| 558 |
+
elem_classes="markdown-text",
|
| 559 |
+
)
|
| 560 |
+
|
| 561 |
logger.info("Submit button")
|
| 562 |
+
submit_button = gr.Button("Submit", variant="primary", interactive=False)
|
| 563 |
submission_result = gr.Markdown()
|
| 564 |
|
| 565 |
+
# Update submit button interactivity based on checkboxes
|
| 566 |
+
def update_submit_button(agreement, privacy, security):
|
| 567 |
+
return gr.update(interactive=agreement and privacy and security)
|
| 568 |
+
|
| 569 |
+
for checkbox in [agreement_checkbox, privacy_checkbox, security_checkbox]:
|
| 570 |
+
checkbox.change(
|
| 571 |
+
update_submit_button,
|
| 572 |
+
inputs=[agreement_checkbox, privacy_checkbox, security_checkbox],
|
| 573 |
+
outputs=submit_button,
|
| 574 |
+
)
|
| 575 |
+
|
| 576 |
submit_button.click(
|
| 577 |
add_solution_cbk,
|
| 578 |
[
|
docs/privacy-policy.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FormulaOne AI Coding Challenge - Privacy Notice v1.2
|
| 2 |
+
Last updated: 6 Aug 2025
|
| 3 |
+
1 Controller
|
| 4 |
+
FormulaOne Team, <legal entity and address>
|
| 5 |
+
Contact: [email protected]
|
| 6 |
+
2 Data We Collect
|
| 7 |
+
- GitHub or Hugging Face username and public profile ID
|
| 8 |
+
- Email address (if supplied via OAuth)
|
| 9 |
+
- Uploaded Submission files, compile/runtime logs, numeric scores
|
| 10 |
+
- IP address and browser telemetry for security and rate limiting
|
| 11 |
+
3 Purposes and GDPR Legal Bases
|
| 12 |
+
Purpose | Basis
|
| 13 |
+
---------------------------------------------- | -------------------
|
| 14 |
+
---
|
| 15 |
+
Evaluate and rank submissions | Contract Art
|
| 16 |
+
6(1)(b)
|
| 17 |
+
Site security and abuse prevention | Legitimate
|
| 18 |
+
interests 6(1)(f)
|
| 19 |
+
Academic, non-commercial research on models | Legitimate
|
| 20 |
+
interests 6(1)(f)
|
| 21 |
+
Contacting participants about results/collab | Legitimate
|
| 22 |
+
interests 6(1)(f)
|
| 23 |
+
|
| 24 |
+
4 Public Disclosure
|
| 25 |
+
Your display name, score and rank appear on a public leaderboard.
|
| 26 |
+
You may use a pseudonym.
|
| 27 |
+
5 Data Sharing
|
| 28 |
+
Processors: Hugging Face Inc., GitHub Inc., <cloud host> - under
|
| 29 |
+
written contracts.
|
| 30 |
+
Independent controllers: GitHub and Hugging Face regarding your
|
| 31 |
+
platform accounts.
|
| 32 |
+
6 International Transfers
|
| 33 |
+
Where data moves outside the EEA/UK, we rely on EU Standard
|
| 34 |
+
Contractual Clauses or adequacy decisions.
|
| 35 |
+
7 Retention
|
| 36 |
+
- Leaderboard entries: indefinitely.
|
| 37 |
+
- Raw submission files and logs: up to 5 years, then deleted or
|
| 38 |
+
anonymised.
|
| 39 |
+
- Security logs: 12 months.
|
| 40 |
+
8 Your Rights
|
| 41 |
+
Access, correction, erasure, restriction, portability, and
|
| 42 |
+
objection. Contact us at the address above.
|
| 43 |
+
You may lodge a complaint with your supervisory authority.
|
| 44 |
+
9 Security
|
| 45 |
+
Submissions run in network-restricted containers. Access is limited
|
| 46 |
+
to authorised staff using multi-factor authentication.
|
| 47 |
+
10 Cookies
|
| 48 |
+
If you use only GitHub and Hugging Face, their cookies apply under
|
| 49 |
+
their policies. If you later self-host a site for the leaderboard,
|
| 50 |
+
publish your own cookie notice.
|
| 51 |
+
11 Children
|
| 52 |
+
The Competition is not directed to children under 16. Do not submit
|
| 53 |
+
personal data if you are under 16.
|
| 54 |
+
12 Changes
|
| 55 |
+
We will post updates here and notify registered participants by
|
| 56 |
+
email when material.
|
src/display/css_html_js.py
CHANGED
|
@@ -118,6 +118,43 @@ custom_css = """
|
|
| 118 |
max-width: 800px !important; width: 100% !important; margin-left: auto !important; margin-right: auto !important;
|
| 119 |
}
|
| 120 |
#hf-login-btn:hover, #hf-login-btn button:hover, button[data-testid="login-button"]:hover, [data-testid="login-button"] button:hover, div[data-testid="login-button"] > button:hover { background: #f9fafb !important; }
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
"""
|
| 122 |
|
| 123 |
get_window_url_params = """
|
|
|
|
| 118 |
max-width: 800px !important; width: 100% !important; margin-left: auto !important; margin-right: auto !important;
|
| 119 |
}
|
| 120 |
#hf-login-btn:hover, #hf-login-btn button:hover, button[data-testid="login-button"]:hover, [data-testid="login-button"] button:hover, div[data-testid="login-button"] > button:hover { background: #f9fafb !important; }
|
| 121 |
+
|
| 122 |
+
/* Checkbox styling for submission requirements */
|
| 123 |
+
.markdown-text input[type="checkbox"] {
|
| 124 |
+
margin-right: 8px !important;
|
| 125 |
+
width: 16px !important;
|
| 126 |
+
height: 16px !important;
|
| 127 |
+
accent-color: #2563eb !important;
|
| 128 |
+
cursor: pointer !important;
|
| 129 |
+
}
|
| 130 |
+
|
| 131 |
+
.markdown-text label[data-testid="checkbox"] {
|
| 132 |
+
color: var(--f1-text) !important;
|
| 133 |
+
font-size: 14px !important;
|
| 134 |
+
line-height: 1.5 !important;
|
| 135 |
+
cursor: pointer !important;
|
| 136 |
+
display: flex !important;
|
| 137 |
+
align-items: flex-start !important;
|
| 138 |
+
margin-bottom: 8px !important;
|
| 139 |
+
}
|
| 140 |
+
|
| 141 |
+
/* Submit button styling when disabled */
|
| 142 |
+
button[data-testid="button"]:disabled {
|
| 143 |
+
opacity: 0.5 !important;
|
| 144 |
+
cursor: not-allowed !important;
|
| 145 |
+
background: #f3f4f6 !important;
|
| 146 |
+
color: #9ca3af !important;
|
| 147 |
+
border-color: #d1d5db !important;
|
| 148 |
+
}
|
| 149 |
+
|
| 150 |
+
/* Required Agreements section
|
| 151 |
+
.markdown-text h3 {
|
| 152 |
+
color: var(--f1-text) !important;
|
| 153 |
+
font-weight: 600 !important;
|
| 154 |
+
margin: 20px 0 12px 0 !important;
|
| 155 |
+
font-size: 18px !important;
|
| 156 |
+
}
|
| 157 |
+
*/
|
| 158 |
"""
|
| 159 |
|
| 160 |
get_window_url_params = """
|
terms/submission-agreement.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FormulaOne AI Coding Challenge - Submission Agreement v1.2
|
| 2 |
+
Last updated: 6 Aug 2025
|
| 3 |
+
1 Definitions
|
| 4 |
+
"Submission" means the code file you upload for a listed problem.
|
| 5 |
+
"Organiser" means the FormulaOne Team, c/o <legal entity and address>.
|
| 6 |
+
|
| 7 |
+
"Competition Site" means the leaderboard hosted at <HF URL>.
|
| 8 |
+
2 Licence to Organiser
|
| 9 |
+
You retain all IP in your Submission. You grant the Organiser and its
|
| 10 |
+
academic partners a worldwide, royalty-free, non-exclusive licence to:
|
| 11 |
+
a) copy, run, test and modify the Submission solely to evaluate it
|
| 12 |
+
against public and private test cases;
|
| 13 |
+
b) store the Submission on secure servers;
|
| 14 |
+
c) manually review the Submission for non-commercial, scientific
|
| 15 |
+
research;
|
| 16 |
+
d) reproduce small code excerpts (<= 25 lines) in research papers or
|
| 17 |
+
blogs;
|
| 18 |
+
e) contact you via the email linked to your platform account to ask
|
| 19 |
+
clarification questions, explore collaboration, or publicise notable
|
| 20 |
+
results.
|
| 21 |
+
3 Security, Integrity and Acceptable Use
|
| 22 |
+
- You confirm the Submission contains no deliberately malicious code,
|
| 23 |
+
back-doors, attempts to exfiltrate data, or calls to external network
|
| 24 |
+
resources beyond what the submission guidelines permit.
|
| 25 |
+
- You will not attempt to discover, reconstruct, scrape, or share
|
| 26 |
+
private test cases, nor to probe the sandbox environment.
|
| 27 |
+
- The Organiser may refuse, delete, re-run or disqualify any
|
| 28 |
+
Submission at its sole discretion for suspected abuse, tampering or
|
| 29 |
+
rule violations.
|
| 30 |
+
4 Competition Rules
|
| 31 |
+
- One account per team.
|
| 32 |
+
- You must own or have rights to your Submission.
|
| 33 |
+
- We may re-execute Submissions to confirm scores; ties may be broken
|
| 34 |
+
by earliest valid submission or additional hidden tests.
|
| 35 |
+
- We may correct or withdraw scores if errors or rule breaches are
|
| 36 |
+
discovered later.
|
| 37 |
+
5 Leaderboard and Publicity
|
| 38 |
+
Your chosen display name, organisation (if provided), total score and
|
| 39 |
+
ranking may be shown publicly and archived indefinitely. You may use a
|
| 40 |
+
pseudonym.
|
| 41 |
+
6 Ownership of Benchmark Assets
|
| 42 |
+
All evaluation code, problem statements and test data remain (c) 2025
|
| 43 |
+
FormulaOne Team and are licensed under Apache 2.0 (code) and CC BY 4.0
|
| 44 |
+
(content) as described in the public repository.
|
| 45 |
+
7 Export Control and Sanctions Compliance
|
| 46 |
+
You represent that your participation is not prohibited by applicable
|
| 47 |
+
export-control or sanctions laws and that you are not located in, under
|
| 48 |
+
the control of, or a national or resident of any country or person
|
| 49 |
+
embargoed by relevant authorities.
|
| 50 |
+
|
| 51 |
+
8 No Warranty
|
| 52 |
+
The benchmark and infrastructure are provided "as is." To the maximum
|
| 53 |
+
extent permitted by law, the Organiser disclaims all warranties,
|
| 54 |
+
express or implied.
|
| 55 |
+
9 Limitation of Liability
|
| 56 |
+
The Organiser's total liability arising out of or in connection with
|
| 57 |
+
the Competition will not exceed USD 100.
|
| 58 |
+
10 Changes to Rules
|
| 59 |
+
We may update these terms and technical rules from time to time.
|
| 60 |
+
Material changes will be posted on the Competition Site and apply to
|
| 61 |
+
submissions made after the effective date.
|
| 62 |
+
11 Governing Law and Venue
|
| 63 |
+
This Agreement is governed by the laws of England and Wales. The courts
|
| 64 |
+
of London, UK, have exclusive jurisdiction.
|
| 65 |
+
12 Contact
|
| 66 |
+
Questions about these terms: [email protected]
|