{ "fetched_at": "2026-10-19T17:55:54Z", "source_url": "https://www.kaggle.com/competitions/distracted-driving-risk-detection-challenge/data", "pages": [ { "name": "data-description", "content": "This competition uses real-world driving data collected from urban driving sessions. The dataset contains time series observations from vehicle sensors, driver health monitors, weather conditions, and historical traffic data.\n\n### What am I predicting?\n\nYou are predicting the **risk_level** of traffic accidents for each observation in the test set. The risk level is a categorical variable with 4 classes:\n\n- **1** = Low risk (normal, safe driving conditions)\n- **2** = Medium risk (elevated risk requiring attention)\n- **3** = High risk (dangerous conditions requiring intervention)\n- **4** = Very high risk (critical situations with imminent danger)\n\n### What files do I need?\n\n**Required for modeling:**\n- **`kaggle_train.csv`** - Training data with risk_level labels\n- **`kaggle_test.csv`** - Test data (predict risk_level for these rows)\n- **`kaggle_sample_submission.csv`** - Example submission format\n\n**Optional for advanced techniques:**\n- **`kaggle_full_unlabeled_data.csv`** - Additional unlabeled data for semi-supervised learning\n\n### What should I expect the data format to be?\n\nAll files are in CSV (comma-separated values) format with headers. Each row represents a single time-stamped observation from a driving session.\n\n---\n\n## Files\n\n### kaggle_train.csv\nThe training set containing **1,980 labeled observations**.\n\n- **Balanced classes**: 495 observations per risk level (1, 2, 3, 4)\n- **14 features** + 1 target variable (`risk_level`)\n- Use this data to train your models\n\n### kaggle_test.csv\nThe test set containing **23,152 observations**.\n\n- Same 14 features as training data\n- **No `risk_level` column** (this is what you're predicting)\n- No `id` column - use row index (0 to 23,151) as the id in your submission\n\n### kaggle_sample_submission.csv\nA sample submission file in the correct format.\n\n- **2 columns**: `id`, `risk_level`\n- **23,153 rows**: Header + 23,152 predictions\n- Shows the exact format your submission must match\n\n### kaggle_full_unlabeled_data.csv\nAdditional unlabeled data containing **82,223 observations**.\n\n- **Optional** - Not required for basic approaches\n- Contains raw data with additional features beyond the competition dataset\n- No `risk_level` labels provided\n- Useful for:\n - Semi-supervised learning\n - Unsupervised pre-training\n - Understanding feature distributions\n - Data augmentation techniques\n\n---\n\n## Columns\n\n### Target Variable\n\n- **`risk_level`** - Traffic accident risk classification (1=Low, 2=Medium, 3=High, 4=Very High). **This is what you're predicting.** Only present in training data.\n\n### Vehicle Telemetry Features\n*Source: OBD-II (On-Board Diagnostics) scanner connected to vehicle*\n\n- **`speed`** - Current vehicle speed in kilometers per hour (km/h). Range: 0-150+\n- **`rpm`** - Engine revolutions per minute. Indicates how fast the engine is spinning. Range: 0-7000+\n- **`acceleration`** - Vehicle acceleration in meters per second squared (m/s²). Positive values = accelerating, negative values = decelerating (braking). Range: -10 to +10\n- **`throttle_position`** - Throttle pedal position as a percentage (0-100%). Higher values indicate more aggressive acceleration.\n- **`engine_temperature`** - Engine coolant temperature in degrees Celsius (°C). Normal range: 80-120°C\n- **`engine_load_value`** - Current engine load as a percentage (0-100%). Indicates how hard the engine is working.\n\n### Driver Health Features\n*Source: Wearable health monitoring device*\n\n- **`heart_rate`** - Driver's heart rate in beats per minute (bpm). Can indicate driver stress, fatigue, or alertness. Range: 40-200\n\n### Temporal Features\n\n- **`observation_hour`** - Hour of the day when observation was recorded, in 24-hour format (0-23). Useful for identifying rush hour, night driving, etc.\n\n### Weather & Environmental Features\n*Source: Weather API based on GPS location*\n\n- **`current_weather`** - Encoded weather condition. Higher numeric values generally indicate worse weather conditions.\n- **`visibility`** - Visibility distance in kilometers (km). Lower values indicate fog, rain, or other visibility-reducing conditions. Range: 0-20+\n- **`precipitation`** - Precipitation amount in millimeters (mm). Includes rain, snow, sleet. Range: 0-50+\n\n### Traffic & Road Infrastructure Features\n*Source: Historical traffic accident database and road characteristics*\n\n- **`accidents_onsite`** - Number of historical fatal accidents (deaths) that have occurred at this specific location. Higher values indicate historically dangerous locations. Range: 0-30+\n- **`design_speed`** - The posted or design speed limit for this road segment in km/h. Used to assess speeding behavior. Range: 30-90\n- **`accidents_time`** - Number of historical fatal accidents (deaths) that have occurred during similar time periods at various locations. Captures temporal risk patterns. Range: 0-10+\n\n### Submission File Columns\n\n- **`id`** - Integer identifier (0 to 23,151) matching the row index in `kaggle_test.csv`\n- **`risk_level`** - Your predicted risk level (must be 1, 2, 3, or 4)\n\n---\n\n## Important Notes\n\n### Time Series Nature\nThis is **time series data** from sequential driving sessions. While you can treat each row independently, temporal patterns may be informative:\n- Consecutive rows may come from the same driving session\n- Consider rolling statistics, rate of change, and sequence patterns\n- LSTM, GRU, or attention-based models may capture temporal dependencies\n\n### Data Collection Context\nData was collected from:\n- 5 real drivers + 1 synthetic driver\n- 3 vehicle types (CUV, Pickup, Sedan)\n- 2 urban routes through high-traffic accident zones\n- Location: Quito, Ecuador\n- Total: ~18 hours of driving data\n\n### Missing Values\nCheck for missing values in your specific dataset. Handle them appropriately for your chosen model.\n\n### Scale Differences\nFeatures have vastly different scales (e.g., rpm goes to 7000+, visibility might be 0-20). Consider:\n- Normalization/standardization\n- Feature scaling appropriate for your model choice\n\n### Feature Engineering Ideas\n\nConsider creating derived features:\n- **Speed violations**: `speed / design_speed` (>1.0 indicates speeding)\n- **Aggressive driving**: High acceleration + high throttle\n- **Driver stress**: Elevated heart rate relative to baseline\n- **Environmental risk**: Combined weather + visibility + precipitation score\n- **Location risk**: `accidents_onsite + accidents_time`\n- **Time-based risk**: Rush hour indicators, night driving flags\n\n### Class Imbalance\n- **Training set**: Perfectly balanced (495 per class)\n- **Test set**: Distribution unknown (may not be balanced)\n\nConsider this when:\n- Choosing evaluation metrics for cross-validation\n- Deciding whether to use class weights\n- Interpreting model confidence scores\n\n---\n\n## Acronyms & Terms\n\n- **OBD-II** - On-Board Diagnostics (version 2), the vehicle's diagnostic system\n- **bpm** - Beats per minute (heart rate)\n- **rpm** - Revolutions per minute (engine speed)\n- **km/h** - Kilometers per hour (speed)\n- **m/s²** - Meters per second squared (acceleration)\n- **mm** - Millimeters (precipitation)\n- **°C** - Degrees Celsius (temperature)\n- **CUV** - Crossover Utility Vehicle (vehicle type)\n- **GPS** - Global Positioning System\n\n---\n\n## Getting Started\n\n1. **Load the data**: Read `kaggle_train.csv` and `kaggle_test.csv`\n2. **Explore**: Check distributions, correlations, missing values\n3. **Engineer features**: Create domain-specific features (speed ratios, driver stress indicators, etc.)\n4. **Train models**: Start with a simple baseline (e.g., Random Forest, XGBoost)\n5. **Validate**: Use cross-validation to assess performance\n6. **Make predictions**: Generate predictions for `kaggle_test.csv`\n7. **Submit**: Format as shown in `kaggle_sample_submission.csv`\n\nGood luck! 🚗📊\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "### Background\n\nTraffic safety is a critical global challenge. According to the World Health Organization, road traffic crashes result in approximately 1.35 million deaths annually. Many of these accidents could be prevented with better real-time risk detection and driver assistance systems.\n\nThis competition uses data from the **POLIDriving** dataset, a public-access driving dataset designed for road traffic safety analysis. The data was collected from real-world driving sessions through high-traffic accident zones in urban environments.\n\n### Data Collection\n\nThe dataset was collected from:\n\n- **5 real drivers** with varying driving styles and experience levels\n- **1 synthetic driver** for controlled scenario testing\n- **3 vehicle types**: CUV (Crossover Utility Vehicle), Pickup, and Sedan\n- **2 urban routes** through areas with documented high accident rates\n- **Urban environment**: Quito, Ecuador\n\nData was captured using:\n- **OBD-II scanner** for vehicle telemetry\n- **GPS receiver** for location and routing\n- **Wearable health monitor** for driver physiological data\n- **Weather API** for environmental conditions\n- **Traffic accident database** for historical risk data\n\n### Dataset Features\n\n#### Vehicle Telemetry (6 features)\nReal-time data from the vehicle's onboard diagnostics system:\n- `speed` - Current vehicle speed (km/h)\n- `rpm` - Engine revolutions per minute\n- `acceleration` - Acceleration or deceleration (m/s²)\n- `throttle_position` - Throttle position (%)\n- `engine_temperature` - Engine coolant temperature (°C)\n- `engine_load_value` - Engine load (%)\n\n#### Driver Health (1 feature)\nPhysiological monitoring of the driver:\n- `heart_rate` - Driver's heart rate (bpm)\n\n#### Environmental Data (4 features)\nWeather and temporal conditions:\n- `current_weather` - Weather condition code\n- `visibility` - Visibility distance (km)\n- `precipitation` - Precipitation amount (mm)\n- `observation_hour` - Hour of day (0-23)\n\n#### Road & Traffic (3 features)\nHistorical accident data and road characteristics:\n- `accidents_onsite` - Historical fatal accidents at location\n- `design_speed` - Road design speed (km/h)\n- `accidents_time` - Fatal accidents during similar time periods\n\n#### Metadata (1 feature)\n- `label_source` - Whether label is `expert_verified` or `semi_supervised`\n\n### Dataset Files\n\n- **`kaggle_train.csv`** - 1,980 labeled observations (495 per class, balanced)\n- **`kaggle_test.csv`** - 23,152 test observations (labels withheld)\n- **`kaggle_sample_submission.csv`** - Example submission format\n- **`kaggle_full_unlabeled_data.csv`** - 82,223 additional unlabeled observations (optional)\n\n### Target Variable\n\nThe `risk_level` indicates the accident risk classification:\n- **1** = Low risk (normal, safe driving)\n- **2** = Medium risk (elevated risk, attention needed)\n- **3** = High risk (dangerous, intervention recommended)\n- **4** = Very high risk (critical, imminent danger)\n\n### Time Series Nature\n\nThis is **time series data** from sequential driving sessions. While each row can be treated independently, the temporal relationships contain valuable information. Consider:\n\n- Rolling statistics over time windows\n- Rate of change in speed, acceleration, heart rate\n- Sequence patterns and trends\n- LSTM, GRU, or Transformer architectures\n\n### Modeling Approaches to Consider\n\n**Feature Engineering**\n- Speed violations: `speed / design_speed`\n- Driver stress indicators: heart rate deviations\n- Aggressive driving: rapid acceleration + high throttle\n- Environmental risk scores: weather × visibility × precipitation\n- Time-of-day risk patterns\n\n**Model Architectures**\n- Gradient boosting (XGBoost, LightGBM, CatBoost)\n- Neural networks with temporal features\n- Sequence models (LSTM, GRU) if preserving time series structure\n- Ensemble methods combining multiple approaches\n\n**Semi-Supervised Learning**\nUse the 82K unlabeled samples for:\n- Pre-training autoencoders\n- Pseudo-labeling\n- Consistency regularization\n- Self-training approaches\n\n### External Data & Pre-trained Models\n\nYou may use external data and pre-trained models, subject to:\n- Free and equal access for all participants\n- Cost not exceeding $100 USD\n- Disclosure in your final documentation\n- No test set leakage\n\n### Citation\n\nThis dataset is derived from research published in Applied Sciences. If you use this data in academic work, please cite:\n\n```\nMarcillo, P., Arciniegas-Ayala, C., Valdivieso Caraguay, Á.L.,\nSanchez-Gordon, S., & Hernández-Álvarez, M. (2024).\nPOLIDriving: A Public-Access Driving Dataset for Road Traffic Safety Analysis.\nApplied Sciences, 14(14), 6300. MDPI.\n```\n\n### Get Started\n\n1. Download the training and test data\n2. Explore feature distributions and correlations\n3. Build baseline models\n4. Engineer features based on domain knowledge\n5. Experiment with time series approaches\n6. Make submissions (up to 5 per day)\n7. Select your best 2 submissions for final scoring\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "Submissions are evaluated using **multi-class classification accuracy**.\n\n### Metric Definition\n\nAccuracy is calculated as:\n\n```\nAccuracy = (Number of Correct Predictions) / (Total Number of Predictions)\n```\n\nA prediction is correct only when your predicted `risk_level` **exactly matches** the true risk level. There is no partial credit for \"close\" predictions.\n\n### Leaderboard Splits\n\n- **Public Leaderboard**: Calculated on approximately **30%** of the test data\n- **Private Leaderboard**: Calculated on the remaining **70%** of test data (determines final rankings)\n\nYour final rank is determined by your performance on the **private leaderboard**. The public leaderboard is provided for feedback during the competition but is not used for final scoring.\n\n### Submission Format\n\nFor each `id` in the test set, you must predict the `risk_level` (1, 2, 3, or 4). Your submission file should contain a header and have the following format:\n\n```csv\nid,risk_level\n0,1\n1,2\n2,1\n3,4\n4,3\n5,2\n...\n```\n\n#### Format Requirements\n\n- **Header row**: Must include `id,risk_level`\n- **23,152 rows**: One prediction for each test sample (plus header)\n- **Valid values**: `risk_level` must be 1, 2, 3, or 4 (integers only)\n- **Complete predictions**: All test IDs must be present\n- **File format**: CSV (comma-separated values)\n\n### Submission Limits\n\n- **5 submissions per day** (24-hour rolling window)\n- **Select up to 2 final submissions** for judging before the deadline\n- If you don't select submissions, your highest-scoring public leaderboard submissions will be used\n\n### Important Notes\n\n**Select Your Final Submissions**: Make sure to select which 2 submissions you want scored on the private leaderboard. This is critical for your final ranking.\n\n**Public vs Private**: The public leaderboard is only 30% of the data. Models that overfit to the public leaderboard may not perform well on the private leaderboard. Use cross-validation on the training data to assess true model performance.\n\n**Class Distribution**: The training set has balanced classes (495 per class), but the test set distribution may differ. Consider this when developing your models.\n\n### Example Submission Code\n\n```python\nimport pandas as pd\n\n# Load your predictions\npredictions = your_model.predict(test_data)\n\n# Create submission dataframe\nsubmission = pd.DataFrame({\n 'id': range(len(predictions)),\n 'risk_level': predictions\n})\n\n# Save to CSV\nsubmission.to_csv('submission.csv', index=False)\n```\n\n### Validation Strategy\n\nSince the public leaderboard only uses 30% of test data, we recommend:\n\n1. **Cross-validation**: Use k-fold cross-validation on the training data\n2. **Stratified splits**: Maintain class balance in your validation folds\n3. **Multiple metrics**: Track accuracy, F1-score, and confusion matrix\n4. **Avoid overfitting**: Don't chase small improvements on public leaderboard\n\n### Tiebreakers\n\nIf multiple submissions have identical accuracy (to 6 decimal places):\n- The **earlier submission timestamp** will rank higher\n- This encourages participants to submit strong solutions early\n\nGood luck! \n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "

Competition-Specific Rules

\n\n

ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES

\n\n

The Competition named below is a skills-based competition to promote and further the field of data science and machine learning. You must register via the Competition Website to enter. To enter the Competition, you must agree to these Official Competition Rules (the \"Rules\"). Please read these Rules carefully before entry to ensure you understand and agree. You further agree that submission of any Entry in the Competition constitutes agreement to these Rules. You may not submit to the Competition and are not eligible to receive any prizes unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition.

\n\n---\n\n

1. COMPETITION-SPECIFIC TERMS

\n\n

1.1 COMPETITION TITLE

\nDistracted Driving Risk Detection Challenge\n\n

1.2 COMPETITION SPONSOR

\nVivan Doshi (Independent Researcher)\n\n

1.3 COMPETITION SPONSOR ADDRESS

\nSan Jose, California, United States\n\n

1.4 COMPETITION WEBSITE

\nhttps://www.kaggle.com/competitions/distracted-driving-risk-detection\n\n

1.5 COMPETITION DURATION

\n\n\n

1.6 PRIZE STRUCTURE

\n

Total Prize Pool: $100 USD

\n\n\n\n

All winning teams will be acknowledged in any publications or presentations resulting from this competition and will have the opportunity to co-author writeups about their solutions.

\n\n

1.7 WINNER LICENSE TYPE

\nOpen Source License\n\n---\n\n

2. ELIGIBILITY

\n\n

2.1 Who May Enter

\n

This Competition is open to individuals and teams worldwide who are at least 18 years of age (or the age of majority in their jurisdiction of residence) at the time of entry.

\n\n

2.2 Restrictions

\n

The following individuals are not eligible to win prizes:

\n\n\n

2.3 Compliance with Local Laws

\n

You are responsible for ensuring your participation complies with all applicable local, state, national, and international laws and regulations.

\n\n---\n\n

3. TEAM FORMATION AND RULES

\n\n

3.1 Team Size

\n\n\n

3.2 Team Formation and Mergers

\n\n\n

3.3 Team Leadership

\n\n\n

3.4 Multiple Account Prohibition

\n

You may not create or use multiple Kaggle accounts to participate in this Competition. Violation of this rule will result in immediate disqualification of all associated accounts.

\n\n---\n\n

4. COMPETITION DATA

\n\n

4.1 Data Access

\n

Competition Data will be made available for download through the Competition Website. You must agree to these Rules before accessing the data.

\n\n

4.2 Data Usage Rights

\n

Competition Use and Non-Commercial Research:

\n\n

You may access and use the Competition Data for:

\n\n\n

Commercial use of the Competition Data is strictly prohibited.

\n\n

4.3 Additional Data License Terms

\n

The Competition Data is derived from the POLIDriving dataset. If you use this data in academic work, please cite:

\n\n
Marcillo, P., Arciniegas-Ayala, C., Valdivieso Caraguay, Á.L., Sanchez-Gordon, S., & Hernández-Álvarez, M. (2024).\nPOLIDriving: A Public-Access Driving Dataset for Road Traffic Safety Analysis.\nApplied Sciences, 14(14), 6300. MDPI.\n
\n\n

4.4 Data Security and Confidentiality

\n

You agree to:

\n\n\n

4.5 External Data

\n

You may use publicly available external data to supplement the Competition Data, provided that:

\n\n\n

4.6 Pre-trained Models

\n

You may use publicly available pre-trained models, subject to:

\n\n\n---\n\n

5. SUBMISSIONS

\n\n

5.1 Submission Limits

\n\n\n

5.2 Submission Requirements

\n

All submissions must:

\n\n\n

5.3 Submission Scoring

\n\n\n

5.4 Computational Limitations

\n

Your solution should be capable of generating predictions within reasonable computational resources. Winners must provide code that can be executed on standard hardware (single GPU or CPU-only systems) within 24 hours for training and 1 hour for inference.

\n\n---\n\n

6. EVALUATION AND WINNER SELECTION

\n\n

6.1 Evaluation Metric

\n

Submissions will be evaluated using: Multi-class Accuracy

\n\n

Accuracy = (Number of Correct Predictions) / (Total Number of Predictions)

\n\n

where predictions must exactly match the true risk level (1, 2, 3, or 4).

\n\n

6.2 Winner Determination

\n

Winners will be determined based on:

\n
    \n
  1. Primary: Performance on the private test set according to multi-class accuracy
    2. \n
  2. Tiebreaker: If scores are tied to 6 decimal places, the earlier submission timestamp prevails
    3. \n
\n\n

6.3 Validation and Code Review

\n

Potential winners will be subject to:

\n\n\n

6.4 Disqualification

\n

The Competition Sponsor reserves the right to disqualify any participant or team who:

\n\n\n---\n\n

7. WINNER OBLIGATIONS

\n\n

7.1 Code and Documentation Delivery

\n

Within 14 days of winner notification, winners must provide:

\n\n

a) Complete Source Code:

\n\n\n

b) Comprehensive Documentation:

\n\n\n

c) Environment Specifications:

\n\n\n

7.2 Reproducibility Requirements

\n

Your submission must be reproducible by the Competition Sponsor following your documentation. Failure to provide reproducible results may result in disqualification and forfeiture of prizes.

\n\n

7.3 Automated ML Tools

\n

If you used automated machine learning platforms or AutoML tools:

\n\n\n

7.4 License Grant

\n

Open Source License:

\n\n

Winners grant an Open Source Initiative-approved license (MIT License recommended) for their winning submission that permits use, modification, and distribution of the code and models for both commercial and non-commercial purposes.

\n\n

You may exclude:

\n\n\n

7.5 Legal Documentation

\n

Winners must complete and return within 14 days:

\n\n\n

7.6 Publicity Release

\n

Winners agree to the use of their name, Kaggle username, submission details, and solution summary for promotional purposes by the Competition Sponsor and Kaggle without additional compensation, except where prohibited by law. This includes publication in academic papers, conference presentations, and blog posts.

\n\n---\n\n

8. INTELLECTUAL PROPERTY

\n\n

8.1 Your IP

\n

Subject to the license grants in Section 7.4, you retain ownership of your original contributions to your submission.

\n\n

8.2 Competition Sponsor IP

\n

The Competition Data, problem description, evaluation metrics, and all related materials remain the property of the original dataset creators and the Competition Sponsor.

\n\n

8.3 Third-Party Rights

\n

You represent and warrant that your submission:

\n\n\n---\n\n

9. PRIVACY AND DATA PROTECTION

\n\n

9.1 Personal Information

\n

By participating, you consent to the collection, processing, and storage of your personal information as described in Kaggle's Privacy Policy and as necessary to administer the Competition.

\n\n

9.2 Data Processing

\n

The Competition Data contains driving behavior and health data that has been anonymized. You agree to process it in accordance with applicable data protection laws and use it only for the purposes outlined in these Rules.

\n\n---\n\n

10. WARRANTIES, INDEMNIFICATION, AND RELEASE

\n\n

10.1 Warranties

\n

You represent and warrant that:

\n\n\n

10.2 Indemnification

\n

You agree to indemnify, defend, and hold harmless the Competition Sponsor, Kaggle, and their respective officers, directors, employees, agents, and affiliates from any claims, damages, liabilities, costs, and expenses (including reasonable attorneys' fees) arising from:

\n\n\n

10.3 Release

\n

You release the Competition Sponsor, Kaggle, and their respective officers, directors, employees, and agents from any liability for claims, injuries, damages, or losses arising from your participation in the Competition or acceptance of any prize.

\n\n

10.4 Limitation of Liability

\n

TO THE MAXIMUM EXTENT PERMITTED BY LAW, THE COMPETITION SPONSOR AND KAGGLE SHALL NOT BE LIABLE FOR ANY INDIRECT, INCIDENTAL, CONSEQUENTIAL, SPECIAL, OR PUNITIVE DAMAGES ARISING OUT OF OR RELATING TO THIS COMPETITION, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.

\n\n---\n\n

11. GENERAL CONDITIONS

\n\n

11.1 No Purchase Necessary

\n

No purchase or payment is necessary to enter or win this Competition.

\n\n

11.2 Modification and Termination

\n

The Competition Sponsor reserves the right to:

\n\n\n

11.3 Disputes

\n

All determinations by the Competition Sponsor regarding the Competition, including but not limited to winner selection and rule interpretation, are final and binding.

\n\n

11.4 Taxes

\n

Winners are solely responsible for all federal, state, local, and foreign taxes on prizes, if applicable.

\n\n

11.5 Prize Forfeiture

\n

Failure to comply with these Rules or winner obligations may result in disqualification and forfeiture of any prizes or recognition.

\n\n

11.6 No Assignment

\n

You may not assign or transfer your rights or obligations under these Rules without the prior written consent of the Competition Sponsor.

\n\n

11.7 Severability

\n

If any provision of these Rules is found invalid or unenforceable, the remaining provisions will remain in full force and effect.

\n\n

11.8 Entire Agreement

\n

These Rules constitute the entire agreement between you and the Competition Sponsor regarding this Competition and supersede all prior agreements and understandings.

\n\n---\n\n

12. GOVERNING LAW AND JURISDICTION

\n\n

12.1 Governing Law

\n

These Rules shall be governed by and construed in accordance with the laws of the State of California, United States, without regard to its conflict of law principles.

\n\n

12.2 Jurisdiction

\n

Any disputes arising from or relating to these Rules or the Competition shall be resolved exclusively in the state or federal courts located in Santa Clara County, California, and you consent to the personal jurisdiction of such courts.

\n\n---\n\n

13. ETHICAL GUIDELINES

\n\n

13.1 Fair Play

\n

Participants must compete fairly and ethically. Prohibited activities include:

\n\n\n

13.2 Responsible AI

\n

This competition focuses on traffic safety, a domain with real-world impact. Participants should strive to develop solutions that:

\n\n\n---\n\n

14. QUESTIONS AND SUPPORT

\n\n

For questions about these Rules or the Competition, please:

\n\n\n---\n\n

15. ACCEPTANCE OF RULES

\n\n

BY ENTERING THIS COMPETITION, YOU ACKNOWLEDGE THAT YOU HAVE READ, UNDERSTOOD, AND AGREE TO BE BOUND BY THESE RULES.

\n\n---\n\n

Competition Sponsor: Vivan Doshi, San Jose, California
\nDataset Source: POLIDriving (Marcillo et al., 2024)
\nLast Updated: [Date of competition launch]

\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "abstract", "content": "## Overview\n\n**Can you predict traffic accident risk from driving behavior?**\n\nThis competition challenges you to build models that classify driving risk levels using real-world time series data from urban driving sessions. Using sensor data from vehicles, drivers, and environmental conditions, you'll predict whether a driving situation poses low, medium, high, or very high accident risk.\n\n### The Challenge\n\nModern vehicles and wearable devices generate rich streams of data about driving behavior, vehicle performance, and driver health. This competition explores whether machine learning can identify dangerous driving situations in real-time by analyzing patterns in:\n\n- **Vehicle telemetry**: Speed, acceleration, engine performance\n- **Driver health**: Heart rate monitoring\n- **Environmental conditions**: Weather, visibility, precipitation\n- **Road characteristics**: Historical accident data, design speed\n- **Temporal patterns**: Time of day effects\n\n### Why This Matters\n\nTraffic accidents remain a leading cause of injury and death worldwide. Developing accurate risk detection systems could enable:\n\n- Real-time driver alerts and assistance systems\n- Insurance telematics and risk assessment\n- Fleet safety monitoring\n- Road infrastructure improvements\n- Traffic safety research\n\n### The Data\n\nThe dataset is derived from the **POLIDriving** dataset, collected from real driving sessions in Quito, Ecuador. It includes:\n\n- **1,980 labeled training samples** (balanced across 4 risk levels)\n- **23,152 test samples** for final evaluation\n- **82,223 unlabeled samples** for semi-supervised learning (optional)\n- **15 features** from vehicle sensors, health monitors, weather APIs, and traffic databases\n- **18 hours** of real-world driving data\n\n### Your Goal\n\nBuild a model that accurately classifies each driving observation into one of four risk levels:\n\n1. **Low Risk** - Normal, safe driving conditions\n2. **Medium Risk** - Elevated risk requiring attention\n3. **High Risk** - Dangerous conditions requiring intervention\n4. **Very High Risk** - Critical situations with imminent danger\n\nGood luck, and drive safely! 🚗\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "\nThis research competition offers both monetary prizes and academic recognition for top performers.\n\n### Total Prize Pool: $100 USD\n\n#### 🥇 First Place - $50\n- Cash prize\n- Featured solution presentation\n- Co-authorship opportunity on research writeup\n- Citation rights in future publications\n- Recognition on competition website\n\n#### 🥈 Second Place - $30\n- Cash prize\n- Co-authorship opportunity on research writeup\n- Citation rights in future publications\n- Recognition on competition website\n\n#### 🥉 Third Place - $20\n- Cash prize\n- Citation rights in future publications\n- Recognition on competition website\n\n### Winner Requirements\n\nAll prize winners must:\n\n1. **Share their solution**: Provide well-documented source code and methodology\n2. **Reproducible results**: Include instructions to reproduce your predictions\n3. **Documentation**: Write a clear explanation of your approach\n4. **Open source**: Release winning solution under an OSI-approved license (MIT recommended)\n5. **Compliance**: Follow all competition rules and eligibility requirements\n\nSee the **Rules** page for complete details on winner obligations.\n\n### Academic Recognition\n\nBeyond monetary prizes, winners will:\n- Be acknowledged in any publications resulting from this competition\n- Have the opportunity to co-author research papers about the competition\n- Have their solutions featured in the competition writeup\n\n### Timeline\n\n- **Winners Announcement**: 14 days after competition close\n- **Code Submission Deadline**: 14 days after winner notification\n- **Prize Distribution**: After code verification and compliance review\n\n### Eligibility\n\nThis competition is open worldwide to individuals and teams (max 5 members). See the **Rules** page for complete eligibility requirements.\n\n**Note**: Winners are responsible for any applicable taxes on prizes.\n\n### Recognition Over Rewards\n\nWhile the monetary prizes are modest, this competition offers valuable:\n- Academic recognition and publication opportunities\n- Portfolio material showcasing your machine learning skills\n- Contribution to traffic safety research with real-world impact\n- Networking with data science and transportation safety communities\n\nThe primary goal is advancing research in traffic safety through collaborative data science. Top solutions will help inform the development of real-world driver assistance systems that could save lives.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "foundational-rules", "content": "The following Kaggle Competition Foundational Rules (“ Foundational Rules ”) apply to every competition regardless of whether the Sponsor creates competition-specific rules. Any competition-specific rules provided by the Sponsor are in addition to these rules, and in the case of any conflict or inconsistency, these Foundational Rules control and nullify contrary competition-specific rules.\n###GENERAL COMPETITION RULES - BINDING AGREEMENT\n####1. ELIGIBILITY\na. To be eligible to enter the Competition, you must be:\n1. a registered account holder at Kaggle.com; \n2. the older of 18 years old or the age of majority in your jurisdiction of residence (unless otherwise agreed to by Competition Sponsor and appropriate parental/guardian consents have been obtained by Competition Sponsor); \n3. not a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, or North Korea; and\n4. not a person or representative of an entity under U.S. export controls or sanctions (see: [https://www.treasury.gov/resourcecenter/sanctions/Programs/Pages/Programs.aspx][1]).\n\nb. Competitions are open to residents of the United States and worldwide, except that if you are a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, North Korea, or are subject to U.S. export controls or sanctions, you may not enter the Competition. Other local rules and regulations may apply to you, so please check your local laws to ensure that you are eligible to participate in skills-based competitions. The Competition Host reserves the right to forego or award alternative Prizes where needed to comply with local laws. If a winner is located in a country where prizes cannot be awarded, then they are not eligible to receive a prize.\n\nc. If you are entering as a representative of a company, educational institution or other legal entity, or on behalf of your employer, these rules are binding on you, individually, and the entity you represent or where you are an employee. If you are acting within the scope of your employment, or as an agent of another party, you warrant that such party or your employer has full knowledge of your actions and has consented thereto, including your potential receipt of a Prize. You further warrant that your actions do not violate your employer's or entity's policies and procedures. \n\nd. The Competition Sponsor reserves the right to verify eligibility and to adjudicate on any dispute at any time. If you provide any false information relating to the Competition concerning your identity, residency, mailing address, telephone number, email address, ownership of right, or information required for entering the Competition, you may be immediately disqualified from the Competition.\n\n####2. SPONSOR AND HOSTING PLATFORM\n\na. The Competition is sponsored by Competition Sponsor named above. The Competition is hosted on behalf of Competition Sponsor by Kaggle Inc. (\"Kaggle\"). Kaggle is an independent contractor of Competition Sponsor, and is not a party to this or any agreement between you and Competition Sponsor. You understand that Kaggle has no responsibility with respect to selecting the potential Competition winner(s) or awarding any Prizes. Kaggle will perform certain administrative functions relating to hosting the Competition, and you agree to abide by the provisions relating to Kaggle under these Rules. As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at [www.kaggle.com/terms][2] in addition to these Rules.\n\n####3. COMPETITION PERIOD\na. For the purposes of Prizes, the Competition will run from the Start Date and time to the Final Submission Deadline (such duration the “Competition Period”). The Competition Timeline is subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.\n\n####4. COMPETITION ENTRY\na. NO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website prior to the Entry Deadline, and follow the instructions for developing and entering your Submission through the Competition Website. Your Submissions must be made in the manner and format, and in compliance with all other requirements, stated on the Competition Website (the \"Requirements\"). Submissions must be received before any Submission deadlines stated on the Competition Website. Submissions not received by the stated deadlines will not be eligible to receive a Prize.\nb. Submissions may not use or incorporate information from hand labeling or human prediction of the validation dataset or test data records.\nc. If the Competition is a multi-stage competition with temporally separate training and/or test data, one or more valid Submissions may be required during each Competition stage in the manner described on the Competition Website in order for the Submissions to be Prize eligible.\nd. Submissions are void if they are in whole or part illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. Competition Sponsor reserves the right to disqualify any entrant who does not follow these Rules, including making a Submission that does not meet the Requirements. \n\n####5. INDIVIDUALS AND TEAMS\na. Individual Account. You may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website. \nb. Teams. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a Team; however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size stated on the Competition Website.\nc. Team Merger. Teams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules. \nd. Private Sharing. No private sharing outside of Teams. Privately sharing code or data outside of Teams is not permitted. It's okay to share code if made available to all Participants on the forums.\n\n####6. SUBMISSION CODE REQUIREMENTS\na. Private Code Sharing. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition Period, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data or other source or executable code relevant to the Competition (“Competition Code”). This prohibition includes sharing Competition Code between separate Teams, unless a Team merger occurs. Any such sharing of Competition Code is a breach of these Competition Rules and may result in disqualification.\nb. Public Code Sharing. You are permitted to publicly share Competition Code, provided that such public sharing does not violate the intellectual property rights of any third party. If you do choose to share Competition Code or other such code, you are required to share it on Kaggle.com on the discussion forum or notebooks associated specifically with the Competition for the benefit of all competitors. By so sharing, you are deemed to have licensed the shared code under an Open Source Initiative-approved license (see [www.opensource.org][3]) that in no event limits commercial use of such Competition Code or model containing or depending on such Competition Code.\nc. Use of Open Source. Unless otherwise stated in the Specific Competition Rules above, if open source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see [www.opensource.org][4]) that in no event limits commercial use of such code or model containing or depending on such code.\n\n####7. DETERMINING WINNERS\na. Each Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's Public Leaderboard. The potential winner(s) are determined solely by the leaderboard ranking on the Private Leaderboard, subject to compliance with these Rules. The Public Leaderboard will be based on the public test set and the Private Leaderboard will be based on the private test set.\nb. In the event of a tie, the Submission that was entered first to the Competition will be the winner. In the event a potential winner is disqualified for any reason, the Submission that received the next highest score rank will be chosen as the potential winner.\n\n####8. NOTIFICATION OF WINNERS & DISQUALIFICATION\na. The potential winner(s) will be notified by email. \nb. If a potential winner (i) does not respond to the notification attempt within one (1) week from the first notification attempt or (ii) notifies Kaggle within one week after the Final Submission Deadline that the potential winner does not want to be nominated as a winner or does not want to receive a Prize, then, in each case (i) and (ii) such potential winner will not receive any Prize, and an alternate potential winner will be selected from among all eligible entries received based on the Competition’s judging criteria.\nc. In case (i) and (ii) above Kaggle may disqualify the Participant. However, in case (ii) above, if requested by Kaggle, such potential winner may provide code and documentation to verify the Participant’s compliance with these Rules. If the potential winner provides code and documentation to the satisfaction of Kaggle, the Participant will not be disqualified pursuant to this paragraph.\nd. Competition Sponsor reserves the right to disqualify any Participant from the Competition if the Competition Sponsor reasonably believes that the Participant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other Participants, Competition Sponsor or Kaggle.\ne. A disqualified Participant may be removed from the Competition leaderboard, at Kaggle's sole discretion. If a Participant is removed from the Competition Leaderboard, additional winning features associated with the Kaggle competition platform, for example Kaggle points or medals, may also not be awarded.\nf. The final leaderboard list will be publicly displayed at Kaggle.com. Determinations of Competition Sponsor are final and binding.\n\n####9. PRIZES\na. Prize(s) are as described on the Competition Website and are only available for winning during the time period described on the Competition Website. The odds of winning any Prize depends on the number of eligible Submissions received during the Competition Period and the skill of the Participants. \nb. All Prizes are subject to Competition Sponsor's review and verification of the Participant’s eligibility and compliance with these Rules, and the compliance of the winning Submissions with the Submissions Requirements. In the event that the Submission demonstrates non-compliance with these Competition Rules, Competition Sponsor may at its discretion take either of the following actions: (i) disqualify the Submission(s); or (ii) require the potential winner to remediate within one week after notice all issues identified in the Submission(s) (including, without limitation, the resolution of license conflicts, the fulfillment of all obligations required by software licenses, and the removal of any software that violates the software restrictions).\nc. A potential winner may decline to be nominated as a Competition winner in accordance with Section 3.8.\nd. Potential winners must return all required Prize acceptance documents within two (2) weeks following notification of such required documents, or such potential winner will be deemed to have forfeited the prize and another potential winner will be selected. Prize(s) will be awarded within approximately thirty (30) days after receipt by Competition Sponsor or Kaggle of the required Prize acceptance documents. Transfer or assignment of a Prize is not allowed. \ne. You are not eligible to receive any Prize if you do not meet the Eligibility requirements in Section 2.7 and Section 3.1 above.\nf. If a Team wins a monetary Prize, the Prize money will be allocated in even shares between the eligible Team members, unless the Team unanimously opts for a different Prize split and notifies Kaggle before Prizes are issued.\n\n####10. TAXES\na. ALL TAXES IMPOSED ON PRIZES ARE THE SOLE RESPONSIBILITY OF THE WINNERS. Payments to potential winners are subject to the express requirement that they submit all documentation requested by Competition Sponsor or Kaggle for compliance with applicable state, federal, local and foreign (including provincial) tax reporting and withholding requirements. Prizes will be net of any taxes that Competition Sponsor is required by law to withhold. If a potential winner fails to provide any required documentation or comply with applicable laws, the Prize may be forfeited and Competition Sponsor may select an alternative potential winner. Any winners who are U.S. residents will receive an IRS Form-1099 in the amount of their Prize.\n\n####11. GENERAL CONDITIONS\na. All federal, state, provincial and local laws and regulations apply.\n\n####12. PUBLICITY\na. You agree that Competition Sponsor, Kaggle and its affiliates may use your name and likeness for advertising and promotional purposes without additional compensation, unless prohibited by law.\n\n####13. PRIVACY\na. You acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to, name, mailing address, phone number, and email address (“Personal Information”). Kaggle acts as an independent controller with regard to its collection, storage, sharing, and other use of this Personal Information, and will use this Personal Information in accordance with its Privacy Policy <[www.kaggle.com/privacy][6]>, including for administering the Competition. As a Kaggle.com account holder, you have the right to request access to, review, rectification, portability or deletion of any personal data held by Kaggle about you by logging into your account and/or contacting Kaggle Support at <[www.kaggle.com/contact][7]>.\nb. As part of Competition Sponsor performing this contract between you and the Competition Sponsor, Kaggle will transfer your Personal Information to Competition Sponsor, which acts as an independent controller with regard to this Personal Information. As a controller of such Personal Information, Competition Sponsor agrees to comply with all U.S. and foreign data protection obligations with regard to your Personal Information. Kaggle will transfer your Personal Information to Competition Sponsor in the country specified in the Competition Sponsor Address listed above, which may be a country outside the country of your residence. Such country may not have privacy laws and regulations similar to those of the country of your residence.\n\n####14. WARRANTY, INDEMNITY AND RELEASE \na. You warrant that your Submission is your own original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses. You agree not to make any Submission that: (i) infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; or (ii) otherwise violates any applicable U.S. or foreign state or federal law.\nb. To the maximum extent permitted by law, you indemnify and agree to keep indemnified Competition Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any of your acts, defaults or omissions and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the Competition Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules or any applicable U.S. or foreign state or federal law; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the Competition; and (e) your acceptance, possession, misuse or use of any Prize, or your participation in the Competition and any Competition-related activity.\nc. You hereby release Competition Entities from any liability associated with: (a) any malfunction or other problem with the Competition Website; (b) any error in the collection, processing, or retention of any Submission; or (c) any typographical or other error in the printing, offering or announcement of any Prize or winners.\n\n####15. INTERNET\na. Competition Entities are not responsible for any malfunction of the Competition Website or any late, lost, damaged, misdirected, incomplete, illegible, undeliverable, or destroyed Submissions or entry materials due to system errors, failed, incomplete or garbled computer or other telecommunication transmission malfunctions, hardware or software failures of any kind, lost or unavailable network connections, typographical or system/human errors and failures, technical malfunction(s) of any telephone network or lines, cable connections, satellite transmissions, servers or providers, or computer equipment, traffic congestion on the Internet or at the Competition Website, or any combination thereof, which may limit a Participant’s ability to participate.\n\n####16. RIGHT TO CANCEL, MODIFY OR DISQUALIFY\na. If for any reason the Competition is not capable of running as planned, including infection by computer virus, bugs, tampering, unauthorized intervention, fraud, technical failures, or any other causes which corrupt or affect the administration, security, fairness, integrity, or proper conduct of the Competition, Competition Sponsor reserves the right to cancel, terminate, modify or suspend the Competition. Competition Sponsor further reserves the right to disqualify any Participant who tampers with the submission process or any other part of the Competition or Competition Website. Any attempt by a Participant to deliberately damage any website, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws. Should such an attempt be made, Competition Sponsor and Kaggle each reserves the right to seek damages from any such Participant to the fullest extent of the applicable law.\n\n####17. NOT AN OFFER OR CONTRACT OF EMPLOYMENT\na. Under no circumstances will the entry of a Submission, the awarding of a Prize, or anything in these Rules be construed as an offer or contract of employment with Competition Sponsor or any of the Competition Entities. You acknowledge that you have submitted your Submission voluntarily and not in confidence or in trust. You acknowledge that no confidential, fiduciary, agency, employment or other similar relationship is created between you and Competition Sponsor or any of the Competition Entities by your acceptance of these Rules or your entry of your Submission.\n\n####18. DEFINITIONS\na. \"Competition Data\" are the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to Participants. \nb. An “Entry” is when a Participant has joined, signed up, or accepted the rules of a competition. Entry is required to make a Submission to a competition.\nc. A “Final Submission” is the Submission selected by the user, or automatically selected by Kaggle in the event not selected by the user, that is/are used for final placement on the competition leaderboard.\nd. A “Participant” or “Participant User” is an individual who participates in a competition by entering the competition and making a Submission.\ne. The “Private Leaderboard” is a ranked display of Participants’ Submission scores against the private test set. The Private Leaderboard determines the final standing in the competition.\nf. The “Public Leaderboard” is a ranked display of Participants’ Submission scores against a representative sample of the test data. This leaderboard is visible throughout the competition.\ng. A “Sponsor” is responsible for hosting the competition, which includes but is not limited to providing the data for the competition, determining winners, and enforcing competition rules.\nh. A “Submission” is anything provided by the Participant to the Sponsor to be evaluated for competition purposes and determine leaderboard position. A Submission may be made as a model, notebook, prediction file, or other format as determined by the Sponsor.\ni. A “Team” is one or more Participants participating together in a Kaggle competition, by officially merging together as a Team within the competition platform.\n\n [1]: https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx\n [2]: http://www.kaggle.com/terms\n [3]: http://www.opensource.org\n [4]: http://www.opensource.org\n [5]: https://www.kaggle.com/WinningModelDocumentationGuidelines\n [6]: http://www.kaggle.com/privacy\n [7]: http://www.kaggle.com/contact\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }