To promote code sharing and useful discussion we will award monthly bonus prizes to shared code and contributions that will be evaluated as useful or promising by the Vesuvius Challenge team. These prizes are not part of the ongoing prediction competition on Kaggle. Sharing code with the Vesuvius Challenge team does not impact your chances to win a prize in this ongoing challenge.
\nHow to participate? Share your code in the Code panel and fill the submission form (the link changes the 1st of every month, I'll keep it updated)
\nWe favor submissions that:
\nBonus prizes go from $1,000 to $20,000 (only for truly outstanding contributions).\nUsually, awarded bonus prizes sit in the $1,000 to $2,500 ballpark.
", "messages": [ { "id": "3346866", "postDate": "11/24/2025 17:25:29", "content": "To promote code sharing and useful discussion we will award monthly bonus prizes to shared code and contributions that will be evaluated as useful or promising by the Vesuvius Challenge team. These prizes are not part of the ongoing prediction competition on Kaggle. Sharing code with the Vesuvius Challenge team does not impact your chances to win a prize in this ongoing challenge.
\nHow to participate? Share your code in the Code panel and fill the submission form (the link changes the 1st of every month, I'll keep it updated)
\nWe favor submissions that:
\nBonus prizes go from $1,000 to $20,000 (only for truly outstanding contributions).\nUsually, awarded bonus prizes sit in the $1,000 to $2,500 ballpark.
", "rawMarkdown": "To promote code sharing and useful discussion we will award [monthly bonus prizes](https://scrollprize.org/prizes#progress-prizes) to shared code and contributions that will be evaluated as useful or promising by the Vesuvius Challenge team. These prizes are not part of the ongoing prediction competition on Kaggle. Sharing code with the Vesuvius Challenge team does not impact your chances to win a prize in this ongoing challenge. \n\nHow to participate? Share your code in the [Code panel](https://www.kaggle.com/competitions/vesuvius-challenge-surface-detection/code) and **fill the submission [form](https://forms.gle/mLUnkaWvaeuMYdgX6)** (the link changes the 1st of every month, I'll keep it updated)\n\nWe favor submissions that:\n\n- Are released or open-sourced **early**. Tools released earlier have a higher chance of being used than those released the last day of the month.\n- Actually **get used**. We’ll look for signals from the community.\n- Are **well documented**. It helps a lot if relevant documentation, walkthroughs, images, tutorials or similar are included with the work so that others can use it!\n\n**Bonus prizes go from $1,000 to $20,000** (only for truly outstanding contributions).\n*Usually, awarded bonus prizes sit in the $1,000 to $2,500 ballpark.*", "votes": null }, { "id": "3349380", "postDate": "11/26/2025 15:52:07", "content": "That's very nice!\nCould you give an example of a code that received a prize, so I can better understand what are you looking for?\nThanks!
", "rawMarkdown": "That's very nice!\nCould you give an example of a code that received a prize, so I can better understand what are you looking for?\nThanks!", "votes": null }, { "id": "3349694", "postDate": "11/26/2025 22:32:30", "content": "I would recommend focusing on something mentioned in this page.\nA good starting point could be looking at the issues of our monorepo.
\nWe would like to have improvements in our virtual unwrapping pipeline, called VC3D, but the codebase is in C++ and does not fit a notebook.
\nWhat could fit the Code panel of the Kaggle competition could be, for instance, a notebook to help people train better models for the Surface Detection competition. I would be really interested in seeing a self-supervised approach that can exploit all the unlabeled data we have. Keep in mind that these prizes are awarded directly by the Vesuvius Challenge team though, and not Kaggle. They are not directly part of the Kaggle competition.
\nIn any case, this is a list with all the prize winning contributions in the Vesuvius Challenge so far.\nHere you can find a broader list of community projects.\nThe amount of information can be overwhelming. For more guidance or direct interaction with the Vesuvius Challenge team join our discord.
", "rawMarkdown": "I would recommend focusing on something mentioned in [this page](https://scrollprize.org/prizes#progress-prizes).\nA good starting point could be [looking at the issues](https://github.com/ScrollPrize/villa/issues) of our monorepo.\n\nWe would like to have improvements in [our virtual unwrapping pipeline, called VC3D](https://github.com/ScrollPrize/villa/tree/main/volume-cartographer), but the codebase is in C++ and does not fit a notebook.\n\nWhat could fit the Code panel of the Kaggle competition could be, for instance, a notebook to help people train better models for the Surface Detection competition. I would be really interested in seeing a self-supervised approach that can exploit all the unlabeled data we have. Keep in mind that these prizes are awarded directly by the Vesuvius Challenge team though, and not Kaggle. They are not directly part of the Kaggle competition.\n\nIn any case, [this is a list](https://scrollprize.org/winners) with all the prize winning contributions in the Vesuvius Challenge so far.\n[Here](https://scrollprize.org/community_projects) you can find a broader list of community projects.\nThe amount of information can be overwhelming. For more guidance or direct interaction with the Vesuvius Challenge team join [our discord](https://discord.com/invite/V4fJhvtaQn).", "votes": null } ], "comments": [ { "id": 3349380, "author_name": "andrefilipeferreira", "author_url": "", "post_date": "11/26/2025 15:52:07", "content": "That's very nice!\nCould you give an example of a code that received a prize, so I can better understand what are you looking for?\nThanks!
", "votes": null, "replies": [ { "id": 3349694, "author_name": "giorgioangelotti", "author_url": "", "post_date": "11/26/2025 22:32:30", "content": "I would recommend focusing on something mentioned in this page.\nA good starting point could be looking at the issues of our monorepo.
\nWe would like to have improvements in our virtual unwrapping pipeline, called VC3D, but the codebase is in C++ and does not fit a notebook.
\nWhat could fit the Code panel of the Kaggle competition could be, for instance, a notebook to help people train better models for the Surface Detection competition. I would be really interested in seeing a self-supervised approach that can exploit all the unlabeled data we have. Keep in mind that these prizes are awarded directly by the Vesuvius Challenge team though, and not Kaggle. They are not directly part of the Kaggle competition.
\nIn any case, this is a list with all the prize winning contributions in the Vesuvius Challenge so far.\nHere you can find a broader list of community projects.\nThe amount of information can be overwhelming. For more guidance or direct interaction with the Vesuvius Challenge team join our discord.
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "3346866": "To promote code sharing and useful discussion we will award [monthly bonus prizes](https://scrollprize.org/prizes#progress-prizes) to shared code and contributions that will be evaluated as useful or promising by the Vesuvius Challenge team. These prizes are not part of the ongoing prediction competition on Kaggle. Sharing code with the Vesuvius Challenge team does not impact your chances to win a prize in this ongoing challenge. \n\nHow to participate? Share your code in the [Code panel](https://www.kaggle.com/competitions/vesuvius-challenge-surface-detection/code) and **fill the submission [form](https://forms.gle/mLUnkaWvaeuMYdgX6)** (the link changes the 1st of every month, I'll keep it updated)\n\nWe favor submissions that:\n\n- Are released or open-sourced **early**. Tools released earlier have a higher chance of being used than those released the last day of the month.\n- Actually **get used**. We’ll look for signals from the community.\n- Are **well documented**. It helps a lot if relevant documentation, walkthroughs, images, tutorials or similar are included with the work so that others can use it!\n\n**Bonus prizes go from $1,000 to $20,000** (only for truly outstanding contributions).\n*Usually, awarded bonus prizes sit in the $1,000 to $2,500 ballpark.*", "3349380": "That's very nice!\nCould you give an example of a code that received a prize, so I can better understand what are you looking for?\nThanks!", "3349694": "I would recommend focusing on something mentioned in [this page](https://scrollprize.org/prizes#progress-prizes).\nA good starting point could be [looking at the issues](https://github.com/ScrollPrize/villa/issues) of our monorepo.\n\nWe would like to have improvements in [our virtual unwrapping pipeline, called VC3D](https://github.com/ScrollPrize/villa/tree/main/volume-cartographer), but the codebase is in C++ and does not fit a notebook.\n\nWhat could fit the Code panel of the Kaggle competition could be, for instance, a notebook to help people train better models for the Surface Detection competition. I would be really interested in seeing a self-supervised approach that can exploit all the unlabeled data we have. Keep in mind that these prizes are awarded directly by the Vesuvius Challenge team though, and not Kaggle. They are not directly part of the Kaggle competition.\n\nIn any case, [this is a list](https://scrollprize.org/winners) with all the prize winning contributions in the Vesuvius Challenge so far.\n[Here](https://scrollprize.org/community_projects) you can find a broader list of community projects.\nThe amount of information can be overwhelming. For more guidance or direct interaction with the Vesuvius Challenge team join [our discord](https://discord.com/invite/V4fJhvtaQn)." }, "source": "meta" }