{ "fetched_at": "2026-10-19T07:11:09Z", "source_url": "https://www.kaggle.com/competitions/concon/data", "pages": [ { "name": "data-description", "content": "# Concon Dataset Structure\n\nConcon contains three image datasets—`unconf`, `disjoint`, and `strict`—designed for training, validation, and testing machine learning models. Each dataset is structured with folders for `train`, `test`, and `val` sets (where applicable) and contains PNG images organized by tasks.\n\n## Overview of Datasets\n\n### unconf\nThe `unconf` dataset is *unconfounded* and generated using only the ground truth rule. Across all tasks, this rule is present in positive images and absent in negative images. This dataset is intended to provide models with data that is free of any confounding factors for accurate testing. It is structured as follows:\n\n- `test`: Contains images for testing, structured with tasks, such as:\n - `images/t0`: Images for testing under task `t0`.\n\n### disjoint\nThe `disjoint` dataset is a *confounded* dataset split into training, validation, and testing sets. In this dataset, **confounders from any task do not reappear across tasks**. This means that the confounders are fully separated, making it useful for evaluating model performance when trained on data with distinctive confounding factors across tasks.\n\n- `train`: Contains images for training, divided into tasks:\n - `images/t0`: Images for task `t0`, further divided into `0`, `1`, etc., subdirectories.\n - `images/t1`: Images for task `t1`.\n - `images/t2`: Images for task `t2`.\n- `test` and `val`: Follow the same structure as `train`, with tasks `t0`, `t1`, etc.\n\n### strict\nThe `strict` dataset is another *confounded* dataset, following the same structure as `disjoint`. Here, **only the specific confounders are avoided in negative samples for each respective task**, creating a stricter confounding setup. This setup allows for a nuanced test of model performance when some but not all confounding factors are present.\n\n- `train`, `test`, and `val`: Each contains images for tasks (`t0`, `t1`, etc.), following the same format as `disjoint`.\n\n---\n\n## Folder Structure\n\nBelow is the structure of the datasets, illustrating the organization of subdirectories within each dataset.\n\n```plaintext\nroot_directory/\n├── unconf\n│ └── test\n│ └── images\n│ └── t0\n├── disjoint\n│ ├── train\n│ │ └── images\n│ │ ├── t0\n│ │ │ ├── 0\n│ │ │ └── 1\n│ │ ├── t1\n│ │ └── t2\n│ ├── test\n│ │ └── images\n│ └── val\n│ └── images\n└── strict\n ├── train\n │ └── images\n ├── test\n │ └── images\n └── val\n └── images\n```\n\n\n### Folder Descriptions\n\n- **`unconf/test/images/t0`**: Contains PNG images for unconfounded testing under `t0`.\n\n- **`disjoint/train/images`**: Holds confounded images for training, with further subdivision by tasks (`t0`, `t1`, `t2`). Within `t0`, subdirectories `0` and `1` may represent different categories or splits within task `t0`.\n\n- **`disjoint/test/images` and `disjoint/val/images`**: Structured similarly to `train/images`, containing confounded test and validation images divided by tasks.\n\n- **`strict/train`, `strict/test`, and `strict/val`**: Follow the same format as `disjoint`, with separate images for each task to simulate confounded conditions.\n\n\n## Additional Details on Dataset Design\n\n- **unconf (Unconfounded)**:\n - This dataset contains only the ground truth rule for each task.\n - The rule appears in positive images and is absent in negative images.\n - These images are used for testing the trained models.\n\n- **disjoint (Confounded)**:\n - Confounders are completely disjoint across tasks, meaning no confounders reappear between tasks.\n - Suitable for training models where confounding effects are separated by tasks.\n - All positive images `(subdirectory 1)` adhere to the groud truth rule as well as have the `disjoint` property and negative images `(subdirectory 0)` do not.\n\n- **strict (Confounded)**:\n - Confounders specific to each task are avoided in the negative samples only for that task.\n - Ideal for testing models under stricter confounding conditions.\n - All positive images `(subdirectory 1)` adhere to the groud truth rule as well as have the `strict` property and negative images `(subdirectory 0)` do not.\n\n## File Types\n\nAll images are stored in **PNG format**. Each task folder contains images relevant to specific tasks, enabling model testing on task-specific data under different configurations (unconfounded, confounded).\n\n---\n\n### Usage Instructions\n\n1. **Loading the Datasets**:\n - Use `unconf` for testing models on unconfounded data.\n - Use `disjoint` and `strict` for training and testing models on confounded data.\n\n2. **Navigating Tasks**:\n - To begin with, either select `disjoint` or `strict` variant of the dataset. \n - Train a model on `t0` ⟶ `t1` ⟶ `t2` i.e. in a sequential manner. \n - Each task folder (e.g., `t0`, `t1`, `t2`) represents a different subset of data. Subfolders like `0` and `1` within each task represent negative and positive labels.\n\n---\n\nThis dataset organization is designed to support comprehensive experiments on unconfounded and confounded datasets, providing a range of task-specific data under conditions where confounders change over time to facilitate testing machine learning models.\n\n\n### License \nThe dataset is made available under the BSD 2-Clause \"Simplified\" License (see https://opensource.org/license/bsd-2-clause)", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "# Dataset Information\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F4133893%2F534e507c6bf938cf73300e54ccd6d807%2FScreenshot%202024-11-07%20at%2010.11.12AM.png?generation=1730954501154839&alt=media)\n\n**ConCon** represents a learning task of two classes: **positive and negative**. All data instances are images based on the **CLEVR** framework. A ground truth rule can be used to determine the class affiliation of any image (green star in the attached figure). In order to correctly classify any image, learning this ground truth rule is sufficient. Since ConCon is a continual learning dataset, there are **three tasks** that are learned after one another. Each task is confounded by a **task-specific confounder** (spiral in the attached figure), i.e., a feature that is present in the positive but not in the negative images of that task. The task-specific confounder changes across tasks.\n\nAs can be seen in the attached figure, there are two dataset variants. There is the\n\n- **Disjoint** dataset, where task-specific confounders **never appear in other tasks**, and the\n- **Strict** dataset, where task-specific confounders **may appear in other tasks** as random features in both positive and negative samples.\n\nWe hypothesize that the main challenge of the disjoint dataset will be to identify that the actual ground truth features are not the ones that are easiest to learn. For the strict dataset, storing information from previous tasks such that the ground truth feature can be learned in new tasks appears to be important.\n\n**We accept submissions on either dataset**, i.e., a submission is not required to perform well on both tasks. Submissions proposing solutions for both datasets are allowed but not required.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Goals & Evaluation", "content": "In this challenge, the goal is to train a model that learns the ground truth rule and, thus, performs well on unconfounded data. To this end, it must avoid only learning the easy solution that is given by the task-specific confounders. To this end, in addition to the data for the confounded tasks, we publish an unconfounded dataset without labels. The goal is to **maximize the performance on this unconfounded dataset**. Specifically, the accuracy is to be calculated as\n\n$$\\text{acc} = \\sum_{i=1}^{n}\\frac{\\mathbb{I}(\\hat{y}_i = y_i)}{n},$$\n\nwhere *n = 1500* is the number of samples in the unconfounded dataset, ŷᵢ is the prediction for sample i, and yᵢ is the ground truth label for sample i. Out of these 1500 images, 450 (30%) images are used for evaluation for the public leaderboard and the other 1050 (70%) images are used for evaluation for a private leaderboard.\n\n**Training instructions:** Training should be conducted one step at a time, following the continual learning order given by the dataset. This means a model should first be trained on data from Task 0, then updated using data from Task 1, and after that, updated using data from Task 2. Data used to train and update the model may not simply be accumulated fully, however using a small amount of memory as a memory buffer is in principle permitted. The size of the buffer should be justified and generally as small as possible.\n\n---\n## Submission Instructions\n\nSubmissions should propose an approach that helps overcome continual confounding. Their success in doing so can be measured by their performance on the confounded tasks and, more importantly, the unconfounded dataset.\n\nFor the submission to be presented at the bridge, participants should write a 3-page report (excluding references, acknowledgments, and an optional appendix including figures) detailing their approach and reporting the results on the public dataset. Submission will be reviewed in a single blind review process (author names included, reviewer names anonymous). In addition, a repository of the code used to train the model should be included as part of this submission.\n\nThere is an **early deadline on December 6, 2024 11:59pm (Anywhere on Earth, AoE)** and the **final deadline on January 7, 2025 11:59pm (Anywhere on Earth, AoE)**. Entries submitted until the early deadline will be reviewed in time for people to register with the early registration and to give more time to deal with possible visa issues.\n\n\n## Submission File\nFor each ID in the test set (filename without extension in `unconf/test/images/t0`), you must predict the correct label for the TARGET variable. The file should contain a header and have the following format:\n\n ID,TARGET\n image_1,0\n image_2,0\n image_3,1\n etc.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "##ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.\n\n*The ConCon Challenge is a skills-based competition to promote and further the field of machine learning. You must register via the Competition Website to enter . To enter the Competition, you must agree to these Official Competition Rules, which incorporate by reference the provisions and content of the Competition Website and any Specific Competition Rules herein (collectively, the \"Rules\"). Please read these Rules carefully before entry to ensure you understand and agree. You further agree that Submission in the Competition constitutes agreement to these Rules. You may not submit to the Competition and are not eligible to receive the prizes associated with this Competition unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition. Your competition Submissions must conform to the requirements stated on the Competition Website. Your Submissions will be scored based on the evaluation metric described on the Competition Website, and the novelty. Subject to compliance with the Competition Rules, Prizes, if any, will be awarded to Participants with the best scores, based on the merits of the data science models submitted. See below for the complete Competition Rules.*\n\n**You cannot sign up to Kaggle from multiple accounts and therefore you cannot enter or submit from multiple accounts.**\n\n###COMPETITION-SPECIFIC RULES \nIn addition to the provisions of the General Competition Rules below, you understand and agree to these Competition-Specific Rules.\n\n####1. TEAM LIMITS\na. The maximum Team size is 5.\nb. Team mergers are allowed and can be performed by the Team leader. In order to merge, the combined Team must have a total Submission count less than or equal to the maximum allowed as of the Team Merger Deadline. The maximum allowed is the number of Submissions per day multiplied by the number of days the competition has been running.\n\n####2. SUBMISSION LIMITS\na. You may submit a maximum of **10 Submissions** per day.\nb. You may select up to **3 Final Submissions** for judging.\n\n####3. COMPETITION TIMELINE\na. Competition Timeline dates (including Entry Deadline, Final Submission Deadline, Start Date, and Team Merger Deadline, as applicable) are reflected on the competition’s Overview > Timeline page.\n\n####4. COMPETITION DATA ACCESS AND USE\nThe dataset is made available under the BSD 2-Clause \"Simplified\" License (see https://opensource.org/license/bsd-2-clause)\n\n####5. TRAINING INSTRUCTIONS\n- You must train on only one of the variants (**disjoint** or **strict**) and test on **unconf** for submission\n- Training should be conducted one step at a time, following the continual learning order given by the dataset. This means a model should first be trained on data from Task 0, then updated using data from Task 1, and after that, updated using data from Task 2. \n- Data used to train and update the model may not simply be accumulated fully, however using a small amount of memory as a memory buffer is in principle permitted. The size of the buffer should be justified and generally as small as possible.\n\n####6. AUXILIARY INFORMATION \nYou are required to submit a readme file along with any submission. The template for the readme file is as follows:\n\n#####readme File\n```markdown\n\nABSTRACT\nLorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc ut lectus nisl. Sed posuere odio quis nibh aliquam, non fringilla risus fringilla. Sed non enim in ante molestie gravida. Sed rhoncus vel felis non varius. Aliquam et posuere turpis. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Donec eget iaculis orci, id tincidunt elit. Donec velit massa, lobortis non dignissim id, accumsan a sem. Etiam quis purus a tortor faucibus pulvinar vitae a est.\n\nDATASET USED IN TRAINING: Choose from either \"Strict\" or \"Disjoint\" (Only one is allowed)\n\nBUFFER SIZE: Applicable only if the methodology involves the use of a replay buffer. \n\nADDITIONAL COMMENTS: Optional, if any.\n```\n\nIn addition to the solutions submission and the readme file, you are required to provide a detailed report of how the submission was generated. This may include a detailed description of methodology, where one must be able to reproduce the approach by reading the description, and includes a detailed explanation of the architecture, preprocessing, loss function, training details, hyper-parameters, etc. The description should also include a link to a code repository with complete and detailed instructions so that the results obtained can be reproduced.\n\nIn the event that the results are not reproducible within a reasonable margin of error, the entry will be disqualified. \n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "abstract", "content": "This [challenge](https://www.continualcausality.org/challenge/) is part of the 3rd [Continual Causality](https://www.continualcausality.org/) Bridge Program at [AAAI 2025](https://aaai.org/conference/aaai/aaai-25/) held on 25th and 26th February 2025.\n\nA well-known problem encountered by typical machine learning methods is that confounders only present in the training data prevent the model from **generalizing to unseen data**. If a model is trained on datasets one after another in the **continual setting**, certain task-specific confounders could negatively affect model performance more severely compared to a joint setup. This **“continual confounding”** problem is represented by **ConCon**, an image dataset based on CLEVR where confounders differ across tasks. It has been shown that joint training on ConCon is less sensitive to confounding compared to the continual learning setup. \n\nIn this challenge, we invite participants to submit solutions to this Kaggle challenge, together with a corresponding 3-page report, for overcoming the challenges posed by continual confounding. All solutions can be submitted **until January 7, 2025**. Note that we also offer an **early deadline on December 6, 2024**. Any entries submitted until this date will be reviewed in time for people to register with the AAAI early registration deadline and to give more time to deal with possible visa issues.\n\n**Leaderboard:** The leaderboard covers submissions for both the strict and disjoint splits of the dataset (even though evaluation is done on the same test set). As both splits come with different assumptions and challenges, don't feel discouraged from submitting your approach just because others seem to perform better in terms of raw numbers. :)\n\n\n# Challenge Submission\n\nParticipants are required to submit a short report (including a link to their code) through the following Google form:\nhttps://forms.gle/vrwmCYT32TTZ7Eor8\n\nIf you have any questions, please contact us at info[at]continualcausality[dot]org.\n\n", "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 }, { "name": "Bridge Inclusion Criteria", "content": "We accept submissions that propose an effective or innovative strategy for overcoming continual confounding. All accepted submissions get the **possibility to present a poster** at the bridge. However, this participation is not mandatory. \n\nOut of all accepted submissions, we will highlight a select subset of papers, inviting them for **long presentation in person at the bridge**. Papers can either be highlighted based on their effectiveness of the proposed strategy on the unconfounded dataset or for their innovativeness and novelty in methodology. Additionally, highlighted papers will get a **free Tutorial/Lab/Bridge Program Only Registration**.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "FAQ", "content": "**Where can I get more information on ConCon and continual confounding?**\nThe paper “Where is the Truth? The Risk of Getting Confounded in a Continual World” introduces ConCon and discusses continual confounding in detail. There, you can get more information and discussions of the problems posed by this challenge. You can find it on [arXiv](https://arxiv.org/abs/2402.06434).\n\n**What is the difference between the disjoint and the strict scenario?**\nIn the disjoint dataset, task-specific confounders never appear in other tasks, and in the strict dataset, task-specific confounders may appear in other tasks as random features in both positive and negative samples. Note that this means that the disjunction of all confounding features is a valid solution for solving all confounded tasks in the disjoint case but not in the strict case.\n\n**Does my method need to work for both disjoint and strict scenarios?**\nNo, it is sufficient if a submission only considers one scenario. Of course, it is also allowed to propose solutions that perform well on both.\n\n**How should I submit?** Please submit a 3-page report on Google Forms, along with a link to your code repository if you wish to present your challenge submission at the bridge. \n\n**What should I evaluate?** The Kaggle competition measures the performance on the unconfounded dataset. In the report, please also include model performance on all confounded task for transparency. \n\n**How should I train the model?** First, choose a scenario (strict or disjoint) on which to run the experiments. Then, the model should be trained in a Continual Learning setting, i.e., starting by training on Task 0, then on Task 1, and, lastly, on Task 2. The datasets should not be accumulated, but using a small number of samples is permitted (for example, for replay techniques).\n\n**Can we use pre-trained weights?** No, using pre-trained weights is not allowed. The model should be trained from scratch using only the ConCon dataset.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }