We’re happy to announce our first release in relational learning at Prior Labs, continuing our commitment to open science.</p>\n<p>We open-source three pieces of software that we expect to accelerate research in the field towards meaningful, real-world impact.</p>\n<p>First and foremost, we release 𝗥𝗲𝗹𝗔𝗿𝗲𝗻𝗮-α: a unified framework for running and comparing baselines on RelBench v1 tasks. Based on learnings from tabular benchmarks like TabArena, we are standardizing data loading, evaluation protocols, tuning regimes, and adding support for systems with custom tuning.</p>\n<p>We also open-source 𝗧𝗮𝗯𝗣𝗙𝗡-𝗥𝗲𝗹: our relational harness for TabPFN-3. We initialize the (living) RelArena-α leaderboard with TabPFN-Rel and a comprehensive set of baselines. The rankings at the time of release are:</p>\n<p>• 𝗧𝗮𝗯𝗣𝗙𝗡-𝗥𝗲𝗹 is the No. 1 model submission<br>• 𝗥𝗧-𝗣𝗹𝘂𝗥𝗲𝗹 is the No. 1 system submission</p>\n<p>Last but not least, we open-source an alpha version of the 𝗥𝗲𝗹𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗣𝗿𝗲𝗱𝗶𝗰𝘁𝗶𝘃𝗲 𝗜𝗻𝘁𝗲𝗿𝗳𝗮𝗰𝗲 (𝗥𝗣𝗜): enabling you to easily specify prediction tasks on your own relational database and then run any RelArena-α model, like TabPFN-Rel, in a few lines of code, all bundled as a simple PyPI package.</p>\n","updatedAt":"2026-08-18T10:01:16.005Z","author":{"_id":"60d84af7eac5e05d4594f010","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60d84af7eac5e05d4594f010/KnGxUR7OUOAGg0S67tRaY.png","fullname":"Alan Arazi","name":"alana89","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8772198557853699},"editors":["alana89"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/60d84af7eac5e05d4594f010/KnGxUR7OUOAGg0S67tRaY.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.16319","authors":[{"_id":"6a842cf2236d8fccf7c417e2","name":"Adrian Hayler","hidden":false},{"_id":"6a842cf2236d8fccf7c417e3","name":"Klemens Flöge","hidden":false},{"_id":"6a842cf2236d8fccf7c417e4","name":"Alan Arazi","hidden":false},{"_id":"6a842cf2236d8fccf7c417e5","name":"Rishabh Ranjan","hidden":false},{"_id":"6a842cf2236d8fccf7c417e6","name":"Jure Leskovec","hidden":false},{"_id":"6a842cf2236d8fccf7c417e7","name":"Felix Birkel","hidden":false},{"_id":"6a842cf2236d8fccf7c417e8","name":"Brendan Roof","hidden":false},{"_id":"6a842cf2236d8fccf7c417e9","name":"Anurag Garg","hidden":false},{"_id":"6a842cf2236d8fccf7c417ea","name":"Kristina Collins","hidden":false},{"_id":"6a842cf2236d8fccf7c417eb","name":"Lydia Sidhoum","hidden":false},{"_id":"6a842cf2236d8fccf7c417ec","name":"Jonas Kübler","hidden":false},{"_id":"6a842cf2236d8fccf7c417ed","name":"Siyuan Guo","hidden":false},{"_id":"6a842cf2236d8fccf7c417ee","name":"Oscar Key","hidden":false},{"_id":"6a842cf2236d8fccf7c417ef","name":"Jan Hendrik Metzen","hidden":false},{"_id":"6a842cf2236d8fccf7c417f0","name":"Rylee Grace","hidden":false},{"_id":"6a842cf2236d8fccf7c417f1","name":"David Salinas","hidden":false},{"_id":"6a842cf2236d8fccf7c417f2","name":"Arthur Cahu","hidden":false},{"_id":"6a842cf2236d8fccf7c417f3","name":"Simon Bing","hidden":false},{"_id":"6a842cf2236d8fccf7c417f4","name":"Benjamin Jäger","hidden":false},{"_id":"6a842cf2236d8fccf7c417f5","name":"Tuana Çelik","hidden":false},{"_id":"6a842cf2236d8fccf7c417f6","name":"Mihir Manium","hidden":false},{"_id":"6a842cf2236d8fccf7c417f7","name":"Vitor Monteiro","hidden":false},{"_id":"6a842cf2236d8fccf7c417f8","name":"Jake Robertson","hidden":false},{"_id":"6a842cf2236d8fccf7c417f9","name":"Jerry Chen","hidden":false},{"_id":"6a842cf2236d8fccf7c417fa","name":"Eliott Kalfon","hidden":false},{"_id":"6a842cf2236d8fccf7c417fb","name":"Tomás Pereda","hidden":false},{"_id":"6a842cf2236d8fccf7c417fc","name":"Lilly Wehrhahn","hidden":false},{"_id":"6a842cf2236d8fccf7c417fd","name":"Dominik Safaric","hidden":false},{"_id":"6a842cf2236d8fccf7c417fe","name":"Tobias Schroeder","hidden":false},{"_id":"6a842cf2236d8fccf7c417ff","name":"Georg Grab","hidden":false},{"_id":"6a842cf2236d8fccf7c41800","name":"Diana Kriuchkova","hidden":false},{"_id":"6a842cf2236d8fccf7c41801","name":"Clara Cornu","hidden":false},{"_id":"6a842cf2236d8fccf7c41802","name":"Philipp Singer","hidden":false},{"_id":"6a842cf2236d8fccf7c41803","name":"Nick Erickson","hidden":false},{"_id":"6a842cf2236d8fccf7c41804","name":"Vahid Balazadeh","hidden":false},{"_id":"6a842cf2236d8fccf7c41805","name":"Marie Salmon","hidden":false},{"_id":"6a842cf2236d8fccf7c41806","name":"Simone Alessi","hidden":false},{"_id":"6a842cf2236d8fccf7c41807","name":"Kürşat Kaya","hidden":false},{"_id":"6a842cf2236d8fccf7c41808","name":"Philipp Jund","hidden":false},{"_id":"6a842cf2236d8fccf7c41809","name":"Léo Grinsztajn","hidden":false},{"_id":"6a842cf2236d8fccf7c4180a","name":"Yann LeCun","hidden":false},{"_id":"6a842cf2236d8fccf7c4180b","name":"Bernhard Schölkopf","hidden":false},{"_id":"6a842cf2236d8fccf7c4180c","name":"Madelon Hulsebos","hidden":false},{"_id":"6a842cf2236d8fccf7c4180d","name":"Lennart Purucker","hidden":false},{"_id":"6a842cf2236d8fccf7c4180e","name":"Sauraj Gambhir","hidden":false},{"_id":"6a842cf2236d8fccf7c4180f","name":"Frank Hutter","hidden":false},{"_id":"6a842cf2236d8fccf7c41810","name":"Noah Hollmann","hidden":false}],"publishedAt":"2026-08-17T00:00:00.000Z","submittedOnDailyAt":"2026-08-18T00:00:00.000Z","title":"Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPI","submittedOnDailyBy":{"_id":"60d84af7eac5e05d4594f010","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60d84af7eac5e05d4594f010/KnGxUR7OUOAGg0S67tRaY.png","isPro":false,"fullname":"Alan Arazi","user":"alana89","type":"user","name":"alana89"},"summary":"This first release of Prior Labs in relational learning shows our continued commitment to open science. We open-source three pieces of software that we expect to accelerate research in the field towards meaningful real-world impact. We aim to steer further development based on feedback from, and in collaboration with, the community. Given the early stage of development, our α-release targets researchers and early-adopting practitioners. Over the past years, a variety of datasets and tasks for relational learning have emerged, but the community has not converged on a reliable, reproducible way to compare different methods on these tasks. Our α-release, RelArena-α, provides a unified framework for running and comparing baselines on RelBench v1 by standardizing data loading, evaluation protocols, tuning regimes, and support for systems with custom tuning, inspired by established tabular benchmarks such as TabArena. We plan to work with the research community to further develop RelArena-α into a catalyst for progress in the relational learning community. We release the initial version of TabPFN-Rel, a purpose-built relational harness for TabPFN-3. Currently ranked first among models on RelArena-α, TabPFN-Rel makes key improvements upon RDBLearn. Beyond its ranking, TabPFN-Rel serves as a strong baseline, adding to the growing evidence that flattening a relational database into a single table remains competitive with specialized relational architectures on real-world tasks.\n To facilitate adoption of relational learning methods in research and industry, we release an initial α-version of our Relational Predictive Interface, RPI, an open-source, model-agnostic interface that enables early adopters to easily define problems on new databases and apply any model implemented in RelArena-α, including TabPFN-Rel, to these problems.","upvotes":14,"discussionId":"6a842cf2236d8fccf7c41811","projectPage":"https://priorlabs.ai/blog-posts/introducing-relarena","githubRepo":"https://github.com/PriorLabs/relarena","githubRepoAddedBy":"user","ai_summary":"Prior Labs released open-source tools including a unified relational benchmark framework, a TabPFN-based relational model, and a model-agnostic predictive interface to advance reproducible relational learning.","ai_keywords":["relational learning","RelBench","RelArena-α","TabPFN-Rel","TabPFN-3","RDBLearn","relational database","RPI"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":18,"organization":{"_id":"67370b3714a06e89f0bdbf76","name":"Prior-Labs","fullname":"Prior Labs","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b78c716d1ab5645846f8b2/GNHO7j_dNIsnK9SQX-7ER.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"60d84af7eac5e05d4594f010","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60d84af7eac5e05d4594f010/KnGxUR7OUOAGg0S67tRaY.png","isPro":false,"fullname":"Alan Arazi","user":"alana89","type":"user"},{"_id":"696dfad5489de75a728ec14a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/696dfad5489de75a728ec14a/SGOSYNkeENNCOGbvddeV2.jpeg","isPro":false,"fullname":"Alan Arazi","user":"alanprior","type":"user"},{"_id":"617721aa4ce8f8cb2c2c7497","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1648853347063-617721aa4ce8f8cb2c2c7497.jpeg","isPro":false,"fullname":"Tuana Celik","user":"Tuana","type":"user"},{"_id":"663b2a89ec1aafe3d68e3012","avatarUrl":"/avatars/6a6e5435af289776bc2f5d90898ece0b.svg","isPro":false,"fullname":"Shoham Grunblat","user":"mikothegreat","type":"user"},{"_id":"60ef001bed64a34082bfa0dd","avatarUrl":"/avatars/78e4daeac169edbf4dc42fbed9b50d59.svg","isPro":false,"fullname":"Omer Shubi","user":"scaperex","type":"user"},{"_id":"64802fb6c57f629056c59966","avatarUrl":"/avatars/d5ecabaceeba759969855acf512b6649.svg","isPro":false,"fullname":"Eilam Shapira","user":"EilamSha","type":"user"},{"_id":"69b15cf17337febadc61ce1b","avatarUrl":"/avatars/e8361301f2009ba0b25330e8a63b59b4.svg","isPro":false,"fullname":"Georg Grab","user":"ggprior","type":"user"},{"_id":"6981b0800dde6f04024f6e85","avatarUrl":"/avatars/dbc2237ba45c48863ca57e58517dbb49.svg","isPro":false,"fullname":"Jan Hendrik Metzen","user":"jmetzen-prior","type":"user"},{"_id":"677d00ac70b9142c01cc90f9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/677d00ac70b9142c01cc90f9/c2utzkEFwdUHPLN8-_AHb.png","isPro":false,"fullname":"Lennart Purucker","user":"LennartPurucker","type":"user"},{"_id":"64b01f320eca8dd88e0c4e47","avatarUrl":"/avatars/5a1065f91124410798316daf9f51fc7e.svg","isPro":false,"fullname":"Oliver Guy","user":"Oliver-Guy","type":"user"},{"_id":"62d0984ffb896639b29d3b7f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1657837531684-noauth.jpeg","isPro":false,"fullname":"Anurag Garg","user":"anuraggarg","type":"user"},{"_id":"666abac46993100c6fd23629","avatarUrl":"/avatars/0fcd2dd452ba899c1c71109b08e18f8d.svg","isPro":false,"fullname":"Jonas Kübler","user":"jonaskuebler","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"67370b3714a06e89f0bdbf76","name":"Prior-Labs","fullname":"Prior Labs","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b78c716d1ab5645846f8b2/GNHO7j_dNIsnK9SQX-7ER.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.16319.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.16319 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.16319 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.16319 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.