{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5PZ7SAXMN3BHKV4ER2D4YRI6R3","short_pith_number":"pith:5PZ7SAXM","schema_version":"1.0","canonical_sha256":"ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2","source":{"kind":"arxiv","id":"2207.01848","version":6},"attestation_state":"computed","paper":{"title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Katharina Eggensperger, Noah Hollmann, Samuel M\\\"uller","submitted_at":"2022-07-05T07:17:43Z","abstract_excerpt":"We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods. TabPFN performs in-context learning (ICL), it learns to make predictions using sequences of labeled examples (x, f(x)) given in the input, without requiring further parameter updates. TabPFN is fully entailed in the weights of our network, which accepts training and test samples as a set-valued input and yields predictions for the entire test set in a single forward pass. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2207.01848","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T07:17:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"25f4e9ad94e4b3fbf7db28c4ab7bfaae622b37a48b0e6199a0f88a4dd20dac16","abstract_canon_sha256":"28acee69c2f4693367d647e5f9cdc9fc67a218e6b96d2d6eb8f36716d625ef9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.723553Z","signature_b64":"+Tp2i9icgth18o6TSXohx0OvYZlhJKy8mVkOumrX4CKTnl16u6hhoJ7ycOW75B5pZXLweBQg39HlULPp9iy0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2","last_reissued_at":"2026-05-17T23:38:53.722896Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.722896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Katharina Eggensperger, Noah Hollmann, Samuel M\\\"uller","submitted_at":"2022-07-05T07:17:43Z","abstract_excerpt":"We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods. TabPFN performs in-context learning (ICL), it learns to make predictions using sequences of labeled examples (x, f(x)) given in the input, without requiring further parameter updates. TabPFN is fully entailed in the weights of our network, which accepts training and test samples as a set-valued input and yields predictions for the entire test set in a single forward pass. "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230× speedup.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The prior over structural causal models used to generate the synthetic training data is sufficiently representative of the distribution of real-world small tabular classification problems so that the trained network generalizes without further adaptation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6852d01c272470356b71902230753f8d782dc64a638a8da6c23d6e6a48757865"},"source":{"id":"2207.01848","kind":"arxiv","version":6},"verdict":{"id":"1943ae2a-5d64-4d0b-bfcf-d12c23b1c328","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:58:24.217861Z","strongest_claim":"On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230× speedup.","one_line_summary":"TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The prior over structural causal models used to generate the synthetic training data is sufficiently representative of the distribution of real-world small tabular classification problems so that the trained network generalizes without further adaptation.","pith_extraction_headline":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning."},"references":{"count":41,"sample":[{"doi":"","year":2004,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","ref_index":1,"cited_arxiv_id":"2004.05150","is_internal_anchor":true},{"doi":"","year":null,"title":"V . Borisov, T. Leemann, K. Seßler, J. Haug, M. Pawelczyk, and G. Kasneci. Deep neural networks and tabular data: A survey. arXiv:2110.01889 [cs.LG],","work_id":"93f57855-ef13-447a-9bb3-7c52593fcd9f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"eb041f9e-11f2-4d39-b912-b66f075cd8ab","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"URL https://proceedings.neurips.cc/paper_files/paper/ 2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf. T. Chen and C. Guestrin. Xgboost: A scalable tree boosting system. In B. Krishnapuram, M. Sh","work_id":"466eef06-1c73-4be7-b5c0-e7a0aac54cb7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"arXiv preprint arXiv:2006.10029 , year=","work_id":"c3db4fa8-1334-4859-bdc9-38d1fc92426f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"28adc855b3cfd2ae0ddbf3638f6f56ac181fe03e7c985b0bb56fe19775b7de70","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dcbffae37fc8598935b1fd0cdb4752ac7d12cfd4950a079218cf981e56141047"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2207.01848","created_at":"2026-05-17T23:38:53.722988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01848v6","created_at":"2026-05-17T23:38:53.722988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01848","created_at":"2026-05-17T23:38:53.722988+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PZ7SAXMN3BH","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PZ7SAXMN3BHKV4E","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PZ7SAXM","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":44,"internal_anchor_count":44,"sample":[{"citing_arxiv_id":"2403.20208","citing_title":"Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretraining","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2503.14434","citing_title":"LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21742","citing_title":"Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21544","citing_title":"Tabular foundation models for robust calibration of near-infrared chemical sensing data","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21465","citing_title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27195","citing_title":"Evaluating TabPFN for Mild Cognitive Impairment to Alzheimer's Disease Conversion in Data Limited Settings","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20674","citing_title":"Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13392","citing_title":"ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07098","citing_title":"CarCrashNet: A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2502.05564","citing_title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","ref_index":226,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18383","citing_title":"TabH2O: A Unified Foundation Model for Tabular Prediction","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18979","citing_title":"TabQL: In-Context Q-Learning with Tabular Foundation Models","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19812","citing_title":"FLUXtrapolation: A benchmark on extrapolating ecosystem fluxes","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19662","citing_title":"When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17406","citing_title":"Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15488","citing_title":"SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11449","citing_title":"Tabular Data with Class Imbalance: Predicting Electric Vehicle Crash Severity with Pretrained Transformers (TabPFN) and Mamba-Based Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":140,"is_internal_anchor":true},{"citing_arxiv_id":"2211.15661","citing_title":"What learning algorithm is in-context learning? Investigations with linear models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2512.21602","citing_title":"An Empirical Study of Machine Learning Robustness and Scalability for Imbalanced Tabular Clinical Data in Emergency and Critical Care","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2602.21876","citing_title":"Comparative Evaluation of Machine Learning Models for Predicting Donor Kidney Discard","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13986","citing_title":"TabPFN-3: Technical Report","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2511.08667","citing_title":"TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14591","citing_title":"Privacy Auditing with Zero (0) Training Run","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16378","citing_title":"Reciprocal Co-Training (RCT): Coupling Gradient-Based and Non-Differentiable Models via Reinforcement Learning","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3","json":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3.json","graph_json":"https://pith.science/api/pith-number/5PZ7SAXMN3BHKV4ER2D4YRI6R3/graph.json","events_json":"https://pith.science/api/pith-number/5PZ7SAXMN3BHKV4ER2D4YRI6R3/events.json","paper":"https://pith.science/paper/5PZ7SAXM"},"agent_actions":{"view_html":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3","download_json":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3.json","view_paper":"https://pith.science/paper/5PZ7SAXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01848&json=true","fetch_graph":"https://pith.science/api/pith-number/5PZ7SAXMN3BHKV4ER2D4YRI6R3/graph.json","fetch_events":"https://pith.science/api/pith-number/5PZ7SAXMN3BHKV4ER2D4YRI6R3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/action/storage_attestation","attest_author":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/action/author_attestation","sign_citation":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/action/citation_signature","submit_replication":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/action/replication_record"}},"created_at":"2026-05-17T23:38:53.722988+00:00","updated_at":"2026-05-17T23:38:53.722988+00:00"}