{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HQZIL4JYLUP5FCKMUMTSJSDG2S","short_pith_number":"pith:HQZIL4JY","schema_version":"1.0","canonical_sha256":"3c3285f1385d1fd2894ca32724c866d4b6d8e3dc315b7e501f53d8bf60270401","source":{"kind":"arxiv","id":"2112.10510","version":7},"attestation_state":"computed","paper":{"title":"Transformers Can Do Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Josif Grabocka, Noah Hollmann, Samuel M\\\"uller, Sebastian Pineda Arango","submitted_at":"2021-12-20T13:07:39Z","abstract_excerpt":"Currently, it is hard to reap the benefits of deep learning for Bayesian methods, which allow the explicit specification of prior knowledge and accurately capture model uncertainty. We present Prior-Data Fitted Networks (PFNs). PFNs leverage in-context learning in large-scale machine learning techniques to approximate a large set of posteriors. The only requirement for PFNs to work is the ability to sample from a prior distribution over supervised learning tasks (or functions). Our method restates the objective of posterior approximation as a supervised classification problem with a set-valued"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2112.10510","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T13:07:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae6699c37687ec3f8332be90e8e1029f8e0f1343ec1cd6e59bfdc20c0b948787","abstract_canon_sha256":"fdfe25b213b21970a56a6d0886c54258c4eaca257530bc3e67f5af4f61707889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:40.252800Z","signature_b64":"NOBnhsjhGwyY1xpofXGfWmNKU2jPLLtvRx92K7XZo5R56/7kU1asM6MtvFF0bxHfk3QkKSaOy1uXgrrvz8zMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c3285f1385d1fd2894ca32724c866d4b6d8e3dc315b7e501f53d8bf60270401","last_reissued_at":"2026-07-05T08:54:40.252310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:40.252310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers Can Do Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Josif Grabocka, Noah Hollmann, Samuel M\\\"uller, Sebastian Pineda Arango","submitted_at":"2021-12-20T13:07:39Z","abstract_excerpt":"Currently, it is hard to reap the benefits of deep learning for Bayesian methods, which allow the explicit specification of prior knowledge and accurately capture model uncertainty. We present Prior-Data Fitted Networks (PFNs). PFNs leverage in-context learning in large-scale machine learning techniques to approximate a large set of posteriors. The only requirement for PFNs to work is the ability to sample from a prior distribution over supervised learning tasks (or functions). Our method restates the objective of posterior approximation as a supervised classification problem with a set-valued"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10510","kind":"arxiv","version":7},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.10510/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2112.10510","created_at":"2026-07-05T08:54:40.252450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10510v7","created_at":"2026-07-05T08:54:40.252450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10510","created_at":"2026-07-05T08:54:40.252450+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQZIL4JYLUP5","created_at":"2026-07-05T08:54:40.252450+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQZIL4JYLUP5FCKM","created_at":"2026-07-05T08:54:40.252450+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQZIL4JY","created_at":"2026-07-05T08:54:40.252450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07500","citing_title":"TimEE: End-to-end Time Series Classification via In-Context Learning","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25197","citing_title":"Efficient Adaptive Data Acquisition via Pretrained Belief Representations","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24995","citing_title":"Are Tabular Foundation Models Robust to Realistic Query Distribution Shifts in Microbiome Data?","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18677","citing_title":"Bounded Context Management for Tabular Foundation Models on Stream Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18812","citing_title":"Reinforcement Learning Foundation Models Should Already Be A Thing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09664","citing_title":"In-Context Learning for Latent Space Bayesian Optimization","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31208","citing_title":"Probing Memorization of Tabular In-Context Learning","ref_index":181,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06128","citing_title":"Amortized Inference of Causal Models via Conditional Fixed-Point Iterations","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2411.08249","citing_title":"Retrieval Augmented Time Series Forecasting","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21742","citing_title":"Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21544","citing_title":"Tabular foundation models for robust calibration of near-infrared chemical sensing data","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20674","citing_title":"Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18147","citing_title":"Foundation Models for Credit Risk Prediction: A Game Changer?","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15488","citing_title":"SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08977","citing_title":"Simulation as Supervision: Mechanistic Pretraining for Scientific Discovery","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2211.15661","citing_title":"What learning algorithm is in-context learning? Investigations with linear models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12292","citing_title":"STRABLE: Benchmarking Tabular Machine Learning with Strings","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06413","citing_title":"Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07863","citing_title":"ADKO: Agentic Decentralized Knowledge Optimization","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07765","citing_title":"Pre-trained Tabular Foundation Models as Versatile Summary Networks for Neural Posterior Estimation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16123","citing_title":"Tabular foundation models for in-context prediction of molecular properties","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S","json":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S.json","graph_json":"https://pith.science/api/pith-number/HQZIL4JYLUP5FCKMUMTSJSDG2S/graph.json","events_json":"https://pith.science/api/pith-number/HQZIL4JYLUP5FCKMUMTSJSDG2S/events.json","paper":"https://pith.science/paper/HQZIL4JY"},"agent_actions":{"view_html":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S","download_json":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S.json","view_paper":"https://pith.science/paper/HQZIL4JY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10510&json=true","fetch_graph":"https://pith.science/api/pith-number/HQZIL4JYLUP5FCKMUMTSJSDG2S/graph.json","fetch_events":"https://pith.science/api/pith-number/HQZIL4JYLUP5FCKMUMTSJSDG2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S/action/storage_attestation","attest_author":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S/action/author_attestation","sign_citation":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S/action/citation_signature","submit_replication":"https://pith.science/pith/HQZIL4JYLUP5FCKMUMTSJSDG2S/action/replication_record"}},"created_at":"2026-07-05T08:54:40.252450+00:00","updated_at":"2026-07-05T08:54:40.252450+00:00"}