{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YJTEI7L7TDIZ26GC6RWQ4OECSD","short_pith_number":"pith:YJTEI7L7","schema_version":"1.0","canonical_sha256":"c266447d7f98d19d78c2f46d0e388290f06c749c9b3d3591a2142c2c8e08c8f8","source":{"kind":"arxiv","id":"2505.23947","version":1},"attestation_state":"computed","paper":{"title":"Position: The Future of Bayesian Prediction Is Prior-Fitted","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arik Reuter, David R\\\"ugamer, Frank Hutter, Noah Hollmann, Samuel M\\\"uller","submitted_at":"2025-05-29T18:56:45Z","abstract_excerpt":"Training neural networks on randomly generated artificial datasets yields Bayesian models that capture the prior defined by the dataset-generating distribution. Prior-data Fitted Networks (PFNs) are a class of methods designed to leverage this insight. In an era of rapidly increasing computational resources for pre-training and a near stagnation in the generation of new real-world data in many applications, PFNs are poised to play a more important role across a wide range of applications. They enable the efficient allocation of pre-training compute to low-data scenarios. Originally applied to "},"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":"2505.23947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T18:56:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cab7fe459595466834dd06eecbfefa20ea7d12f72baee495d1a58f5160853aa4","abstract_canon_sha256":"5392908675e1647a89441e5fc4ca9e7f2f876a8d735d9362faea5590d51f9108"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:38.849103Z","signature_b64":"Jzzv1As6rTbfR8/QmD03HE0ju0g0gZoboPrHH49f4ERevJDyHt/6mPx/7KdcPt0iQFftukq78d6TqsfWO5PXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c266447d7f98d19d78c2f46d0e388290f06c749c9b3d3591a2142c2c8e08c8f8","last_reissued_at":"2026-07-05T11:12:38.848608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:38.848608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: The Future of Bayesian Prediction Is Prior-Fitted","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arik Reuter, David R\\\"ugamer, Frank Hutter, Noah Hollmann, Samuel M\\\"uller","submitted_at":"2025-05-29T18:56:45Z","abstract_excerpt":"Training neural networks on randomly generated artificial datasets yields Bayesian models that capture the prior defined by the dataset-generating distribution. Prior-data Fitted Networks (PFNs) are a class of methods designed to leverage this insight. In an era of rapidly increasing computational resources for pre-training and a near stagnation in the generation of new real-world data in many applications, PFNs are poised to play a more important role across a wide range of applications. They enable the efficient allocation of pre-training compute to low-data scenarios. Originally applied to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23947","kind":"arxiv","version":1},"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/2505.23947/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":"2505.23947","created_at":"2026-07-05T11:12:38.848669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23947v1","created_at":"2026-07-05T11:12:38.848669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23947","created_at":"2026-07-05T11:12:38.848669+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJTEI7L7TDIZ","created_at":"2026-07-05T11:12:38.848669+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJTEI7L7TDIZ26GC","created_at":"2026-07-05T11:12:38.848669+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJTEI7L7","created_at":"2026-07-05T11:12:38.848669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18812","citing_title":"Reinforcement Learning Foundation Models Should Already Be A Thing","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09664","citing_title":"In-Context Learning for Latent Space Bayesian Optimization","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15488","citing_title":"SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD","json":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD.json","graph_json":"https://pith.science/api/pith-number/YJTEI7L7TDIZ26GC6RWQ4OECSD/graph.json","events_json":"https://pith.science/api/pith-number/YJTEI7L7TDIZ26GC6RWQ4OECSD/events.json","paper":"https://pith.science/paper/YJTEI7L7"},"agent_actions":{"view_html":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD","download_json":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD.json","view_paper":"https://pith.science/paper/YJTEI7L7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23947&json=true","fetch_graph":"https://pith.science/api/pith-number/YJTEI7L7TDIZ26GC6RWQ4OECSD/graph.json","fetch_events":"https://pith.science/api/pith-number/YJTEI7L7TDIZ26GC6RWQ4OECSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD/action/storage_attestation","attest_author":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD/action/author_attestation","sign_citation":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD/action/citation_signature","submit_replication":"https://pith.science/pith/YJTEI7L7TDIZ26GC6RWQ4OECSD/action/replication_record"}},"created_at":"2026-07-05T11:12:38.848669+00:00","updated_at":"2026-07-05T11:12:38.848669+00:00"}