{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PMOQ4BVK5L5SNPV3XHHZBTFZPW","short_pith_number":"pith:PMOQ4BVK","schema_version":"1.0","canonical_sha256":"7b1d0e06aaeafb26bebbb9cf90ccb97d8d0e167d4768aa24f7844464dfc9f037","source":{"kind":"arxiv","id":"2305.11097","version":1},"attestation_state":"computed","paper":{"title":"Statistical Foundations of Prior-Data Fitted Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Thomas Nagler","submitted_at":"2023-05-18T16:34:21Z","abstract_excerpt":"Prior-data fitted networks (PFNs) were recently proposed as a new paradigm for machine learning. Instead of training the network to an observed training set, a fixed model is pre-trained offline on small, simulated training sets from a variety of tasks. The pre-trained model is then used to infer class probabilities in-context on fresh training sets with arbitrary size and distribution. Empirically, PFNs achieve state-of-the-art performance on tasks with similar size to the ones used in pre-training. Surprisingly, their accuracy further improves when passed larger data sets during inference. T"},"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":"2305.11097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-18T16:34:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16619f9e4368cb61eefa2157b2f5307fc1f3e88a62d96abc89d52dc80adc0eae","abstract_canon_sha256":"75dc4a8ef60e74e5c51a6b23163f6a3c5843f13599db6b3797c1c06a1126c7b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:30.367392Z","signature_b64":"9w/POS5Q2DiFvROQUmjmL/0GfJNt5Ngukzv1WYChMwrz7EsazZ5IpeCm9zU6T3cugpNGdhy6OkIqnBBTyUurCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b1d0e06aaeafb26bebbb9cf90ccb97d8d0e167d4768aa24f7844464dfc9f037","last_reissued_at":"2026-07-05T06:11:30.366945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:30.366945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Foundations of Prior-Data Fitted Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Thomas Nagler","submitted_at":"2023-05-18T16:34:21Z","abstract_excerpt":"Prior-data fitted networks (PFNs) were recently proposed as a new paradigm for machine learning. Instead of training the network to an observed training set, a fixed model is pre-trained offline on small, simulated training sets from a variety of tasks. The pre-trained model is then used to infer class probabilities in-context on fresh training sets with arbitrary size and distribution. Empirically, PFNs achieve state-of-the-art performance on tasks with similar size to the ones used in pre-training. Surprisingly, their accuracy further improves when passed larger data sets during inference. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11097","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/2305.11097/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":"2305.11097","created_at":"2026-07-05T06:11:30.366998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11097v1","created_at":"2026-07-05T06:11:30.366998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11097","created_at":"2026-07-05T06:11:30.366998+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMOQ4BVK5L5S","created_at":"2026-07-05T06:11:30.366998+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMOQ4BVK5L5SNPV3","created_at":"2026-07-05T06:11:30.366998+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMOQ4BVK","created_at":"2026-07-05T06:11:30.366998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10590","citing_title":"Amortizing Causal Sensitivity Analysis via Prior Data-Fitted Networks","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW","json":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW.json","graph_json":"https://pith.science/api/pith-number/PMOQ4BVK5L5SNPV3XHHZBTFZPW/graph.json","events_json":"https://pith.science/api/pith-number/PMOQ4BVK5L5SNPV3XHHZBTFZPW/events.json","paper":"https://pith.science/paper/PMOQ4BVK"},"agent_actions":{"view_html":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW","download_json":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW.json","view_paper":"https://pith.science/paper/PMOQ4BVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11097&json=true","fetch_graph":"https://pith.science/api/pith-number/PMOQ4BVK5L5SNPV3XHHZBTFZPW/graph.json","fetch_events":"https://pith.science/api/pith-number/PMOQ4BVK5L5SNPV3XHHZBTFZPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW/action/storage_attestation","attest_author":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW/action/author_attestation","sign_citation":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW/action/citation_signature","submit_replication":"https://pith.science/pith/PMOQ4BVK5L5SNPV3XHHZBTFZPW/action/replication_record"}},"created_at":"2026-07-05T06:11:30.366998+00:00","updated_at":"2026-07-05T06:11:30.366998+00:00"}