{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VCVEC7BCHOEZ5TRL4X4EOCYF35","short_pith_number":"pith:VCVEC7BC","schema_version":"1.0","canonical_sha256":"a8aa417c223b899ece2be5f8470b05df483720984311e5ba3cb5c61fc588b1ef","source":{"kind":"arxiv","id":"2606.07134","version":1},"attestation_state":"computed","paper":{"title":"$\\alpha$-PFN: Fast Entropy Search via In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carl Hvarfner, Eytan Bakshy, Frank Hutter, Herilalaina Rakotoarison, Samuel M\\\"uller, Steven Adriaensen, Tom Viering","submitted_at":"2026-06-05T10:45:49Z","abstract_excerpt":"Information-theoretic acquisition functions such as Entropy Search (ES) offer a principled exploration-exploitation framework for Bayesian optimization (BO). However, their practical implementation relies on complicated and slow approximations, i.e., a Monte Carlo estimation of the information gain. This complexity can introduce numerical errors and requires specialized, hand-crafted implementations. We propose a two-stage amortization strategy that learns to approximate entropy search-based acquisition functions using Prior-data Fitted Networks (PFNs) in a single forward pass. A first PFN is "},"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":"2606.07134","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T10:45:49Z","cross_cats_sorted":[],"title_canon_sha256":"9b69d6fcee01e15439674ed4c8d4932a5237c3a619288fe084ef29a63f4ef04b","abstract_canon_sha256":"f23de5656be5a2221c738808a43340a3f368d2c9b94e9fc4e306c13fc6b615af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:48.486911Z","signature_b64":"0f2FMHXxay4q7OJbvtkBzuuMLrRL7PsJLzz0CPrkjhA0Jztnw40qi/f7H7ifJEAm7AXs3TsrFC5YseSuiMbtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8aa417c223b899ece2be5f8470b05df483720984311e5ba3cb5c61fc588b1ef","last_reissued_at":"2026-06-08T01:04:48.486043Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:48.486043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\alpha$-PFN: Fast Entropy Search via In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carl Hvarfner, Eytan Bakshy, Frank Hutter, Herilalaina Rakotoarison, Samuel M\\\"uller, Steven Adriaensen, Tom Viering","submitted_at":"2026-06-05T10:45:49Z","abstract_excerpt":"Information-theoretic acquisition functions such as Entropy Search (ES) offer a principled exploration-exploitation framework for Bayesian optimization (BO). However, their practical implementation relies on complicated and slow approximations, i.e., a Monte Carlo estimation of the information gain. This complexity can introduce numerical errors and requires specialized, hand-crafted implementations. We propose a two-stage amortization strategy that learns to approximate entropy search-based acquisition functions using Prior-data Fitted Networks (PFNs) in a single forward pass. A first PFN is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07134","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/2606.07134/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":"2606.07134","created_at":"2026-06-08T01:04:48.486176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07134v1","created_at":"2026-06-08T01:04:48.486176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07134","created_at":"2026-06-08T01:04:48.486176+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCVEC7BCHOEZ","created_at":"2026-06-08T01:04:48.486176+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCVEC7BCHOEZ5TRL","created_at":"2026-06-08T01:04:48.486176+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCVEC7BC","created_at":"2026-06-08T01:04:48.486176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35","json":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35.json","graph_json":"https://pith.science/api/pith-number/VCVEC7BCHOEZ5TRL4X4EOCYF35/graph.json","events_json":"https://pith.science/api/pith-number/VCVEC7BCHOEZ5TRL4X4EOCYF35/events.json","paper":"https://pith.science/paper/VCVEC7BC"},"agent_actions":{"view_html":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35","download_json":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35.json","view_paper":"https://pith.science/paper/VCVEC7BC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07134&json=true","fetch_graph":"https://pith.science/api/pith-number/VCVEC7BCHOEZ5TRL4X4EOCYF35/graph.json","fetch_events":"https://pith.science/api/pith-number/VCVEC7BCHOEZ5TRL4X4EOCYF35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35/action/storage_attestation","attest_author":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35/action/author_attestation","sign_citation":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35/action/citation_signature","submit_replication":"https://pith.science/pith/VCVEC7BCHOEZ5TRL4X4EOCYF35/action/replication_record"}},"created_at":"2026-06-08T01:04:48.486176+00:00","updated_at":"2026-06-08T01:04:48.486176+00:00"}