{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RMH725E7JABADHIU2FHHCE42TG","short_pith_number":"pith:RMH725E7","canonical_record":{"source":{"id":"1811.09558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-23T16:54:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"590719dd7fb3dc84d00328315811a1b0c1baad8826cdd1704c0579e59c8a736d","abstract_canon_sha256":"5f22dbb3c7396934cb0180269f7f0a140d923cd692678ba0c6bfa955f2459e58"},"schema_version":"1.0"},"canonical_sha256":"8b0ffd749f4802019d14d14e71139a99bd681032d3b4ddfa4371d2d38a102f2b","source":{"kind":"arxiv","id":"1811.09558","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.09558","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.09558v1","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09558","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"RMH725E7JABA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RMH725E7JABADHIU","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RMH725E7","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RMH725E7JABADHIU2FHHCE42TG","target":"record","payload":{"canonical_record":{"source":{"id":"1811.09558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-23T16:54:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"590719dd7fb3dc84d00328315811a1b0c1baad8826cdd1704c0579e59c8a736d","abstract_canon_sha256":"5f22dbb3c7396934cb0180269f7f0a140d923cd692678ba0c6bfa955f2459e58"},"schema_version":"1.0"},"canonical_sha256":"8b0ffd749f4802019d14d14e71139a99bd681032d3b4ddfa4371d2d38a102f2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:03.057455Z","signature_b64":"zO+9p9QaGClgibD0eYt1jbUmnt3q/gv3zyGuY/H34KFL1za/OadE7Z9Lt7RIHOsicj8W3qI0WpFCOjRanTnJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b0ffd749f4802019d14d14e71139a99bd681032d3b4ddfa4371d2d38a102f2b","last_reissued_at":"2026-05-18T00:00:03.057031Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:03.057031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.09558","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJg1OjscXGwtxzap2sDZBgrWG1FvfEj7i7u1I7tms4aqFJFjeFXcN6S4cL//IxhpFX8XuxjddrXbxIcXthXkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:21:28.709032Z"},"content_sha256":"36fe3ae216a520daac63c16e06280d03f756cb3d5c11806fecf2b89cab1217dc","schema_version":"1.0","event_id":"sha256:36fe3ae216a520daac63c16e06280d03f756cb3d5c11806fecf2b89cab1217dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RMH725E7JABADHIU2FHHCE42TG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Beomjoon Kim, Leslie Pack Kaelbling, Zi Wang","submitted_at":"2018-11-23T16:54:45Z","abstract_excerpt":"Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussian process prior from offline data sampled from the same prior and constructing unbiased estimators of the posterior, variants of both GP-UCB and probability of improvement achieve a near-zero regret bound, which decreases to a constant proportional to the observational noise as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09558","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9wdSI9Q7tMvgJx3a2DAOWHY1rTw0InuHAm0T/EIebIwDWlaoVkiT0wH2R7416JwiL4iNq7snRgJrpphMmGgDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:21:28.709725Z"},"content_sha256":"d15e6afcb4a2336cbbca8a0afa3cf0ba58bcb249e038d3b3f71f180cb472f493","schema_version":"1.0","event_id":"sha256:d15e6afcb4a2336cbbca8a0afa3cf0ba58bcb249e038d3b3f71f180cb472f493"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMH725E7JABADHIU2FHHCE42TG/bundle.json","state_url":"https://pith.science/pith/RMH725E7JABADHIU2FHHCE42TG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMH725E7JABADHIU2FHHCE42TG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T17:21:28Z","links":{"resolver":"https://pith.science/pith/RMH725E7JABADHIU2FHHCE42TG","bundle":"https://pith.science/pith/RMH725E7JABADHIU2FHHCE42TG/bundle.json","state":"https://pith.science/pith/RMH725E7JABADHIU2FHHCE42TG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMH725E7JABADHIU2FHHCE42TG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RMH725E7JABADHIU2FHHCE42TG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5f22dbb3c7396934cb0180269f7f0a140d923cd692678ba0c6bfa955f2459e58","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-23T16:54:45Z","title_canon_sha256":"590719dd7fb3dc84d00328315811a1b0c1baad8826cdd1704c0579e59c8a736d"},"schema_version":"1.0","source":{"id":"1811.09558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.09558","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.09558v1","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09558","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"RMH725E7JABA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RMH725E7JABADHIU","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RMH725E7","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:d15e6afcb4a2336cbbca8a0afa3cf0ba58bcb249e038d3b3f71f180cb472f493","target":"graph","created_at":"2026-05-18T00:00:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussian process prior from offline data sampled from the same prior and constructing unbiased estimators of the posterior, variants of both GP-UCB and probability of improvement achieve a near-zero regret bound, which decreases to a constant proportional to the observational noise as ","authors_text":"Beomjoon Kim, Leslie Pack Kaelbling, Zi Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-23T16:54:45Z","title":"Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09558","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:36fe3ae216a520daac63c16e06280d03f756cb3d5c11806fecf2b89cab1217dc","target":"record","created_at":"2026-05-18T00:00:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5f22dbb3c7396934cb0180269f7f0a140d923cd692678ba0c6bfa955f2459e58","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-23T16:54:45Z","title_canon_sha256":"590719dd7fb3dc84d00328315811a1b0c1baad8826cdd1704c0579e59c8a736d"},"schema_version":"1.0","source":{"id":"1811.09558","kind":"arxiv","version":1}},"canonical_sha256":"8b0ffd749f4802019d14d14e71139a99bd681032d3b4ddfa4371d2d38a102f2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b0ffd749f4802019d14d14e71139a99bd681032d3b4ddfa4371d2d38a102f2b","first_computed_at":"2026-05-18T00:00:03.057031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:03.057031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zO+9p9QaGClgibD0eYt1jbUmnt3q/gv3zyGuY/H34KFL1za/OadE7Z9Lt7RIHOsicj8W3qI0WpFCOjRanTnJCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:03.057455Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.09558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36fe3ae216a520daac63c16e06280d03f756cb3d5c11806fecf2b89cab1217dc","sha256:d15e6afcb4a2336cbbca8a0afa3cf0ba58bcb249e038d3b3f71f180cb472f493"],"state_sha256":"969204929211e0aab8334103cffaff17decdd03eb6efbf95b265fd8e833db45c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+eowO1+59mTKTrYG65j2LpXqiqLDTVILdKwc1dYs4sXA8CHkko0E89Ev7CmS27O66H7yyiU5GuAje5i0DBTBDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T17:21:28.713146Z","bundle_sha256":"a4aa58a4b34080ee7b0fef342ed81fa808d1bf6411791cf2d8cacbc03ea6a8c9"}}