{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2009:X4UPYDYH65LYXXPBHU35KTVQRO","short_pith_number":"pith:X4UPYDYH","canonical_record":{"source":{"id":"0912.3995","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-21T00:08:19Z","cross_cats_sorted":[],"title_canon_sha256":"adb4c26ea869a338a06efb991f4cec5780cfd1b6f5dc4df32c544508cce4df67","abstract_canon_sha256":"e1302309bb547973eb39a67c7707d91f57262f923b480f7c12b1e5faa83c0d93"},"schema_version":"1.0"},"canonical_sha256":"bf28fc0f07f7578bdde13d37d54eb08b8fc7df4005f3190d1055878d145b5b27","source":{"kind":"arxiv","id":"0912.3995","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0912.3995","created_at":"2026-05-18T02:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"0912.3995v4","created_at":"2026-05-18T02:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0912.3995","created_at":"2026-05-18T02:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"X4UPYDYH65LY","created_at":"2026-05-18T12:26:02Z"},{"alias_kind":"pith_short_16","alias_value":"X4UPYDYH65LYXXPB","created_at":"2026-05-18T12:26:02Z"},{"alias_kind":"pith_short_8","alias_value":"X4UPYDYH","created_at":"2026-05-18T12:26:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2009:X4UPYDYH65LYXXPBHU35KTVQRO","target":"record","payload":{"canonical_record":{"source":{"id":"0912.3995","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-21T00:08:19Z","cross_cats_sorted":[],"title_canon_sha256":"adb4c26ea869a338a06efb991f4cec5780cfd1b6f5dc4df32c544508cce4df67","abstract_canon_sha256":"e1302309bb547973eb39a67c7707d91f57262f923b480f7c12b1e5faa83c0d93"},"schema_version":"1.0"},"canonical_sha256":"bf28fc0f07f7578bdde13d37d54eb08b8fc7df4005f3190d1055878d145b5b27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:24:45.583110Z","signature_b64":"czoBsp+s9gv/zWPPT2cmrDL0UAajnq/jIYrI0jOwhmawp+upAo7ZfktT4tYPNTA6/Mr9PSdSCBICYUFL5lFUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf28fc0f07f7578bdde13d37d54eb08b8fc7df4005f3190d1055878d145b5b27","last_reissued_at":"2026-05-18T02:24:45.582629Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:24:45.582629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"0912.3995","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:24:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dV9TMxtwC5fLVrDEQBYL5xPBkGIqKaMlv6P5yWdLo3E0YGx8RCX8/2+UXhMYZ/I3CcXr1vx1u5ofrUyUWsRNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:09:34.178829Z"},"content_sha256":"03164af5e620b39079cd6b08e15fd3e7155f68017a99727d4def4e71ff89afbc","schema_version":"1.0","event_id":"sha256:03164af5e620b39079cd6b08e15fd3e7155f68017a99727d4def4e71ff89afbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2009:X4UPYDYH65LYXXPBHU35KTVQRO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Matthias Seeger, Niranjan Srinivas, Sham M. Kakade","submitted_at":"2009-12-21T00:08:19Z","abstract_excerpt":"Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS norm. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0912.3995","kind":"arxiv","version":4},"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":"2026-05-18T02:24:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pazJPN4rlZten8cq4jZOt9OooG31jYkfXH6LftdJp1LLw9ZQQrUV8ARR09ZtW5lKtWXQUk6V+ZdN0G2HVYQYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:09:34.179485Z"},"content_sha256":"f70a56f5f7d0fb9241e1f4cd40f58cb71693cff7e082285616fb459457a3ea41","schema_version":"1.0","event_id":"sha256:f70a56f5f7d0fb9241e1f4cd40f58cb71693cff7e082285616fb459457a3ea41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/bundle.json","state_url":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4UPYDYH65LYXXPBHU35KTVQRO/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":"2026-05-26T23:09:34Z","links":{"resolver":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO","bundle":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/bundle.json","state":"https://pith.science/pith/X4UPYDYH65LYXXPBHU35KTVQRO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4UPYDYH65LYXXPBHU35KTVQRO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2009:X4UPYDYH65LYXXPBHU35KTVQRO","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":"e1302309bb547973eb39a67c7707d91f57262f923b480f7c12b1e5faa83c0d93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-21T00:08:19Z","title_canon_sha256":"adb4c26ea869a338a06efb991f4cec5780cfd1b6f5dc4df32c544508cce4df67"},"schema_version":"1.0","source":{"id":"0912.3995","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0912.3995","created_at":"2026-05-18T02:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"0912.3995v4","created_at":"2026-05-18T02:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0912.3995","created_at":"2026-05-18T02:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"X4UPYDYH65LY","created_at":"2026-05-18T12:26:02Z"},{"alias_kind":"pith_short_16","alias_value":"X4UPYDYH65LYXXPB","created_at":"2026-05-18T12:26:02Z"},{"alias_kind":"pith_short_8","alias_value":"X4UPYDYH","created_at":"2026-05-18T12:26:02Z"}],"graph_snapshots":[{"event_id":"sha256:f70a56f5f7d0fb9241e1f4cd40f58cb71693cff7e082285616fb459457a3ea41","target":"graph","created_at":"2026-05-18T02:24:45Z","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":"Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS norm. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design","authors_text":"Andreas Krause, Matthias Seeger, Niranjan Srinivas, Sham M. Kakade","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-21T00:08:19Z","title":"Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0912.3995","kind":"arxiv","version":4},"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":"sha256:03164af5e620b39079cd6b08e15fd3e7155f68017a99727d4def4e71ff89afbc","target":"record","created_at":"2026-05-18T02:24:45Z","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":"e1302309bb547973eb39a67c7707d91f57262f923b480f7c12b1e5faa83c0d93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-21T00:08:19Z","title_canon_sha256":"adb4c26ea869a338a06efb991f4cec5780cfd1b6f5dc4df32c544508cce4df67"},"schema_version":"1.0","source":{"id":"0912.3995","kind":"arxiv","version":4}},"canonical_sha256":"bf28fc0f07f7578bdde13d37d54eb08b8fc7df4005f3190d1055878d145b5b27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf28fc0f07f7578bdde13d37d54eb08b8fc7df4005f3190d1055878d145b5b27","first_computed_at":"2026-05-18T02:24:45.582629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:24:45.582629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"czoBsp+s9gv/zWPPT2cmrDL0UAajnq/jIYrI0jOwhmawp+upAo7ZfktT4tYPNTA6/Mr9PSdSCBICYUFL5lFUCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:24:45.583110Z","signed_message":"canonical_sha256_bytes"},"source_id":"0912.3995","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03164af5e620b39079cd6b08e15fd3e7155f68017a99727d4def4e71ff89afbc","sha256:f70a56f5f7d0fb9241e1f4cd40f58cb71693cff7e082285616fb459457a3ea41"],"state_sha256":"a30126428acdffbea4b4e8e0bf4c5060cffcf3153934537a77c2540efb566584"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z9apEUsgSEiwKs71dKMvTJMPHzXq3Czm0MGHbUDJ5ddD/l3l2xVc2TvN23LczJyOlgjGtqTYQZdlkbvlQQplCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T23:09:34.183944Z","bundle_sha256":"72e6a663c89cd9f8eed4d599739ab084f8de33d53455ae882b200a0c7916e23e"}}