{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QZ7Z6DF52OH6YMKYEGXAZKDXKT","short_pith_number":"pith:QZ7Z6DF5","canonical_record":{"source":{"id":"2605.07565","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T10:37:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"55555a59c29a191171681536ddbadc812f8e357c9157a72e6dbfdb16afbd0f52","abstract_canon_sha256":"83aa20be39455a3173f79c9c4848e27814ad10009b21de0caa9fd851a12e1c95"},"schema_version":"1.0"},"canonical_sha256":"867f9f0cbdd38fec315821ae0ca87754f534744c789fa0f6040b3307e2023b25","source":{"kind":"arxiv","id":"2605.07565","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07565","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07565v2","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07565","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"QZ7Z6DF52OH6","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"QZ7Z6DF52OH6YMKY","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"QZ7Z6DF5","created_at":"2026-06-24T01:15:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QZ7Z6DF52OH6YMKYEGXAZKDXKT","target":"record","payload":{"canonical_record":{"source":{"id":"2605.07565","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T10:37:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"55555a59c29a191171681536ddbadc812f8e357c9157a72e6dbfdb16afbd0f52","abstract_canon_sha256":"83aa20be39455a3173f79c9c4848e27814ad10009b21de0caa9fd851a12e1c95"},"schema_version":"1.0"},"canonical_sha256":"867f9f0cbdd38fec315821ae0ca87754f534744c789fa0f6040b3307e2023b25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:03.667145Z","signature_b64":"EDuiff3pd04IBJ3KGpPkYX7B+E+DLRKMrf2ELG7545bF9Jz8zcIk/PlpRbuxDbRcLGTKuD38Mi65iJ5jOW1eAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"867f9f0cbdd38fec315821ae0ca87754f534744c789fa0f6040b3307e2023b25","last_reissued_at":"2026-06-24T01:15:03.666735Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:03.666735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.07565","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQW/2zGqDWBERHWYprevm8AN4zW/LTNQr2e++HdE8f9Pmp9ttQSQ8TQMdNthFcjVlM2q/13GIwmcSR3g8ZJMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:51:07.318746Z"},"content_sha256":"d4f53b88199eaec7cc7a73a8243804aa24b39a066536d1e751966a4b1e67a17b","schema_version":"1.0","event_id":"sha256:d4f53b88199eaec7cc7a73a8243804aa24b39a066536d1e751966a4b1e67a17b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QZ7Z6DF52OH6YMKYEGXAZKDXKT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A novel algorithm for ensemble distributionally robust Bayesian optimisation stays computationally tractable for continuous contexts and achieves sublinear regret bounds that improve on prior results.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Denis Derkach, Tigran Ramazyan","submitted_at":"2026-05-08T10:37:10Z","abstract_excerpt":"We study Bayesian Optimisation (BO) in settings where the objective function is influenced by uncontrollable environmental contexts governed by an unknown probability distribution. In practice, the contextual distribution must be estimated from empirical data, a process that inherently introduces distributional mismatch, producing sub-optimal results. While Distributionally Robust Optimisation (DRO) provides a framework to mitigate these risks, existing robust BO methods frequently suffer from high computational complexity, rely on discretisation of continuous context spaces, or impose restric"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose a novel algorithm for Ensemble Distributionally Robust Bayesian Optimisation that remains computationally tractable while managing continuous context. We obtain theoretical sublinear regret bounds, improving current state-of-the-art results.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The regret analysis and tractability claims rest on unstated assumptions about the ensemble construction, the form of distributional uncertainty, and the surrogate models; these are not detailed in the abstract and could be violated in practice.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A novel algorithm for ensemble distributionally robust Bayesian optimisation stays computationally tractable for continuous contexts and achieves sublinear regret bounds that improve on prior results.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b214871945de926aa36b6b346cd322a44c82aacfd167caa53747440ef550eca9"},"source":{"id":"2605.07565","kind":"arxiv","version":2},"verdict":{"id":"d07a6185-5790-4b67-87e8-3a1ac0dc9156","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T03:14:59.080494Z","strongest_claim":"We propose a novel algorithm for Ensemble Distributionally Robust Bayesian Optimisation that remains computationally tractable while managing continuous context. We obtain theoretical sublinear regret bounds, improving current state-of-the-art results.","one_line_summary":"A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The regret analysis and tractability claims rest on unstated assumptions about the ensemble construction, the form of distributional uncertainty, and the surrogate models; these are not detailed in the abstract and could be violated in practice.","pith_extraction_headline":"A novel algorithm for ensemble distributionally robust Bayesian optimisation stays computationally tractable for continuous contexts and achieves sublinear regret bounds that improve on prior results."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07565/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T10:42:02.845431Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T05:39:42.473426Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.552695Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:41:47.350140Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"faff3d7bb8e5e420a4b211dc736f484efffb0c12685f214a6aa1d1519f0f8378"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3eefcc49e3b66c21b31cac8a1d89c6777ba201ba45a175ade67cc98925bf630f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d07a6185-5790-4b67-87e8-3a1ac0dc9156"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"anFksL8ABdUZXDcdrvUlebkeQcmIu0HqAqMrM59TYBxJ1JHXw8f5aQrvgeio9p40vcMD/kHvhGcbHFAED1lICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:51:07.319647Z"},"content_sha256":"38ac75a155fcfba16db6e4ef10f3c0af391ab6ff8f7e23e3754c90cbf4d5040a","schema_version":"1.0","event_id":"sha256:38ac75a155fcfba16db6e4ef10f3c0af391ab6ff8f7e23e3754c90cbf4d5040a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZ7Z6DF52OH6YMKYEGXAZKDXKT/bundle.json","state_url":"https://pith.science/pith/QZ7Z6DF52OH6YMKYEGXAZKDXKT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZ7Z6DF52OH6YMKYEGXAZKDXKT/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":"2026-08-06T05:51:07Z","links":{"resolver":"https://pith.science/pith/QZ7Z6DF52OH6YMKYEGXAZKDXKT","bundle":"https://pith.science/pith/QZ7Z6DF52OH6YMKYEGXAZKDXKT/bundle.json","state":"https://pith.science/pith/QZ7Z6DF52OH6YMKYEGXAZKDXKT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZ7Z6DF52OH6YMKYEGXAZKDXKT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QZ7Z6DF52OH6YMKYEGXAZKDXKT","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":"83aa20be39455a3173f79c9c4848e27814ad10009b21de0caa9fd851a12e1c95","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T10:37:10Z","title_canon_sha256":"55555a59c29a191171681536ddbadc812f8e357c9157a72e6dbfdb16afbd0f52"},"schema_version":"1.0","source":{"id":"2605.07565","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07565","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07565v2","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07565","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"QZ7Z6DF52OH6","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"QZ7Z6DF52OH6YMKY","created_at":"2026-06-24T01:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"QZ7Z6DF5","created_at":"2026-06-24T01:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:38ac75a155fcfba16db6e4ef10f3c0af391ab6ff8f7e23e3754c90cbf4d5040a","target":"graph","created_at":"2026-06-24T01:15:03Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We propose a novel algorithm for Ensemble Distributionally Robust Bayesian Optimisation that remains computationally tractable while managing continuous context. We obtain theoretical sublinear regret bounds, improving current state-of-the-art results."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The regret analysis and tractability claims rest on unstated assumptions about the ensemble construction, the form of distributional uncertainty, and the surrogate models; these are not detailed in the abstract and could be violated in practice."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A novel algorithm for ensemble distributionally robust Bayesian optimisation stays computationally tractable for continuous contexts and achieves sublinear regret bounds that improve on prior results."}],"snapshot_sha256":"b214871945de926aa36b6b346cd322a44c82aacfd167caa53747440ef550eca9"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3eefcc49e3b66c21b31cac8a1d89c6777ba201ba45a175ade67cc98925bf630f"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T10:42:02.845431Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T05:39:42.473426Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.552695Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T11:41:47.350140Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.07565/integrity.json","findings":[],"snapshot_sha256":"faff3d7bb8e5e420a4b211dc736f484efffb0c12685f214a6aa1d1519f0f8378","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study Bayesian Optimisation (BO) in settings where the objective function is influenced by uncontrollable environmental contexts governed by an unknown probability distribution. In practice, the contextual distribution must be estimated from empirical data, a process that inherently introduces distributional mismatch, producing sub-optimal results. While Distributionally Robust Optimisation (DRO) provides a framework to mitigate these risks, existing robust BO methods frequently suffer from high computational complexity, rely on discretisation of continuous context spaces, or impose restric","authors_text":"Denis Derkach, Tigran Ramazyan","cross_cats":["cs.AI","stat.ML"],"headline":"A novel algorithm for ensemble distributionally robust Bayesian optimisation stays computationally tractable for continuous contexts and achieves sublinear regret bounds that improve on prior results.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T10:37:10Z","title":"Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.07565","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T03:14:59.080494Z","id":"d07a6185-5790-4b67-87e8-3a1ac0dc9156","model_set":{"reader":"grok-4.3"},"one_line_summary":"A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A novel algorithm for ensemble distributionally robust Bayesian optimisation stays computationally tractable for continuous contexts and achieves sublinear regret bounds that improve on prior results.","strongest_claim":"We propose a novel algorithm for Ensemble Distributionally Robust Bayesian Optimisation that remains computationally tractable while managing continuous context. We obtain theoretical sublinear regret bounds, improving current state-of-the-art results.","weakest_assumption":"The regret analysis and tractability claims rest on unstated assumptions about the ensemble construction, the form of distributional uncertainty, and the surrogate models; these are not detailed in the abstract and could be violated in practice."}},"verdict_id":"d07a6185-5790-4b67-87e8-3a1ac0dc9156"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d4f53b88199eaec7cc7a73a8243804aa24b39a066536d1e751966a4b1e67a17b","target":"record","created_at":"2026-06-24T01:15:03Z","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":"83aa20be39455a3173f79c9c4848e27814ad10009b21de0caa9fd851a12e1c95","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T10:37:10Z","title_canon_sha256":"55555a59c29a191171681536ddbadc812f8e357c9157a72e6dbfdb16afbd0f52"},"schema_version":"1.0","source":{"id":"2605.07565","kind":"arxiv","version":2}},"canonical_sha256":"867f9f0cbdd38fec315821ae0ca87754f534744c789fa0f6040b3307e2023b25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"867f9f0cbdd38fec315821ae0ca87754f534744c789fa0f6040b3307e2023b25","first_computed_at":"2026-06-24T01:15:03.666735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:03.666735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EDuiff3pd04IBJ3KGpPkYX7B+E+DLRKMrf2ELG7545bF9Jz8zcIk/PlpRbuxDbRcLGTKuD38Mi65iJ5jOW1eAw==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:03.667145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.07565","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4f53b88199eaec7cc7a73a8243804aa24b39a066536d1e751966a4b1e67a17b","sha256:38ac75a155fcfba16db6e4ef10f3c0af391ab6ff8f7e23e3754c90cbf4d5040a"],"state_sha256":"e6eba86930ebcbe5ac7bc582112ae97a5ebaab74f8c774fde2cb66e4e4d84287"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdThALCFgwMCrtdo+YZJ+RfnY+syF2OjPy8BS8xDIpJbjmpQHGDfoLT4JW7m3WqJvHnLrbLbR/n5E7QmdYK3Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:51:07.323541Z","bundle_sha256":"81f1c47116abf339817964955add8774fbabd9a52c31e5fad27f53f1f13b47b2"}}