{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Y2TLRLELJAS7P6FWPCQWHASXR7","short_pith_number":"pith:Y2TLRLEL","canonical_record":{"source":{"id":"1807.02811","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-08T13:06:26Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"9159c215c228d4f2f4a272fa1e1e27fe7c4db68eea975dd95b9864614368fcf9","abstract_canon_sha256":"85f042f5376ce92a90d01f095623e3ff4dec0a068769ff7841ba8e1b771d9436"},"schema_version":"1.0"},"canonical_sha256":"c6a6b8ac8b4825f7f8b678a16382578ff4fccc0b5ad990dd263275c7f2e8405b","source":{"kind":"arxiv","id":"1807.02811","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.02811","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"arxiv_version","alias_value":"1807.02811v1","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02811","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"pith_short_12","alias_value":"Y2TLRLELJAS7","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"pith_short_16","alias_value":"Y2TLRLELJAS7P6FW","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"pith_short_8","alias_value":"Y2TLRLEL","created_at":"2026-07-04T22:53:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Y2TLRLELJAS7P6FWPCQWHASXR7","target":"record","payload":{"canonical_record":{"source":{"id":"1807.02811","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-08T13:06:26Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"9159c215c228d4f2f4a272fa1e1e27fe7c4db68eea975dd95b9864614368fcf9","abstract_canon_sha256":"85f042f5376ce92a90d01f095623e3ff4dec0a068769ff7841ba8e1b771d9436"},"schema_version":"1.0"},"canonical_sha256":"c6a6b8ac8b4825f7f8b678a16382578ff4fccc0b5ad990dd263275c7f2e8405b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T22:53:53.807916Z","signature_b64":"mcaIlyD2qm6IaM/VoCPUJrWISOc/7cZ7fdorVrHorfPz70imxYqYaoKfIDg6BqbckeRULzGowOX3G30bzgZxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6a6b8ac8b4825f7f8b678a16382578ff4fccc0b5ad990dd263275c7f2e8405b","last_reissued_at":"2026-07-04T22:53:53.807374Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T22:53:53.807374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.02811","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":"2026-07-04T22:53:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yeZ6mHfwketVMfhIiDO/ERpAzoqZ9ypkB4JlfXPbVLNVJkTf8CBwBW2zRITZLI6WX4BJdLNxOdtkuRjceLDmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:54:52.674194Z"},"content_sha256":"abe3c583b249dab42cabacf2f7fd1fd51890e6f7ffdc2d714073aa79f661963b","schema_version":"1.0","event_id":"sha256:abe3c583b249dab42cabacf2f7fd1fd51890e6f7ffdc2d714073aa79f661963b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Y2TLRLELJAS7P6FWPCQWHASXR7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Tutorial on Bayesian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Bayesian optimization builds a Gaussian process surrogate for an expensive objective and uses an acquisition function to choose each next evaluation point.","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Peter I. Frazier","submitted_at":"2018-07-08T13:06:26Z","abstract_excerpt":"Bayesian optimization is an approach to optimizing objective functions that take a long time (minutes or hours) to evaluate. It is best-suited for optimization over continuous domains of less than 20 dimensions, and tolerates stochastic noise in function evaluations. It builds a surrogate for the objective and quantifies the uncertainty in that surrogate using a Bayesian machine learning technique, Gaussian process regression, and then uses an acquisition function defined from this surrogate to decide where to sample. In this tutorial, we describe how Bayesian optimization works, including Gau"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We provide a generalization of expected improvement to noisy evaluations, justified by a formal decision-theoretic argument, standing in contrast to previous ad hoc modifications.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The tutorial assumes that a Gaussian process provides an adequate surrogate model for the objective function and that the reader has sufficient background in Bayesian methods and Gaussian processes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Bayesian optimization uses Gaussian process regression to build a surrogate model and acquisition functions to guide sampling for optimizing costly objective functions, including a new formal generalization of expected improvement to noisy evaluations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Bayesian optimization builds a Gaussian process surrogate for an expensive objective and uses an acquisition function to choose each next evaluation point.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"56842bd2672bf678e2d85168199b6b51317b4b5a4c770ca0dd44e980c6c9e688"},"source":{"id":"1807.02811","kind":"arxiv","version":1},"verdict":{"id":"d2611f24-f700-4b86-a532-32295201701d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T14:12:39.323428Z","strongest_claim":"We provide a generalization of expected improvement to noisy evaluations, justified by a formal decision-theoretic argument, standing in contrast to previous ad hoc modifications.","one_line_summary":"Bayesian optimization uses Gaussian process regression to build a surrogate model and acquisition functions to guide sampling for optimizing costly objective functions, including a new formal generalization of expected improvement to noisy evaluations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The tutorial assumes that a Gaussian process provides an adequate surrogate model for the objective function and that the reader has sufficient background in Bayesian methods and Gaussian processes.","pith_extraction_headline":"Bayesian optimization builds a Gaussian process surrogate for an expensive objective and uses an acquisition function to choose each next evaluation point."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1807.02811/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":101,"sample":[{"doi":"","year":2016,"title":"O., Shahriari, B., and Schmidt, M","work_id":"cc143d0e-dfbe-402e-a2bb-9b27b6591cc3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Berger, J. O. (2013). Statistical Decision Theory and Bayesian Analysis . Springer Science & Business Media","work_id":"4c6e7a1b-f6ad-4c90-bb19-e7aac5c6e815","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1954,"title":"Blum, J. R. (1954). Multidimensional stochastic approximation methods. The Annals of Mathematical Statistics , pages 737--744","work_id":"d83fc444-3a13-4ef9-b289-cabae357f8ba","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1999,"title":"Booker, A., Dennis, J., Frank, P., Serafini, D., Torczon, V., and Trosset, M. (1999). A rigorous framework for optimization of expensive functions by surrogates . Structural and Multidisciplinary Opti","work_id":"c86e3966-3e0d-475a-ac15-c5c25232bb89","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"Bottou, L. (2012). Stochastic gradient descent tricks. In Montavon, G., Orr, G. B., and M \\\"u ller, K. R., editors, Neural Networks: Tricks of the Trade , pages 421--436. Springer","work_id":"35c07c29-944d-45a0-9b53-7a1edb7d2279","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":101,"snapshot_sha256":"256b78b9b1377205ef2a4d85f1856f0727bb958298e1abd58660bb5f4d0e5ad2","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"64fac19c9faaa72c0dce660d8c954e0a2855b9cca1f57e2c8b06d95b9acd30c7"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d2611f24-f700-4b86-a532-32295201701d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T22:53:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfRO/ayRcGRfIiK7JHkcgCEvNKHULXHvbf1pqVnvACk+wOQsIuTaKx1qBEGlf8dYWfvKx25om/h1SOX3KYgOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:54:52.674733Z"},"content_sha256":"3df6580b93d7d25bd6e074b38b74d3bfc8349312038c856cdbd34d5ae4caf92f","schema_version":"1.0","event_id":"sha256:3df6580b93d7d25bd6e074b38b74d3bfc8349312038c856cdbd34d5ae4caf92f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2TLRLELJAS7P6FWPCQWHASXR7/bundle.json","state_url":"https://pith.science/pith/Y2TLRLELJAS7P6FWPCQWHASXR7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2TLRLELJAS7P6FWPCQWHASXR7/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":"2026-07-10T12:54:52Z","links":{"resolver":"https://pith.science/pith/Y2TLRLELJAS7P6FWPCQWHASXR7","bundle":"https://pith.science/pith/Y2TLRLELJAS7P6FWPCQWHASXR7/bundle.json","state":"https://pith.science/pith/Y2TLRLELJAS7P6FWPCQWHASXR7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2TLRLELJAS7P6FWPCQWHASXR7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y2TLRLELJAS7P6FWPCQWHASXR7","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":"85f042f5376ce92a90d01f095623e3ff4dec0a068769ff7841ba8e1b771d9436","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-08T13:06:26Z","title_canon_sha256":"9159c215c228d4f2f4a272fa1e1e27fe7c4db68eea975dd95b9864614368fcf9"},"schema_version":"1.0","source":{"id":"1807.02811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.02811","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"arxiv_version","alias_value":"1807.02811v1","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02811","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"pith_short_12","alias_value":"Y2TLRLELJAS7","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"pith_short_16","alias_value":"Y2TLRLELJAS7P6FW","created_at":"2026-07-04T22:53:53Z"},{"alias_kind":"pith_short_8","alias_value":"Y2TLRLEL","created_at":"2026-07-04T22:53:53Z"}],"graph_snapshots":[{"event_id":"sha256:3df6580b93d7d25bd6e074b38b74d3bfc8349312038c856cdbd34d5ae4caf92f","target":"graph","created_at":"2026-07-04T22:53:53Z","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 provide a generalization of expected improvement to noisy evaluations, justified by a formal decision-theoretic argument, standing in contrast to previous ad hoc modifications."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The tutorial assumes that a Gaussian process provides an adequate surrogate model for the objective function and that the reader has sufficient background in Bayesian methods and Gaussian processes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Bayesian optimization uses Gaussian process regression to build a surrogate model and acquisition functions to guide sampling for optimizing costly objective functions, including a new formal generalization of expected improvement to noisy evaluations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Bayesian optimization builds a Gaussian process surrogate for an expensive objective and uses an acquisition function to choose each next evaluation point."}],"snapshot_sha256":"56842bd2672bf678e2d85168199b6b51317b4b5a4c770ca0dd44e980c6c9e688"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"64fac19c9faaa72c0dce660d8c954e0a2855b9cca1f57e2c8b06d95b9acd30c7"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1807.02811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bayesian optimization is an approach to optimizing objective functions that take a long time (minutes or hours) to evaluate. It is best-suited for optimization over continuous domains of less than 20 dimensions, and tolerates stochastic noise in function evaluations. It builds a surrogate for the objective and quantifies the uncertainty in that surrogate using a Bayesian machine learning technique, Gaussian process regression, and then uses an acquisition function defined from this surrogate to decide where to sample. In this tutorial, we describe how Bayesian optimization works, including Gau","authors_text":"Peter I. Frazier","cross_cats":["cs.LG","math.OC"],"headline":"Bayesian optimization builds a Gaussian process surrogate for an expensive objective and uses an acquisition function to choose each next evaluation point.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-08T13:06:26Z","title":"A Tutorial on Bayesian Optimization"},"references":{"count":101,"internal_anchors":4,"resolved_work":101,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"O., Shahriari, B., and Schmidt, M","work_id":"cc143d0e-dfbe-402e-a2bb-9b27b6591cc3","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Berger, J. O. (2013). Statistical Decision Theory and Bayesian Analysis . Springer Science & Business Media","work_id":"4c6e7a1b-f6ad-4c90-bb19-e7aac5c6e815","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Blum, J. R. (1954). Multidimensional stochastic approximation methods. The Annals of Mathematical Statistics , pages 737--744","work_id":"d83fc444-3a13-4ef9-b289-cabae357f8ba","year":1954},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Booker, A., Dennis, J., Frank, P., Serafini, D., Torczon, V., and Trosset, M. (1999). A rigorous framework for optimization of expensive functions by surrogates . Structural and Multidisciplinary Opti","work_id":"c86e3966-3e0d-475a-ac15-c5c25232bb89","year":1999},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bottou, L. (2012). Stochastic gradient descent tricks. In Montavon, G., Orr, G. B., and M \\\"u ller, K. R., editors, Neural Networks: Tricks of the Trade , pages 421--436. Springer","work_id":"35c07c29-944d-45a0-9b53-7a1edb7d2279","year":2012}],"snapshot_sha256":"256b78b9b1377205ef2a4d85f1856f0727bb958298e1abd58660bb5f4d0e5ad2"},"source":{"id":"1807.02811","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-13T14:12:39.323428Z","id":"d2611f24-f700-4b86-a532-32295201701d","model_set":{"reader":"grok-4.3"},"one_line_summary":"Bayesian optimization uses Gaussian process regression to build a surrogate model and acquisition functions to guide sampling for optimizing costly objective functions, including a new formal generalization of expected improvement to noisy evaluations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Bayesian optimization builds a Gaussian process surrogate for an expensive objective and uses an acquisition function to choose each next evaluation point.","strongest_claim":"We provide a generalization of expected improvement to noisy evaluations, justified by a formal decision-theoretic argument, standing in contrast to previous ad hoc modifications.","weakest_assumption":"The tutorial assumes that a Gaussian process provides an adequate surrogate model for the objective function and that the reader has sufficient background in Bayesian methods and Gaussian processes."}},"verdict_id":"d2611f24-f700-4b86-a532-32295201701d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:abe3c583b249dab42cabacf2f7fd1fd51890e6f7ffdc2d714073aa79f661963b","target":"record","created_at":"2026-07-04T22:53:53Z","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":"85f042f5376ce92a90d01f095623e3ff4dec0a068769ff7841ba8e1b771d9436","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-08T13:06:26Z","title_canon_sha256":"9159c215c228d4f2f4a272fa1e1e27fe7c4db68eea975dd95b9864614368fcf9"},"schema_version":"1.0","source":{"id":"1807.02811","kind":"arxiv","version":1}},"canonical_sha256":"c6a6b8ac8b4825f7f8b678a16382578ff4fccc0b5ad990dd263275c7f2e8405b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6a6b8ac8b4825f7f8b678a16382578ff4fccc0b5ad990dd263275c7f2e8405b","first_computed_at":"2026-07-04T22:53:53.807374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T22:53:53.807374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mcaIlyD2qm6IaM/VoCPUJrWISOc/7cZ7fdorVrHorfPz70imxYqYaoKfIDg6BqbckeRULzGowOX3G30bzgZxBQ==","signature_status":"signed_v1","signed_at":"2026-07-04T22:53:53.807916Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.02811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abe3c583b249dab42cabacf2f7fd1fd51890e6f7ffdc2d714073aa79f661963b","sha256:3df6580b93d7d25bd6e074b38b74d3bfc8349312038c856cdbd34d5ae4caf92f"],"state_sha256":"c0f59e9baf79a97cc95a2b50cdf38ecd5ea11902a0df69451d3e29759b1e1123"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYWVXW6PDwT/ZhxKQ0enpZ4f9YFokfk8Wg+JD3nOESnGs7oGGNWvj5ro7QFAXoYh3JLJFNWlLFU+YthxneC4BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T12:54:52.678519Z","bundle_sha256":"b8d38412fc84b295287b3382569650f8fb89d2790967eb4c9ed0b8d713b7948b"}}