{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IZHUHFCYHPHS2S6LMXZ53T65C7","short_pith_number":"pith:IZHUHFCY","canonical_record":{"source":{"id":"1907.05600","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T07:37:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b75f07f5b1033e09b1209c28be091524212e58474763bb135b7ec8620e416b82","abstract_canon_sha256":"8b8a8ca576822bf40b200dc900d7ab59460fc585198d16880952c92d2eac2423"},"schema_version":"1.0"},"canonical_sha256":"464f4394583bcf2d4bcb65f3ddcfdd17f17ca9e6a108204ca48924543df5f7e3","source":{"kind":"arxiv","id":"1907.05600","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05600","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05600v3","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05600","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"IZHUHFCYHPHS","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IZHUHFCYHPHS2S6L","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IZHUHFCY","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IZHUHFCYHPHS2S6LMXZ53T65C7","target":"record","payload":{"canonical_record":{"source":{"id":"1907.05600","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T07:37:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b75f07f5b1033e09b1209c28be091524212e58474763bb135b7ec8620e416b82","abstract_canon_sha256":"8b8a8ca576822bf40b200dc900d7ab59460fc585198d16880952c92d2eac2423"},"schema_version":"1.0"},"canonical_sha256":"464f4394583bcf2d4bcb65f3ddcfdd17f17ca9e6a108204ca48924543df5f7e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.894500Z","signature_b64":"vYZir7X+glE6yUNCE1S7PuTZ/pBZ244mccQZofLbIwLu4zlrDUH8wd6ZryWPbcra5bWiOgfREH16Qnyj7j+qCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"464f4394583bcf2d4bcb65f3ddcfdd17f17ca9e6a108204ca48924543df5f7e3","last_reissued_at":"2026-05-17T23:38:13.893886Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.893886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.05600","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WvaI6NNlRcbY9tobKE8Ihb8idwWfVQHX/T6up4relMrdlz37bHqD3Ac6Se50hQjmx7NuVGc8SIextDVM+g76Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T16:29:45.109675Z"},"content_sha256":"25cde1e4669a48b543caedb57b402b4e4e680e62daed4521e8266e19a3649327","schema_version":"1.0","event_id":"sha256:25cde1e4669a48b543caedb57b402b4e4e680e62daed4521e8266e19a3649327"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IZHUHFCYHPHS2S6LMXZ53T65C7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Modeling by Estimating Gradients of the Data Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A generative model learns gradients of noisy data distributions to drive annealed Langevin dynamics and produce samples without adversarial training.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Stefano Ermon, Yang Song","submitted_at":"2019-07-12T07:37:26Z","abstract_excerpt":"We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching. Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores, i.e., the vector fields of gradients of the perturbed data distribution for all noise levels. For sampling, we propose an annealed Langevin dynamics where we use gradients corresponding to gradually decreasing noise levels as"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our models produce samples comparable to GANs on MNIST, CelebA and CIFAR-10 datasets, achieving a new state-of-the-art inception score of 8.87 on CIFAR-10. Additionally, we demonstrate that our models learn effective representations via image inpainting experiments.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Score-based generative modeling via multi-noise-level score matching and annealed Langevin dynamics produces samples on par with GANs and sets a new inception score record on CIFAR-10.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A generative model learns gradients of noisy data distributions to drive annealed Langevin dynamics and produce samples without adversarial training.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ba39214c102c2fa9d25b014968bd60b5d60bf3807bb9068b2abcefe578b38177"},"source":{"id":"1907.05600","kind":"arxiv","version":3},"verdict":{"id":"5edb9a9a-cf0a-4c43-a367-e3146d1cfd82","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T13:56:41.052084Z","strongest_claim":"Our models produce samples comparable to GANs on MNIST, CelebA and CIFAR-10 datasets, achieving a new state-of-the-art inception score of 8.87 on CIFAR-10. Additionally, we demonstrate that our models learn effective representations via image inpainting experiments.","one_line_summary":"Score-based generative modeling via multi-noise-level score matching and annealed Langevin dynamics produces samples on par with GANs and sets a new inception score record on CIFAR-10.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores.","pith_extraction_headline":"A generative model learns gradients of noisy data distributions to drive annealed Langevin dynamics and produce samples without adversarial training."},"references":{"count":66,"sample":[{"doi":"","year":2016,"title":"G. Alain, Y . Bengio, L. Yao, J. Yosinski, E. Thibodeau-Laufer, S. Zhang, and P. Vincent. GSNs: generative stochastic networks. Information and Inference, 2016","work_id":"257e3fc4-3552-42d6-8b29-fa05f0292c12","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"M. Arjovsky, S. Chintala, and L. Bottou. Wasserstein generative adversarial networks. In D. Precup and Y . W. Teh, editors,Proceedings of the 34th International Conference on Ma- chine Learning, volum","work_id":"0476ca03-7a2c-4410-9eb9-78e4b014fdb4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2003,"title":"M. Belkin and P. Niyogi. Laplacian eigenmaps for dimensionality reduction and data represen- tation. Neural computation, 15(6):1373–1396, 2003","work_id":"0def5714-d589-46d8-83a4-281c81047140","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Y . Bengio, L. Yao, G. Alain, and P. Vincent. Generalized denoising auto-encoders as generative models. In Advances in neural information processing systems, pages 899–907, 2013","work_id":"6ed59c5e-d966-4018-b108-2a701f7b1dfe","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Learning to Generate Samples from Noise through Infusion Training","work_id":"dcfc7c7b-9a83-4c3a-9cc6-3bba57a917e1","ref_index":5,"cited_arxiv_id":"1703.06975","is_internal_anchor":true}],"resolved_work":66,"snapshot_sha256":"cd1d876188adea6a00b1580ffd92a9df06c81adadf09639b8f98cfe679df431d","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"acbb7a964ecf6987e147ce17748e3845dadaf02af51890bba3ae8868e33e0d8e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5edb9a9a-cf0a-4c43-a367-e3146d1cfd82"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5pUv9fTEku8bvG4O0cMZFQziFvbs+yO+l0BUr69TkrgrKocbH4aFVJgRQYgylE4H3kWUdG8vHhDj2MKO9EyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T16:29:45.110299Z"},"content_sha256":"6786b6e1dfe82a606c85b4a145e758bdd816399a1a15a0382e685a2e0a77962d","schema_version":"1.0","event_id":"sha256:6786b6e1dfe82a606c85b4a145e758bdd816399a1a15a0382e685a2e0a77962d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZHUHFCYHPHS2S6LMXZ53T65C7/bundle.json","state_url":"https://pith.science/pith/IZHUHFCYHPHS2S6LMXZ53T65C7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZHUHFCYHPHS2S6LMXZ53T65C7/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":"2026-05-19T16:29:45Z","links":{"resolver":"https://pith.science/pith/IZHUHFCYHPHS2S6LMXZ53T65C7","bundle":"https://pith.science/pith/IZHUHFCYHPHS2S6LMXZ53T65C7/bundle.json","state":"https://pith.science/pith/IZHUHFCYHPHS2S6LMXZ53T65C7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZHUHFCYHPHS2S6LMXZ53T65C7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IZHUHFCYHPHS2S6LMXZ53T65C7","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":"8b8a8ca576822bf40b200dc900d7ab59460fc585198d16880952c92d2eac2423","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T07:37:26Z","title_canon_sha256":"b75f07f5b1033e09b1209c28be091524212e58474763bb135b7ec8620e416b82"},"schema_version":"1.0","source":{"id":"1907.05600","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05600","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05600v3","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05600","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"IZHUHFCYHPHS","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IZHUHFCYHPHS2S6L","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IZHUHFCY","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:6786b6e1dfe82a606c85b4a145e758bdd816399a1a15a0382e685a2e0a77962d","target":"graph","created_at":"2026-05-17T23:38:13Z","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":"Our models produce samples comparable to GANs on MNIST, CelebA and CIFAR-10 datasets, achieving a new state-of-the-art inception score of 8.87 on CIFAR-10. Additionally, we demonstrate that our models learn effective representations via image inpainting experiments."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Score-based generative modeling via multi-noise-level score matching and annealed Langevin dynamics produces samples on par with GANs and sets a new inception score record on CIFAR-10."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A generative model learns gradients of noisy data distributions to drive annealed Langevin dynamics and produce samples without adversarial training."}],"snapshot_sha256":"ba39214c102c2fa9d25b014968bd60b5d60bf3807bb9068b2abcefe578b38177"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"acbb7a964ecf6987e147ce17748e3845dadaf02af51890bba3ae8868e33e0d8e"},"paper":{"abstract_excerpt":"We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching. Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores, i.e., the vector fields of gradients of the perturbed data distribution for all noise levels. For sampling, we propose an annealed Langevin dynamics where we use gradients corresponding to gradually decreasing noise levels as","authors_text":"Stefano Ermon, Yang Song","cross_cats":["stat.ML"],"headline":"A generative model learns gradients of noisy data distributions to drive annealed Langevin dynamics and produce samples without adversarial training.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T07:37:26Z","title":"Generative Modeling by Estimating Gradients of the Data Distribution"},"references":{"count":66,"internal_anchors":10,"resolved_work":66,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"G. Alain, Y . Bengio, L. Yao, J. Yosinski, E. Thibodeau-Laufer, S. Zhang, and P. Vincent. GSNs: generative stochastic networks. Information and Inference, 2016","work_id":"257e3fc4-3552-42d6-8b29-fa05f0292c12","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"M. Arjovsky, S. Chintala, and L. Bottou. Wasserstein generative adversarial networks. In D. Precup and Y . W. Teh, editors,Proceedings of the 34th International Conference on Ma- chine Learning, volum","work_id":"0476ca03-7a2c-4410-9eb9-78e4b014fdb4","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"M. Belkin and P. Niyogi. Laplacian eigenmaps for dimensionality reduction and data represen- tation. Neural computation, 15(6):1373–1396, 2003","work_id":"0def5714-d589-46d8-83a4-281c81047140","year":2003},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Y . Bengio, L. Yao, G. Alain, and P. Vincent. Generalized denoising auto-encoders as generative models. In Advances in neural information processing systems, pages 899–907, 2013","work_id":"6ed59c5e-d966-4018-b108-2a701f7b1dfe","year":2013},{"cited_arxiv_id":"1703.06975","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Learning to Generate Samples from Noise through Infusion Training","work_id":"dcfc7c7b-9a83-4c3a-9cc6-3bba57a917e1","year":2017}],"snapshot_sha256":"cd1d876188adea6a00b1580ffd92a9df06c81adadf09639b8f98cfe679df431d"},"source":{"id":"1907.05600","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T13:56:41.052084Z","id":"5edb9a9a-cf0a-4c43-a367-e3146d1cfd82","model_set":{"reader":"grok-4.3"},"one_line_summary":"Score-based generative modeling via multi-noise-level score matching and annealed Langevin dynamics produces samples on par with GANs and sets a new inception score record on CIFAR-10.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A generative model learns gradients of noisy data distributions to drive annealed Langevin dynamics and produce samples without adversarial training.","strongest_claim":"Our models produce samples comparable to GANs on MNIST, CelebA and CIFAR-10 datasets, achieving a new state-of-the-art inception score of 8.87 on CIFAR-10. Additionally, we demonstrate that our models learn effective representations via image inpainting experiments.","weakest_assumption":"Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores."}},"verdict_id":"5edb9a9a-cf0a-4c43-a367-e3146d1cfd82"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:25cde1e4669a48b543caedb57b402b4e4e680e62daed4521e8266e19a3649327","target":"record","created_at":"2026-05-17T23:38:13Z","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":"8b8a8ca576822bf40b200dc900d7ab59460fc585198d16880952c92d2eac2423","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T07:37:26Z","title_canon_sha256":"b75f07f5b1033e09b1209c28be091524212e58474763bb135b7ec8620e416b82"},"schema_version":"1.0","source":{"id":"1907.05600","kind":"arxiv","version":3}},"canonical_sha256":"464f4394583bcf2d4bcb65f3ddcfdd17f17ca9e6a108204ca48924543df5f7e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"464f4394583bcf2d4bcb65f3ddcfdd17f17ca9e6a108204ca48924543df5f7e3","first_computed_at":"2026-05-17T23:38:13.893886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.893886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vYZir7X+glE6yUNCE1S7PuTZ/pBZ244mccQZofLbIwLu4zlrDUH8wd6ZryWPbcra5bWiOgfREH16Qnyj7j+qCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.894500Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.05600","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25cde1e4669a48b543caedb57b402b4e4e680e62daed4521e8266e19a3649327","sha256:6786b6e1dfe82a606c85b4a145e758bdd816399a1a15a0382e685a2e0a77962d"],"state_sha256":"24fa56f6a683251341a3b00b9234d55657694ad5ed6671fb0dee807a0c6124d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0vd/KUA+m+FDDzkW2c+r75Qd5/h81atRcQE4pWt/ruz6uRPrgg09fu4ap9qFfD2ER6dxN0VGH/RR8+Y/VZyNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T16:29:45.112803Z","bundle_sha256":"10902cdfd7c9b97a477bf129cb9844c28a2667cc3a8a57891c09c3ea896ebef7"}}