{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SUGCGL76Y4GGD3Y3XIQUZ5GXXV","short_pith_number":"pith:SUGCGL76","canonical_record":{"source":{"id":"2307.05663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T17:57:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4ed0f7565832bdec93c6ea9dbd812d44062d29604c46f110f8ef1ffe45321ae","abstract_canon_sha256":"de37717dea52d31cb54f357d0ecab19713af592b5d4d4217b34431c8362cc432"},"schema_version":"1.0"},"canonical_sha256":"950c232ffec70c61ef1bba214cf4d7bd4df9d8b668fc4d49ca8235c38663ab9a","source":{"kind":"arxiv","id":"2307.05663","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05663","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05663v1","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05663","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"SUGCGL76Y4GG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SUGCGL76Y4GGD3Y3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SUGCGL76","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SUGCGL76Y4GGD3Y3XIQUZ5GXXV","target":"record","payload":{"canonical_record":{"source":{"id":"2307.05663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T17:57:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4ed0f7565832bdec93c6ea9dbd812d44062d29604c46f110f8ef1ffe45321ae","abstract_canon_sha256":"de37717dea52d31cb54f357d0ecab19713af592b5d4d4217b34431c8362cc432"},"schema_version":"1.0"},"canonical_sha256":"950c232ffec70c61ef1bba214cf4d7bd4df9d8b668fc4d49ca8235c38663ab9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.020323Z","signature_b64":"uTvtBa8/9OlCsH0L13noJDgYfz+Ok1iip+ag61KLYLkapqeKr8L7KDrfppKDPGc2jdubT87iTPy9U5fjddRuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"950c232ffec70c61ef1bba214cf4d7bd4df9d8b668fc4d49ca8235c38663ab9a","last_reissued_at":"2026-05-17T23:38:14.019562Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.019562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.05663","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":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C61zo+QvHr3fshTkiFOPCRIK+fGNuLVe1k01DPrEV8eLBL5dCllc/cIcw3oIYSsfgdGEXV/3Wc6nPICwOT2PCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:20:56.365350Z"},"content_sha256":"2289a3b5f3d659541119ac5c545a56a9d7af93e48de1fce427f020b8268e87a5","schema_version":"1.0","event_id":"sha256:2289a3b5f3d659541119ac5c545a56a9d7af93e48de1fce427f020b8268e87a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SUGCGL76Y4GGD3Y3XIQUZ5GXXV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Objaverse-XL: A Universe of 10M+ 3D Objects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Objaverse-XL supplies over 10 million 3D objects that let models like Zero123 reach strong zero-shot generalization on novel view synthesis.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aditya Kusupati, Alan Fan, Ali Farhadi, Aniruddha Kembhavi, Carl Vondrick, Christian Laforte, Eli VanderBilt, Georgia Gkioxari, Huong Ngo, Kiana Ehsani, Ludwig Schmidt, Matt Deitke, Matthew Wallingford, Oscar Michel, Ruoshi Liu, Samir Yitzhak Gadre, Vikram Voleti","submitted_at":"2023-07-11T17:57:40Z","abstract_excerpt":"Natural language processing and 2D vision models have attained remarkable proficiency on many tasks primarily by escalating the scale of training data. However, 3D vision tasks have not seen the same progress, in part due to the challenges of acquiring high-quality 3D data. In this work, we present Objaverse-XL, a dataset of over 10 million 3D objects. Our dataset comprises deduplicated 3D objects from a diverse set of sources, including manually designed objects, photogrammetry scans of landmarks and everyday items, and professional scans of historic and antique artifacts. Representing the la"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"by training Zero123 on novel view synthesis, utilizing over 100 million multi-view rendered images, we achieve strong zero-shot generalization abilities.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the observed gains in zero-shot performance are attributable primarily to the scale and diversity of Objaverse-XL rather than to other training choices or evaluation details not fully isolated in the experiments.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Objaverse-XL supplies over 10 million diverse 3D objects that, when used to render 100 million views, improve zero-shot novel-view synthesis in models such as Zero123.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Objaverse-XL supplies over 10 million 3D objects that let models like Zero123 reach strong zero-shot generalization on novel view synthesis.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c327ec4137243f9a47d6f3144765c8a37c13dd97186a64bd04c0303b1cef227c"},"source":{"id":"2307.05663","kind":"arxiv","version":1},"verdict":{"id":"ebd590ab-129e-47fb-9188-db3e782a74d0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T12:56:59.647505Z","strongest_claim":"by training Zero123 on novel view synthesis, utilizing over 100 million multi-view rendered images, we achieve strong zero-shot generalization abilities.","one_line_summary":"Objaverse-XL supplies over 10 million diverse 3D objects that, when used to render 100 million views, improve zero-shot novel-view synthesis in models such as Zero123.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the observed gains in zero-shot performance are attributable primarily to the scale and diversity of Objaverse-XL rather than to other training choices or evaluation details not fully isolated in the experiments.","pith_extraction_headline":"Objaverse-XL supplies over 10 million 3D objects that let models like Zero123 reach strong zero-shot generalization on novel view synthesis."},"references":{"count":67,"sample":[{"doi":"","year":null,"title":"URL https://commoncrawl.org/the-data/. 3","work_id":"5339893e-8497-4c0d-86bb-0669438bbe6e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"H. Aanæs, R. R. Jensen, G. V ogiatzis, E. Tola, and A. B. Dahl. Large-scale data for multiple-view stereopsis. International Journal of Computer Vision, pages 1–16, 2016. 9","work_id":"cd438338-b8ea-4c2e-8bd4-437120f2bf73","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"J.-B. Alayrac, J. Donahue, P. Luc, A. Miech, I. Barr, Y . Hasson, K. Lenc, A. Mensch, K. Millican, M. Reynolds, et al. Flamingo: a visual language model for few-shot learning. Advances in Neural Infor","work_id":"1f5fbec8-ce89-4522-8455-e131c761ae66","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"L. Biewald. Experiment tracking with weights and biases, 2020. URL https://www.wandb. com/. Software available from wandb.com. 10","work_id":"1828d401-dea9-4bbe-b816-abf226e45ec8","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Blender - a 3d modelling and rendering package","work_id":"59196cc3-411b-4358-af91-8c29a50a979d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":67,"snapshot_sha256":"152e1464fa73bb08d23d816ac8715c95b0c0c061ccee8483f26b39b09690c96e","internal_anchors":14},"formal_canon":{"evidence_count":1,"snapshot_sha256":"b12f6558728573e59749fa720cf75ac585dc1a688c608ea87f106810315b83cd"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ebd590ab-129e-47fb-9188-db3e782a74d0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuOhScK2XPLz8IDBI4QTLDhKiZqdYgQYkErZJXX2I+w54/zVcZeiXc/Avg2wxUTc2JnsioFAu8dNKRd7+kZqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:20:56.366051Z"},"content_sha256":"85e2d309ef5a93f84503ba3167c9b8e324ee21225acd8d79a3a86bb371add19a","schema_version":"1.0","event_id":"sha256:85e2d309ef5a93f84503ba3167c9b8e324ee21225acd8d79a3a86bb371add19a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SUGCGL76Y4GGD3Y3XIQUZ5GXXV/bundle.json","state_url":"https://pith.science/pith/SUGCGL76Y4GGD3Y3XIQUZ5GXXV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SUGCGL76Y4GGD3Y3XIQUZ5GXXV/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":"2026-05-28T20:20:56Z","links":{"resolver":"https://pith.science/pith/SUGCGL76Y4GGD3Y3XIQUZ5GXXV","bundle":"https://pith.science/pith/SUGCGL76Y4GGD3Y3XIQUZ5GXXV/bundle.json","state":"https://pith.science/pith/SUGCGL76Y4GGD3Y3XIQUZ5GXXV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SUGCGL76Y4GGD3Y3XIQUZ5GXXV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SUGCGL76Y4GGD3Y3XIQUZ5GXXV","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":"de37717dea52d31cb54f357d0ecab19713af592b5d4d4217b34431c8362cc432","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T17:57:40Z","title_canon_sha256":"b4ed0f7565832bdec93c6ea9dbd812d44062d29604c46f110f8ef1ffe45321ae"},"schema_version":"1.0","source":{"id":"2307.05663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05663","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05663v1","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05663","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"SUGCGL76Y4GG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SUGCGL76Y4GGD3Y3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SUGCGL76","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:85e2d309ef5a93f84503ba3167c9b8e324ee21225acd8d79a3a86bb371add19a","target":"graph","created_at":"2026-05-17T23:38:14Z","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":"by training Zero123 on novel view synthesis, utilizing over 100 million multi-view rendered images, we achieve strong zero-shot generalization abilities."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the observed gains in zero-shot performance are attributable primarily to the scale and diversity of Objaverse-XL rather than to other training choices or evaluation details not fully isolated in the experiments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Objaverse-XL supplies over 10 million diverse 3D objects that, when used to render 100 million views, improve zero-shot novel-view synthesis in models such as Zero123."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Objaverse-XL supplies over 10 million 3D objects that let models like Zero123 reach strong zero-shot generalization on novel view synthesis."}],"snapshot_sha256":"c327ec4137243f9a47d6f3144765c8a37c13dd97186a64bd04c0303b1cef227c"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"b12f6558728573e59749fa720cf75ac585dc1a688c608ea87f106810315b83cd"},"paper":{"abstract_excerpt":"Natural language processing and 2D vision models have attained remarkable proficiency on many tasks primarily by escalating the scale of training data. However, 3D vision tasks have not seen the same progress, in part due to the challenges of acquiring high-quality 3D data. In this work, we present Objaverse-XL, a dataset of over 10 million 3D objects. Our dataset comprises deduplicated 3D objects from a diverse set of sources, including manually designed objects, photogrammetry scans of landmarks and everyday items, and professional scans of historic and antique artifacts. Representing the la","authors_text":"Aditya Kusupati, Alan Fan, Ali Farhadi, Aniruddha Kembhavi, Carl Vondrick, Christian Laforte, Eli VanderBilt, Georgia Gkioxari, Huong Ngo, Kiana Ehsani, Ludwig Schmidt, Matt Deitke, Matthew Wallingford, Oscar Michel, Ruoshi Liu, Samir Yitzhak Gadre, Vikram Voleti","cross_cats":["cs.AI"],"headline":"Objaverse-XL supplies over 10 million 3D objects that let models like Zero123 reach strong zero-shot generalization on novel view synthesis.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T17:57:40Z","title":"Objaverse-XL: A Universe of 10M+ 3D Objects"},"references":{"count":67,"internal_anchors":14,"resolved_work":67,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"URL https://commoncrawl.org/the-data/. 3","work_id":"5339893e-8497-4c0d-86bb-0669438bbe6e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"H. Aanæs, R. R. Jensen, G. V ogiatzis, E. Tola, and A. B. Dahl. Large-scale data for multiple-view stereopsis. International Journal of Computer Vision, pages 1–16, 2016. 9","work_id":"cd438338-b8ea-4c2e-8bd4-437120f2bf73","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"J.-B. Alayrac, J. Donahue, P. Luc, A. Miech, I. Barr, Y . Hasson, K. Lenc, A. Mensch, K. Millican, M. Reynolds, et al. Flamingo: a visual language model for few-shot learning. Advances in Neural Infor","work_id":"1f5fbec8-ce89-4522-8455-e131c761ae66","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"L. Biewald. Experiment tracking with weights and biases, 2020. URL https://www.wandb. com/. Software available from wandb.com. 10","work_id":"1828d401-dea9-4bbe-b816-abf226e45ec8","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Blender - a 3d modelling and rendering package","work_id":"59196cc3-411b-4358-af91-8c29a50a979d","year":2023}],"snapshot_sha256":"152e1464fa73bb08d23d816ac8715c95b0c0c061ccee8483f26b39b09690c96e"},"source":{"id":"2307.05663","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-17T12:56:59.647505Z","id":"ebd590ab-129e-47fb-9188-db3e782a74d0","model_set":{"reader":"grok-4.3"},"one_line_summary":"Objaverse-XL supplies over 10 million diverse 3D objects that, when used to render 100 million views, improve zero-shot novel-view synthesis in models such as Zero123.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Objaverse-XL supplies over 10 million 3D objects that let models like Zero123 reach strong zero-shot generalization on novel view synthesis.","strongest_claim":"by training Zero123 on novel view synthesis, utilizing over 100 million multi-view rendered images, we achieve strong zero-shot generalization abilities.","weakest_assumption":"That the observed gains in zero-shot performance are attributable primarily to the scale and diversity of Objaverse-XL rather than to other training choices or evaluation details not fully isolated in the experiments."}},"verdict_id":"ebd590ab-129e-47fb-9188-db3e782a74d0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2289a3b5f3d659541119ac5c545a56a9d7af93e48de1fce427f020b8268e87a5","target":"record","created_at":"2026-05-17T23:38:14Z","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":"de37717dea52d31cb54f357d0ecab19713af592b5d4d4217b34431c8362cc432","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T17:57:40Z","title_canon_sha256":"b4ed0f7565832bdec93c6ea9dbd812d44062d29604c46f110f8ef1ffe45321ae"},"schema_version":"1.0","source":{"id":"2307.05663","kind":"arxiv","version":1}},"canonical_sha256":"950c232ffec70c61ef1bba214cf4d7bd4df9d8b668fc4d49ca8235c38663ab9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"950c232ffec70c61ef1bba214cf4d7bd4df9d8b668fc4d49ca8235c38663ab9a","first_computed_at":"2026-05-17T23:38:14.019562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:14.019562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uTvtBa8/9OlCsH0L13noJDgYfz+Ok1iip+ag61KLYLkapqeKr8L7KDrfppKDPGc2jdubT87iTPy9U5fjddRuDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:14.020323Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.05663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2289a3b5f3d659541119ac5c545a56a9d7af93e48de1fce427f020b8268e87a5","sha256:85e2d309ef5a93f84503ba3167c9b8e324ee21225acd8d79a3a86bb371add19a"],"state_sha256":"672f50e0fddbaa02cff3b507ba1225f96ededefd04ad37858b1d33dbabf05650"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMazhc3KukvKOjwVymC/m2HBAXRUSaYlYNqoQQusa8OnHSisw+rehRn3Tp6Vow6t4B8vdUjdYms8BfWBvm3EDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:20:56.370039Z","bundle_sha256":"6fbc9534210076bbd139858d32d9ab1359f65d8f93c1603b2b34a9d5b1e2bc27"}}