{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YBWMYB6XSOOZE2I3FLDL6CKLF6","short_pith_number":"pith:YBWMYB6X","canonical_record":{"source":{"id":"2605.13565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:04:56Z","cross_cats_sorted":[],"title_canon_sha256":"829e1750ce48e2abaeb7fa068dc357e111dd807843d69c81a6abf30dbd1daa1d","abstract_canon_sha256":"f6e24bde400885c0d6579e6b385077eafcf9f8777a2da89fc92cac9f31f64458"},"schema_version":"1.0"},"canonical_sha256":"c06ccc07d7939d92691b2ac6bf094b2fb5c6f6cc8f02e86643fc53da549e7e15","source":{"kind":"arxiv","id":"2605.13565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13565","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13565v1","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13565","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"YBWMYB6XSOOZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YBWMYB6XSOOZE2I3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YBWMYB6X","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YBWMYB6XSOOZE2I3FLDL6CKLF6","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:04:56Z","cross_cats_sorted":[],"title_canon_sha256":"829e1750ce48e2abaeb7fa068dc357e111dd807843d69c81a6abf30dbd1daa1d","abstract_canon_sha256":"f6e24bde400885c0d6579e6b385077eafcf9f8777a2da89fc92cac9f31f64458"},"schema_version":"1.0"},"canonical_sha256":"c06ccc07d7939d92691b2ac6bf094b2fb5c6f6cc8f02e86643fc53da549e7e15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:23.462948Z","signature_b64":"2AHckHsf18GUxTwd3iWh517yBI906lZLJzBJZKCNsu1F0xNOvmvC1OzE3Hxi573Lat7qdnkgENMglSo29M6wCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c06ccc07d7939d92691b2ac6bf094b2fb5c6f6cc8f02e86643fc53da549e7e15","last_reissued_at":"2026-05-18T02:44:23.462470Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:23.462470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13565","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":"2026-05-18T02:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OtqqowKMMi+5x9v5sHAV2II+Y1OqdQJSOOuWy7glh7YJDH3mHmZktZGJ2rRNkkMHVm6ZjFdxZa31eHfbFNPZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:21:03.061605Z"},"content_sha256":"346ae5e2a739393af5e0b2555f7b15363aff12ba8adc7fa32a5b190ef93cc75c","schema_version":"1.0","event_id":"sha256:346ae5e2a739393af5e0b2555f7b15363aff12ba8adc7fa32a5b190ef93cc75c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YBWMYB6XSOOZE2I3FLDL6CKLF6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Qwen-Image-VAE-2.0 Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Qwen-Image-VAE-2.0 delivers state-of-the-art image reconstruction at high compression ratios while accelerating diffusion model convergence.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Kaiyuan Gao, Kuan Cao, Kun Yan, Liang Peng, Lihan Jiang, Lin Qu, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiaoxiao Xu, Xiao Xu, Xiaoyue Chen, Yanran Zhang, Yan Shu, Yilei Chen, Yiliang Gu, Yi Wang, Yixian Xu, Yujia Wu, Yu Wu, Yuxiang Chen, Zekai Zhang, Zhendong Wang, Zihao Liu, Zikai Zhou","submitted_at":"2026-05-13T14:04:56Z","abstract_excerpt":"We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To address the reconstruction bottlenecks of high compression, we adopt an improved architecture featuring Global Skip Connections (GSC) and expanded latent channels. Moreover, we scale training to billions of images and incorporate a synthetic rendering engine to improve performance in text-rich scenarios. To tackle the convergence challenges of high-dimensional latent space, we implement an enhanced semantic alignment "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Qwen-Image-VAE-2.0 achieves state-of-the-art reconstruction performance, demonstrating exceptional capabilities in both general domains and text-rich scenarios at high compression ratio. Furthermore, downstream DiT experiments reveal our models possess superior diffusability, significantly accelerating convergence compared to existing high-compression baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that scaling training to billions of images combined with synthetic rendering and semantic alignment will produce a high-dimensional latent space that is highly amenable to diffusion modeling without introducing new artifacts or domain biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Qwen-Image-VAE-2.0 achieves state-of-the-art high-compression image reconstruction and superior diffusability for diffusion models, with a new text-rich document benchmark.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Qwen-Image-VAE-2.0 delivers state-of-the-art image reconstruction at high compression ratios while accelerating diffusion model convergence.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"16682d4838ee297f3aba4eeb0745df6e28752e674ae22fd5123169c28805d2b3"},"source":{"id":"2605.13565","kind":"arxiv","version":1},"verdict":{"id":"b3642a0c-9f0f-4a10-8b8c-fcceba5f2fd8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:48:20.473139Z","strongest_claim":"Qwen-Image-VAE-2.0 achieves state-of-the-art reconstruction performance, demonstrating exceptional capabilities in both general domains and text-rich scenarios at high compression ratio. Furthermore, downstream DiT experiments reveal our models possess superior diffusability, significantly accelerating convergence compared to existing high-compression baselines.","one_line_summary":"Qwen-Image-VAE-2.0 achieves state-of-the-art high-compression image reconstruction and superior diffusability for diffusion models, with a new text-rich document benchmark.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that scaling training to billions of images combined with synthetic rendering and semantic alignment will produce a high-dimensional latent space that is highly amenable to diffusion modeling without introducing new artifacts or domain biases.","pith_extraction_headline":"Qwen-Image-VAE-2.0 delivers state-of-the-art image reconstruction at high compression ratios while accelerating diffusion model convergence."},"references":{"count":19,"sample":[{"doi":"","year":null,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","ref_index":1,"cited_arxiv_id":"2501.03575","is_internal_anchor":true},{"doi":"","year":null,"title":"Perception Encoder: The best visual embeddings are not at the output of the network","work_id":"409be941-4d4a-4ceb-a28a-eaa2d7709a1c","ref_index":2,"cited_arxiv_id":"2504.13181","is_internal_anchor":true},{"doi":"","year":null,"title":"HunyuanImage 3.0 Technical Report","work_id":"36511e33-8360-43dd-9407-dddf867c1d7c","ref_index":3,"cited_arxiv_id":"2509.23951","is_internal_anchor":true},{"doi":"","year":null,"title":"PaddleOCR 3.0 Technical Report","work_id":"444c549c-1895-4cae-a2d3-c13d7ed5f462","ref_index":4,"cited_arxiv_id":"2507.05595","is_internal_anchor":true},{"doi":"","year":null,"title":"Seedream 3.0 Technical Report","work_id":"013e56d0-7f47-4d0e-bbca-e9540fc0e0cc","ref_index":5,"cited_arxiv_id":"2504.11346","is_internal_anchor":true}],"resolved_work":19,"snapshot_sha256":"cf2c1a3bd5fdd45c31329e07bce2f71e5bdc7152583539999d85550339bb2e88","internal_anchors":14},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ce02d830bd5a2aadf7d61f30a5985cb9a0cd82a666c9af95f2cac91b661d138e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"b3642a0c-9f0f-4a10-8b8c-fcceba5f2fd8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obglI6LpKzXIIpKBMd30bxm+X2rG1xlDGfZa1ALNTtnAeliEK+CjRaiEemsZoIArMWy7GG7MSkKbTKizmgKkBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:21:03.062290Z"},"content_sha256":"3cad174a8c8ccb79bfd6f9431a0b39479db0b5b18a1b374bf4d4225bfce48a15","schema_version":"1.0","event_id":"sha256:3cad174a8c8ccb79bfd6f9431a0b39479db0b5b18a1b374bf4d4225bfce48a15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBWMYB6XSOOZE2I3FLDL6CKLF6/bundle.json","state_url":"https://pith.science/pith/YBWMYB6XSOOZE2I3FLDL6CKLF6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBWMYB6XSOOZE2I3FLDL6CKLF6/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":"2026-05-31T18:21:03Z","links":{"resolver":"https://pith.science/pith/YBWMYB6XSOOZE2I3FLDL6CKLF6","bundle":"https://pith.science/pith/YBWMYB6XSOOZE2I3FLDL6CKLF6/bundle.json","state":"https://pith.science/pith/YBWMYB6XSOOZE2I3FLDL6CKLF6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBWMYB6XSOOZE2I3FLDL6CKLF6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YBWMYB6XSOOZE2I3FLDL6CKLF6","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":"f6e24bde400885c0d6579e6b385077eafcf9f8777a2da89fc92cac9f31f64458","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:04:56Z","title_canon_sha256":"829e1750ce48e2abaeb7fa068dc357e111dd807843d69c81a6abf30dbd1daa1d"},"schema_version":"1.0","source":{"id":"2605.13565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13565","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13565v1","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13565","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"YBWMYB6XSOOZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YBWMYB6XSOOZE2I3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YBWMYB6X","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:3cad174a8c8ccb79bfd6f9431a0b39479db0b5b18a1b374bf4d4225bfce48a15","target":"graph","created_at":"2026-05-18T02:44:23Z","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":"Qwen-Image-VAE-2.0 achieves state-of-the-art reconstruction performance, demonstrating exceptional capabilities in both general domains and text-rich scenarios at high compression ratio. Furthermore, downstream DiT experiments reveal our models possess superior diffusability, significantly accelerating convergence compared to existing high-compression baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that scaling training to billions of images combined with synthetic rendering and semantic alignment will produce a high-dimensional latent space that is highly amenable to diffusion modeling without introducing new artifacts or domain biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Qwen-Image-VAE-2.0 achieves state-of-the-art high-compression image reconstruction and superior diffusability for diffusion models, with a new text-rich document benchmark."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Qwen-Image-VAE-2.0 delivers state-of-the-art image reconstruction at high compression ratios while accelerating diffusion model convergence."}],"snapshot_sha256":"16682d4838ee297f3aba4eeb0745df6e28752e674ae22fd5123169c28805d2b3"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ce02d830bd5a2aadf7d61f30a5985cb9a0cd82a666c9af95f2cac91b661d138e"},"paper":{"abstract_excerpt":"We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To address the reconstruction bottlenecks of high compression, we adopt an improved architecture featuring Global Skip Connections (GSC) and expanded latent channels. Moreover, we scale training to billions of images and incorporate a synthetic rendering engine to improve performance in text-rich scenarios. To tackle the convergence challenges of high-dimensional latent space, we implement an enhanced semantic alignment ","authors_text":"Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Kaiyuan Gao, Kuan Cao, Kun Yan, Liang Peng, Lihan Jiang, Lin Qu, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiaoxiao Xu, Xiao Xu, Xiaoyue Chen, Yanran Zhang, Yan Shu, Yilei Chen, Yiliang Gu, Yi Wang, Yixian Xu, Yujia Wu, Yu Wu, Yuxiang Chen, Zekai Zhang, Zhendong Wang, Zihao Liu, Zikai Zhou","cross_cats":[],"headline":"Qwen-Image-VAE-2.0 delivers state-of-the-art image reconstruction at high compression ratios while accelerating diffusion model convergence.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:04:56Z","title":"Qwen-Image-VAE-2.0 Technical Report"},"references":{"count":19,"internal_anchors":14,"resolved_work":19,"sample":[{"cited_arxiv_id":"2501.03575","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","year":null},{"cited_arxiv_id":"2504.13181","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Perception Encoder: The best visual embeddings are not at the output of the network","work_id":"409be941-4d4a-4ceb-a28a-eaa2d7709a1c","year":null},{"cited_arxiv_id":"2509.23951","doi":"","is_internal_anchor":true,"ref_index":3,"title":"HunyuanImage 3.0 Technical Report","work_id":"36511e33-8360-43dd-9407-dddf867c1d7c","year":null},{"cited_arxiv_id":"2507.05595","doi":"","is_internal_anchor":true,"ref_index":4,"title":"PaddleOCR 3.0 Technical Report","work_id":"444c549c-1895-4cae-a2d3-c13d7ed5f462","year":null},{"cited_arxiv_id":"2504.11346","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Seedream 3.0 Technical Report","work_id":"013e56d0-7f47-4d0e-bbca-e9540fc0e0cc","year":null}],"snapshot_sha256":"cf2c1a3bd5fdd45c31329e07bce2f71e5bdc7152583539999d85550339bb2e88"},"source":{"id":"2605.13565","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:48:20.473139Z","id":"b3642a0c-9f0f-4a10-8b8c-fcceba5f2fd8","model_set":{"reader":"grok-4.3"},"one_line_summary":"Qwen-Image-VAE-2.0 achieves state-of-the-art high-compression image reconstruction and superior diffusability for diffusion models, with a new text-rich document benchmark.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Qwen-Image-VAE-2.0 delivers state-of-the-art image reconstruction at high compression ratios while accelerating diffusion model convergence.","strongest_claim":"Qwen-Image-VAE-2.0 achieves state-of-the-art reconstruction performance, demonstrating exceptional capabilities in both general domains and text-rich scenarios at high compression ratio. Furthermore, downstream DiT experiments reveal our models possess superior diffusability, significantly accelerating convergence compared to existing high-compression baselines.","weakest_assumption":"The assumption that scaling training to billions of images combined with synthetic rendering and semantic alignment will produce a high-dimensional latent space that is highly amenable to diffusion modeling without introducing new artifacts or domain biases."}},"verdict_id":"b3642a0c-9f0f-4a10-8b8c-fcceba5f2fd8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:346ae5e2a739393af5e0b2555f7b15363aff12ba8adc7fa32a5b190ef93cc75c","target":"record","created_at":"2026-05-18T02:44:23Z","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":"f6e24bde400885c0d6579e6b385077eafcf9f8777a2da89fc92cac9f31f64458","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:04:56Z","title_canon_sha256":"829e1750ce48e2abaeb7fa068dc357e111dd807843d69c81a6abf30dbd1daa1d"},"schema_version":"1.0","source":{"id":"2605.13565","kind":"arxiv","version":1}},"canonical_sha256":"c06ccc07d7939d92691b2ac6bf094b2fb5c6f6cc8f02e86643fc53da549e7e15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c06ccc07d7939d92691b2ac6bf094b2fb5c6f6cc8f02e86643fc53da549e7e15","first_computed_at":"2026-05-18T02:44:23.462470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:23.462470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2AHckHsf18GUxTwd3iWh517yBI906lZLJzBJZKCNsu1F0xNOvmvC1OzE3Hxi573Lat7qdnkgENMglSo29M6wCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:23.462948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:346ae5e2a739393af5e0b2555f7b15363aff12ba8adc7fa32a5b190ef93cc75c","sha256:3cad174a8c8ccb79bfd6f9431a0b39479db0b5b18a1b374bf4d4225bfce48a15"],"state_sha256":"87e596d68d67dc9a9a6091b6d6432b190ab447b95cb9cf0294a83c1257120577"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"01hrs749yYVk4M7g/SsVIPdWB4MStpE/XJabXVBXtxD3h0CYNG4MUXYzkn9xQG1HQWj3TjqfJMRc/WVxLlxmBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:21:03.067619Z","bundle_sha256":"4089347edae216c4fa95829845c96e1851b4aae555e84ca6ca0056a9d96b7734"}}