{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7HKATMNBITTROYLKPUQETWCMAT","short_pith_number":"pith:7HKATMNB","canonical_record":{"source":{"id":"2310.00426","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-30T16:18:00Z","cross_cats_sorted":[],"title_canon_sha256":"cb9e9b56edb1ab9b86f426ca6f1b7399e043df8ba98246bdd57dd8249c50c0c3","abstract_canon_sha256":"a88755545e90ead117f4d3a318aa0b9baa73dd4555b7cdbf94939c6fdc966f3f"},"schema_version":"1.0"},"canonical_sha256":"f9d409b1a144e717616a7d2049d84c04d05a99ccc969032ae2111bb008f1095c","source":{"kind":"arxiv","id":"2310.00426","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00426","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00426v3","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00426","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"7HKATMNBITTR","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"7HKATMNBITTROYLK","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"7HKATMNB","created_at":"2026-07-05T07:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7HKATMNBITTROYLKPUQETWCMAT","target":"record","payload":{"canonical_record":{"source":{"id":"2310.00426","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-30T16:18:00Z","cross_cats_sorted":[],"title_canon_sha256":"cb9e9b56edb1ab9b86f426ca6f1b7399e043df8ba98246bdd57dd8249c50c0c3","abstract_canon_sha256":"a88755545e90ead117f4d3a318aa0b9baa73dd4555b7cdbf94939c6fdc966f3f"},"schema_version":"1.0"},"canonical_sha256":"f9d409b1a144e717616a7d2049d84c04d05a99ccc969032ae2111bb008f1095c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:46.082064Z","signature_b64":"BtcmzWxs+6InJMBQRukn74MBASroe7pAHTT00fA537wR8yjT/UWzd7ZtTmyRD7HaxIrMmqfpKT68oVXckTJ4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9d409b1a144e717616a7d2049d84c04d05a99ccc969032ae2111bb008f1095c","last_reissued_at":"2026-07-05T07:28:46.081583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:46.081583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.00426","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":"2026-07-05T07:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"owLzqR93uQk7IGasReDO1gRfXqNK1NV6+RETG9aJibb9+BSwQq1rIPb6bjpKgrP6lRQBYFIjPFBi7YL86pRNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:11:57.390863Z"},"content_sha256":"438273b248a4e311f3aef8b7ee5d99eb6dfc4cfbe85b854190147415cb9f20e5","schema_version":"1.0","event_id":"sha256:438273b248a4e311f3aef8b7ee5d99eb6dfc4cfbe85b854190147415cb9f20e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7HKATMNBITTROYLKPUQETWCMAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"PIXART-α trains a high-quality text-to-image diffusion transformer in 10.8 percent the time of Stable Diffusion v1.5.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Enze Xie, Huchuan Lu, James Kwok, Jincheng Yu, Junsong Chen, Lewei Yao, Ping Luo, Yue Wu, Zhenguo Li, Zhongdao Wang","submitted_at":"2023-09-30T16:18:00Z","abstract_excerpt":"The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces PIXART-$\\alpha$, a Transformer-based T2I diffusion model whose image generation quality is competitive with state-of-the-art image generators (e.g., Imagen, SDXL, and even Midjourney), reaching near-commercial application standards. Additionally, it supports high-resolution image synthesis up to 1024px resolution with low training cost, as shown in Figure 1 and 2"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PIXART-α only takes 10.8% of Stable Diffusion v1.5's training time (675 vs. 6,250 A100 GPU days), saving nearly $300,000 and reducing 90% CO2 emissions while achieving competitive image quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three-stage training decomposition plus VLM-generated dense captions are the primary drivers of both the quality and the massive efficiency gain, rather than differences in data scale, optimizer choices, or unstated implementation details.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PIXART-α trains a high-quality text-to-image diffusion transformer in 10.8 percent the time of Stable Diffusion v1.5.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5da3204806648c349bf836d44d387e8a17832a0ad8a036596c90b0c256177a19"},"source":{"id":"2310.00426","kind":"arxiv","version":3},"verdict":{"id":"d4d8d0b8-1dc0-4916-86e0-8d671dd8bdc0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T20:33:40.515106Z","strongest_claim":"PIXART-α only takes 10.8% of Stable Diffusion v1.5's training time (675 vs. 6,250 A100 GPU days), saving nearly $300,000 and reducing 90% CO2 emissions while achieving competitive image quality.","one_line_summary":"PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three-stage training decomposition plus VLM-generated dense captions are the primary drivers of both the quality and the massive efficiency gain, rather than differences in data scale, optimizer choices, or unstated implementation details.","pith_extraction_headline":"PIXART-α trains a high-quality text-to-image diffusion transformer in 10.8 percent the time of Stable Diffusion v1.5."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.00426/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":154,"sample":[{"doi":"","year":2022,"title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","work_id":"7b3f0ec5-8cde-4746-91c4-b2f525378054","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"All are worth words: A vit backbone for diffusion models","work_id":"dc5742de-b306-4fe7-8565-d4c06c76ff88","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"A study on the evaluation of generative models","work_id":"b610c3c1-fa7b-48fd-a654-b3733895def6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"End-to-end object detection with transformers","work_id":"9e8de266-8b5e-4baa-a192-25c6902a2f71","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"DeepFloyd. Deepfloyd, 2023. URL https://www.deepfloyd.ai/","work_id":"f4edd0e8-a0a5-48c2-a2cf-c04e92826000","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":154,"snapshot_sha256":"8eace96fbb91f7cb94b7f9a2461f69d84d4bdfaaa0ad8c4e350a6f723e26c877","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"54643ef00902e8b58e0cc3a424e9869e724cf101a40f67ffc559efc8ec21165e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d4d8d0b8-1dc0-4916-86e0-8d671dd8bdc0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mkoXSN4TAjehcgH4Sr2dQ3vzVVEvmxxx8tSnazMkZTpbE6As1Tu+e2tgmUxEGateSh5l8d+ZNe/jK7OcnUXgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:11:57.391672Z"},"content_sha256":"766ee962cffbbbe0770e32740ca2177994d34d7d5212c06e90f574fa58fb84aa","schema_version":"1.0","event_id":"sha256:766ee962cffbbbe0770e32740ca2177994d34d7d5212c06e90f574fa58fb84aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HKATMNBITTROYLKPUQETWCMAT/bundle.json","state_url":"https://pith.science/pith/7HKATMNBITTROYLKPUQETWCMAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HKATMNBITTROYLKPUQETWCMAT/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":"2026-08-07T06:11:57Z","links":{"resolver":"https://pith.science/pith/7HKATMNBITTROYLKPUQETWCMAT","bundle":"https://pith.science/pith/7HKATMNBITTROYLKPUQETWCMAT/bundle.json","state":"https://pith.science/pith/7HKATMNBITTROYLKPUQETWCMAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HKATMNBITTROYLKPUQETWCMAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7HKATMNBITTROYLKPUQETWCMAT","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":"a88755545e90ead117f4d3a318aa0b9baa73dd4555b7cdbf94939c6fdc966f3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-30T16:18:00Z","title_canon_sha256":"cb9e9b56edb1ab9b86f426ca6f1b7399e043df8ba98246bdd57dd8249c50c0c3"},"schema_version":"1.0","source":{"id":"2310.00426","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00426","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00426v3","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00426","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"7HKATMNBITTR","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"7HKATMNBITTROYLK","created_at":"2026-07-05T07:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"7HKATMNB","created_at":"2026-07-05T07:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:766ee962cffbbbe0770e32740ca2177994d34d7d5212c06e90f574fa58fb84aa","target":"graph","created_at":"2026-07-05T07:28:46Z","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":"PIXART-α only takes 10.8% of Stable Diffusion v1.5's training time (675 vs. 6,250 A100 GPU days), saving nearly $300,000 and reducing 90% CO2 emissions while achieving competitive image quality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the three-stage training decomposition plus VLM-generated dense captions are the primary drivers of both the quality and the massive efficiency gain, rather than differences in data scale, optimizer choices, or unstated implementation details."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PIXART-α trains a high-quality text-to-image diffusion transformer in 10.8 percent the time of Stable Diffusion v1.5."}],"snapshot_sha256":"5da3204806648c349bf836d44d387e8a17832a0ad8a036596c90b0c256177a19"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"54643ef00902e8b58e0cc3a424e9869e724cf101a40f67ffc559efc8ec21165e"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.00426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces PIXART-$\\alpha$, a Transformer-based T2I diffusion model whose image generation quality is competitive with state-of-the-art image generators (e.g., Imagen, SDXL, and even Midjourney), reaching near-commercial application standards. Additionally, it supports high-resolution image synthesis up to 1024px resolution with low training cost, as shown in Figure 1 and 2","authors_text":"Chongjian Ge, Enze Xie, Huchuan Lu, James Kwok, Jincheng Yu, Junsong Chen, Lewei Yao, Ping Luo, Yue Wu, Zhenguo Li, Zhongdao Wang","cross_cats":[],"headline":"PIXART-α trains a high-quality text-to-image diffusion transformer in 10.8 percent the time of Stable Diffusion v1.5.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-30T16:18:00Z","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis"},"references":{"count":154,"internal_anchors":1,"resolved_work":154,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","work_id":"7b3f0ec5-8cde-4746-91c4-b2f525378054","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"All are worth words: A vit backbone for diffusion models","work_id":"dc5742de-b306-4fe7-8565-d4c06c76ff88","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A study on the evaluation of generative models","work_id":"b610c3c1-fa7b-48fd-a654-b3733895def6","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"End-to-end object detection with transformers","work_id":"9e8de266-8b5e-4baa-a192-25c6902a2f71","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":6,"title":"DeepFloyd. Deepfloyd, 2023. URL https://www.deepfloyd.ai/","work_id":"f4edd0e8-a0a5-48c2-a2cf-c04e92826000","year":2023}],"snapshot_sha256":"8eace96fbb91f7cb94b7f9a2461f69d84d4bdfaaa0ad8c4e350a6f723e26c877"},"source":{"id":"2310.00426","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-12T20:33:40.515106Z","id":"d4d8d0b8-1dc0-4916-86e0-8d671dd8bdc0","model_set":{"reader":"grok-4.3"},"one_line_summary":"PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PIXART-α trains a high-quality text-to-image diffusion transformer in 10.8 percent the time of Stable Diffusion v1.5.","strongest_claim":"PIXART-α only takes 10.8% of Stable Diffusion v1.5's training time (675 vs. 6,250 A100 GPU days), saving nearly $300,000 and reducing 90% CO2 emissions while achieving competitive image quality.","weakest_assumption":"That the three-stage training decomposition plus VLM-generated dense captions are the primary drivers of both the quality and the massive efficiency gain, rather than differences in data scale, optimizer choices, or unstated implementation details."}},"verdict_id":"d4d8d0b8-1dc0-4916-86e0-8d671dd8bdc0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:438273b248a4e311f3aef8b7ee5d99eb6dfc4cfbe85b854190147415cb9f20e5","target":"record","created_at":"2026-07-05T07:28:46Z","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":"a88755545e90ead117f4d3a318aa0b9baa73dd4555b7cdbf94939c6fdc966f3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-30T16:18:00Z","title_canon_sha256":"cb9e9b56edb1ab9b86f426ca6f1b7399e043df8ba98246bdd57dd8249c50c0c3"},"schema_version":"1.0","source":{"id":"2310.00426","kind":"arxiv","version":3}},"canonical_sha256":"f9d409b1a144e717616a7d2049d84c04d05a99ccc969032ae2111bb008f1095c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9d409b1a144e717616a7d2049d84c04d05a99ccc969032ae2111bb008f1095c","first_computed_at":"2026-07-05T07:28:46.081583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:46.081583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BtcmzWxs+6InJMBQRukn74MBASroe7pAHTT00fA537wR8yjT/UWzd7ZtTmyRD7HaxIrMmqfpKT68oVXckTJ4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:46.082064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00426","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:438273b248a4e311f3aef8b7ee5d99eb6dfc4cfbe85b854190147415cb9f20e5","sha256:766ee962cffbbbe0770e32740ca2177994d34d7d5212c06e90f574fa58fb84aa"],"state_sha256":"95a44b46084dd8ee5690f4cf654b19a78f174fdc145fe161136fe85dd1d7c4b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0XNAx7WfATyDP3EdRqel/HMEMZZlkpdle3rkgtmbJUmlx3V98IZDQFVCflHYVHGt8WyBBMoWZ3v1A3hLyzwSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:11:57.396624Z","bundle_sha256":"d9d0ab59acd929f9823bf4aad07d47bd606486dc3c907dde97e97641002b3ef3"}}