{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GJ2S7I7QZ3JEO3JJCGKNGZ3THD","short_pith_number":"pith:GJ2S7I7Q","canonical_record":{"source":{"id":"2605.14108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T20:47:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6a6221b5b336ccdbeb55cd2e46f1ae1b3ccbc8d97b15ae90fdc9bc31ae7e1fcb","abstract_canon_sha256":"5f4becdfd7f8a3c3e92a6c4cf9810603481465235bea0a6429ab06860e1a5ef1"},"schema_version":"1.0"},"canonical_sha256":"32752fa3f0ced2476d291194d3677338de1b91d9af5c0569bd42701747f3ca91","source":{"kind":"arxiv","id":"2605.14108","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14108","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14108v1","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14108","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"GJ2S7I7QZ3JE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"GJ2S7I7QZ3JEO3JJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"GJ2S7I7Q","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GJ2S7I7QZ3JEO3JJCGKNGZ3THD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T20:47:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6a6221b5b336ccdbeb55cd2e46f1ae1b3ccbc8d97b15ae90fdc9bc31ae7e1fcb","abstract_canon_sha256":"5f4becdfd7f8a3c3e92a6c4cf9810603481465235bea0a6429ab06860e1a5ef1"},"schema_version":"1.0"},"canonical_sha256":"32752fa3f0ced2476d291194d3677338de1b91d9af5c0569bd42701747f3ca91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:12.030268Z","signature_b64":"OThzA4zToQSeEcAM/nbjkK1sKoeIRf+WOZAsLAH1m3BImjjGML47u7aYNtBo61Y5TjLPbxNYmbsS54iOVMkCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32752fa3f0ced2476d291194d3677338de1b91d9af5c0569bd42701747f3ca91","last_reissued_at":"2026-05-17T23:39:12.029791Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:12.029791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14108","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":"2026-05-17T23:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zpa/D1Mu36DULqj+IKHLHV4j4k9f96BbP66sLCB2JrEhvniTjxcc3rs+svqmOnEkkxiSFdHRCXvZ3LZOpwwuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:45:32.126966Z"},"content_sha256":"79154ac65be1a5149f89cd6b4cb4db6051c6311ac614be0654188aa8521112f0","schema_version":"1.0","event_id":"sha256:79154ac65be1a5149f89cd6b4cb4db6051c6311ac614be0654188aa8521112f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GJ2S7I7QZ3JEO3JJCGKNGZ3THD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Rural Healthcare Gap: A Cascaded Edge-Cloud Architecture for Automated Retinal Screening","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An edge-cloud cascade cuts cloud calls for diabetic retinopathy screening by half with near-identical accuracy to full cloud processing.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Nishi Doshi, Shrey Shah","submitted_at":"2026-05-13T20:47:16Z","abstract_excerpt":"Diabetic Retinopathy (DR) is one of the leading causes of preventable blindness, yet rural regions often lack the specialists and infrastructure needed for early detection. Although cloud-based deep learning systems offer high accuracy, they face significant challenges in these settings due to high latency, limited bandwidth, and high data transmission costs. To address these challenges, we propose a two-tier edge-cloud cascade on the public APTOS 2019 Blindness Detection dataset. Tier 1 runs a lightweight MobileNetV3-small model on a local clinic device to perform a binary triage between Refe"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On a stratified APTOS test split of 733 images, Tier 1 reaches 98.99% sensitivity and 84.37% specificity; the cascade forwards 49.52% of images to Tier 2, reducing cloud calls by 50.48%, and obtains 80.49% accuracy and 0.8167 quadratic weighted kappa versus 80.76% and 0.8184 for cloud-only.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The validation-tuned high-sensitivity threshold for Tier 1 triage will maintain reliable performance and not miss referable cases when applied to real-world images from diverse populations, cameras, and lighting conditions outside the APTOS dataset.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A cascaded edge-cloud architecture for diabetic retinopathy screening uses local triage to cut cloud calls by 50% with only a minor drop in grading performance on the APTOS 2019 dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An edge-cloud cascade cuts cloud calls for diabetic retinopathy screening by half with near-identical accuracy to full cloud processing.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6197adad57c063d3d25783059896a934dfa5e9e128f95b1964eacc41fc283087"},"source":{"id":"2605.14108","kind":"arxiv","version":1},"verdict":{"id":"2ac48977-6af2-465b-84e7-9ce8c3b6fcf3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:17:03.234647Z","strongest_claim":"On a stratified APTOS test split of 733 images, Tier 1 reaches 98.99% sensitivity and 84.37% specificity; the cascade forwards 49.52% of images to Tier 2, reducing cloud calls by 50.48%, and obtains 80.49% accuracy and 0.8167 quadratic weighted kappa versus 80.76% and 0.8184 for cloud-only.","one_line_summary":"A cascaded edge-cloud architecture for diabetic retinopathy screening uses local triage to cut cloud calls by 50% with only a minor drop in grading performance on the APTOS 2019 dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The validation-tuned high-sensitivity threshold for Tier 1 triage will maintain reliable performance and not miss referable cases when applied to real-world images from diverse populations, cameras, and lighting conditions outside the APTOS dataset.","pith_extraction_headline":"An edge-cloud cascade cuts cloud calls for diabetic retinopathy screening by half with near-identical accuracy to full cloud processing."},"references":{"count":18,"sample":[{"doi":"","year":2045,"title":"Global prevalence of diabetic retinopathy and projection of burden through 2045: Systematic review and meta-analysis","work_id":"d018b5a9-8587-4135-9411-0b7b27bffc4a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Contrastive learning-based pretrain- ing improves representation and transferability of diabetic retinopathy classification models,","work_id":"0456e8b5-edba-4af1-8ff0-ec55e47a7c16","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"GBD 2019 Blindness and Vision Impairment Collaborators and Vision Loss Expert Group of the Global Burden of Disease Study, “Causes of blindness and vision impairment in 2020 and trends over 30 years, ","work_id":"c4b010c3-7d7f-4101-a517-0b2cf4df0dd4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2030,"title":"Global strategy on human resources for health: Workforce 2030 – a five-year check-in,","work_id":"6756a534-af21-44b3-86e5-aff7d09061c9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Barriers to digital health im- plementation in low- and middle-income countries: a narrative review,","work_id":"d710cf29-69a3-4f0b-9cec-dc2f0062a9d2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"0a1512888d9762f33456a730542a7654e66dd7646211daf2e7521e41cf6bb5ef","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2ac48977-6af2-465b-84e7-9ce8c3b6fcf3"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2Xa4U4Z277WAbjEJlz70g9zzCkmSPfyqxNvdD9d+QUXmvdwAhQGSZ9Di4PFRj3LsVk8ACUnrJy3HoLnMfSaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:45:32.127862Z"},"content_sha256":"2bae24a1dae420ccf5800b18e6b71909a17dc4040ee9a7e25e657edf39790980","schema_version":"1.0","event_id":"sha256:2bae24a1dae420ccf5800b18e6b71909a17dc4040ee9a7e25e657edf39790980"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJ2S7I7QZ3JEO3JJCGKNGZ3THD/bundle.json","state_url":"https://pith.science/pith/GJ2S7I7QZ3JEO3JJCGKNGZ3THD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJ2S7I7QZ3JEO3JJCGKNGZ3THD/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":"2026-05-26T19:45:32Z","links":{"resolver":"https://pith.science/pith/GJ2S7I7QZ3JEO3JJCGKNGZ3THD","bundle":"https://pith.science/pith/GJ2S7I7QZ3JEO3JJCGKNGZ3THD/bundle.json","state":"https://pith.science/pith/GJ2S7I7QZ3JEO3JJCGKNGZ3THD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJ2S7I7QZ3JEO3JJCGKNGZ3THD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GJ2S7I7QZ3JEO3JJCGKNGZ3THD","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":"5f4becdfd7f8a3c3e92a6c4cf9810603481465235bea0a6429ab06860e1a5ef1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T20:47:16Z","title_canon_sha256":"6a6221b5b336ccdbeb55cd2e46f1ae1b3ccbc8d97b15ae90fdc9bc31ae7e1fcb"},"schema_version":"1.0","source":{"id":"2605.14108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14108","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14108v1","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14108","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"GJ2S7I7QZ3JE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"GJ2S7I7QZ3JEO3JJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"GJ2S7I7Q","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2bae24a1dae420ccf5800b18e6b71909a17dc4040ee9a7e25e657edf39790980","target":"graph","created_at":"2026-05-17T23:39:12Z","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":"On a stratified APTOS test split of 733 images, Tier 1 reaches 98.99% sensitivity and 84.37% specificity; the cascade forwards 49.52% of images to Tier 2, reducing cloud calls by 50.48%, and obtains 80.49% accuracy and 0.8167 quadratic weighted kappa versus 80.76% and 0.8184 for cloud-only."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The validation-tuned high-sensitivity threshold for Tier 1 triage will maintain reliable performance and not miss referable cases when applied to real-world images from diverse populations, cameras, and lighting conditions outside the APTOS dataset."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A cascaded edge-cloud architecture for diabetic retinopathy screening uses local triage to cut cloud calls by 50% with only a minor drop in grading performance on the APTOS 2019 dataset."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An edge-cloud cascade cuts cloud calls for diabetic retinopathy screening by half with near-identical accuracy to full cloud processing."}],"snapshot_sha256":"6197adad57c063d3d25783059896a934dfa5e9e128f95b1964eacc41fc283087"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Diabetic Retinopathy (DR) is one of the leading causes of preventable blindness, yet rural regions often lack the specialists and infrastructure needed for early detection. Although cloud-based deep learning systems offer high accuracy, they face significant challenges in these settings due to high latency, limited bandwidth, and high data transmission costs. To address these challenges, we propose a two-tier edge-cloud cascade on the public APTOS 2019 Blindness Detection dataset. Tier 1 runs a lightweight MobileNetV3-small model on a local clinic device to perform a binary triage between Refe","authors_text":"Nishi Doshi, Shrey Shah","cross_cats":["cs.AI","cs.LG"],"headline":"An edge-cloud cascade cuts cloud calls for diabetic retinopathy screening by half with near-identical accuracy to full cloud processing.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T20:47:16Z","title":"Bridging the Rural Healthcare Gap: A Cascaded Edge-Cloud Architecture for Automated Retinal Screening"},"references":{"count":18,"internal_anchors":0,"resolved_work":18,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Global prevalence of diabetic retinopathy and projection of burden through 2045: Systematic review and meta-analysis","work_id":"d018b5a9-8587-4135-9411-0b7b27bffc4a","year":2045},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Contrastive learning-based pretrain- ing improves representation and transferability of diabetic retinopathy classification models,","work_id":"0456e8b5-edba-4af1-8ff0-ec55e47a7c16","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"GBD 2019 Blindness and Vision Impairment Collaborators and Vision Loss Expert Group of the Global Burden of Disease Study, “Causes of blindness and vision impairment in 2020 and trends over 30 years, ","work_id":"c4b010c3-7d7f-4101-a517-0b2cf4df0dd4","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Global strategy on human resources for health: Workforce 2030 – a five-year check-in,","work_id":"6756a534-af21-44b3-86e5-aff7d09061c9","year":2030},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Barriers to digital health im- plementation in low- and middle-income countries: a narrative review,","work_id":"d710cf29-69a3-4f0b-9cec-dc2f0062a9d2","year":2026}],"snapshot_sha256":"0a1512888d9762f33456a730542a7654e66dd7646211daf2e7521e41cf6bb5ef"},"source":{"id":"2605.14108","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:17:03.234647Z","id":"2ac48977-6af2-465b-84e7-9ce8c3b6fcf3","model_set":{"reader":"grok-4.3"},"one_line_summary":"A cascaded edge-cloud architecture for diabetic retinopathy screening uses local triage to cut cloud calls by 50% with only a minor drop in grading performance on the APTOS 2019 dataset.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"An edge-cloud cascade cuts cloud calls for diabetic retinopathy screening by half with near-identical accuracy to full cloud processing.","strongest_claim":"On a stratified APTOS test split of 733 images, Tier 1 reaches 98.99% sensitivity and 84.37% specificity; the cascade forwards 49.52% of images to Tier 2, reducing cloud calls by 50.48%, and obtains 80.49% accuracy and 0.8167 quadratic weighted kappa versus 80.76% and 0.8184 for cloud-only.","weakest_assumption":"The validation-tuned high-sensitivity threshold for Tier 1 triage will maintain reliable performance and not miss referable cases when applied to real-world images from diverse populations, cameras, and lighting conditions outside the APTOS dataset."}},"verdict_id":"2ac48977-6af2-465b-84e7-9ce8c3b6fcf3"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79154ac65be1a5149f89cd6b4cb4db6051c6311ac614be0654188aa8521112f0","target":"record","created_at":"2026-05-17T23:39:12Z","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":"5f4becdfd7f8a3c3e92a6c4cf9810603481465235bea0a6429ab06860e1a5ef1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T20:47:16Z","title_canon_sha256":"6a6221b5b336ccdbeb55cd2e46f1ae1b3ccbc8d97b15ae90fdc9bc31ae7e1fcb"},"schema_version":"1.0","source":{"id":"2605.14108","kind":"arxiv","version":1}},"canonical_sha256":"32752fa3f0ced2476d291194d3677338de1b91d9af5c0569bd42701747f3ca91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32752fa3f0ced2476d291194d3677338de1b91d9af5c0569bd42701747f3ca91","first_computed_at":"2026-05-17T23:39:12.029791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:12.029791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OThzA4zToQSeEcAM/nbjkK1sKoeIRf+WOZAsLAH1m3BImjjGML47u7aYNtBo61Y5TjLPbxNYmbsS54iOVMkCCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:12.030268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79154ac65be1a5149f89cd6b4cb4db6051c6311ac614be0654188aa8521112f0","sha256:2bae24a1dae420ccf5800b18e6b71909a17dc4040ee9a7e25e657edf39790980"],"state_sha256":"a7ee45b6ed0cf794a71cafbb340cb1b60fe23ddc9d6df275eee5b5241af340f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9C58E4YCK9PoRrauPDC6opT7Ue6gM+qEphR3H5hmAQXZk/Qq9wfPDcfdTqhffW+20gDV8Rqt9YAH0oPSChC/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:45:32.131435Z","bundle_sha256":"ee9726a58d5f7c75b3fe4dad2d5869cac7b46cda97b89f42e77c1bfee37c0eca"}}