{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NXG3YUB63DWKQRSY6GSLMD7BBZ","short_pith_number":"pith:NXG3YUB6","canonical_record":{"source":{"id":"2605.13368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T11:27:32Z","cross_cats_sorted":[],"title_canon_sha256":"7fba05e92e83f58cdca23df1e608365ebbd229b69ac5c092d3a21d155f305bb5","abstract_canon_sha256":"e73be54613a7714e9038f97eb3d2f8c92d91c21ebfcb89d540e737cc39d30ba1"},"schema_version":"1.0"},"canonical_sha256":"6dcdbc503ed8eca84658f1a4b60fe10e4385a11635867779f50e2eb315dd9d0f","source":{"kind":"arxiv","id":"2605.13368","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13368","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13368v1","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13368","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"NXG3YUB63DWK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NXG3YUB63DWKQRSY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NXG3YUB6","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NXG3YUB63DWKQRSY6GSLMD7BBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T11:27:32Z","cross_cats_sorted":[],"title_canon_sha256":"7fba05e92e83f58cdca23df1e608365ebbd229b69ac5c092d3a21d155f305bb5","abstract_canon_sha256":"e73be54613a7714e9038f97eb3d2f8c92d91c21ebfcb89d540e737cc39d30ba1"},"schema_version":"1.0"},"canonical_sha256":"6dcdbc503ed8eca84658f1a4b60fe10e4385a11635867779f50e2eb315dd9d0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:48.028958Z","signature_b64":"PV0aICT/DB7aGDehjl+XujfO9KvW4jxPC18z50IYsU6XscGtBetUK5xQWtLTZpyT5JzYay9I23ZB04llNnU+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dcdbc503ed8eca84658f1a4b60fe10e4385a11635867779f50e2eb315dd9d0f","last_reissued_at":"2026-05-18T02:44:48.028504Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:48.028504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13368","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":"2026-05-18T02:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQ31V78wef8tABhLkEboLE21wQ9/ildhEshKQr1LPXOcof7tc127TMJ6TokXCFyoB4i/r/DCWSVS+NxkdmJkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:45:53.215337Z"},"content_sha256":"f25316638eb0e933c4a907998425e5b735afcc910b6a98be828b0cdb79997c8b","schema_version":"1.0","event_id":"sha256:f25316638eb0e933c4a907998425e5b735afcc910b6a98be828b0cdb79997c8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NXG3YUB63DWKQRSY6GSLMD7BBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Document-level translation followed by segment-level refinement produces the most reliable gains in literary machine translation.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bill Byrne, Dawei Zhu, Felix Hieber, Ke Tran, Leonardo Ribeiro, Michael Denkowski, Shaomu Tan, Sony Trenous","submitted_at":"2026-05-13T11:27:32Z","abstract_excerpt":"Iterative self-refinement is a simple inference-time strategy for machine translation: an LLM revises its own translation over multiple inference-time passes. Yet document-scale refinement remains poorly understood: 1) which pipelines work best, 2) what quality dimensions improve, and 3) how refiners behave. In this paper, we present a systematic study of document-level literary translation, covering nine LLMs and seven language pairs. Across nine translation-refinement granularity combinations and five refinement strategies, we find a robust recipe: document-level MT followed by segment-level"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across nine translation-refinement granularity combinations and five refinement strategies, we find a robust recipe: document-level MT followed by segment-level refinement yields strong and stable improvements. In contrast, document-level refinement often makes fewer edits and leads to smaller or less reliable gains.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the observed patterns in refinement behavior and quality dimensions will generalize beyond the specific nine LLMs, seven language pairs, and literary texts tested in the study.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Document-level translation followed by segment-level refinement produces the most reliable gains in literary machine translation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"372853385b851e2261c878e020a453774d824a5efe24c83e2871acfc9be8a274"},"source":{"id":"2605.13368","kind":"arxiv","version":1},"verdict":{"id":"3fcbbbbb-1b0a-4772-a3aa-0a65cc3e7f7e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:05:46.245306Z","strongest_claim":"Across nine translation-refinement granularity combinations and five refinement strategies, we find a robust recipe: document-level MT followed by segment-level refinement yields strong and stable improvements. In contrast, document-level refinement often makes fewer edits and leads to smaller or less reliable gains.","one_line_summary":"Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the observed patterns in refinement behavior and quality dimensions will generalize beyond the specific nine LLMs, seven language pairs, and literary texts tested in the study.","pith_extraction_headline":"Document-level translation followed by segment-level refinement produces the most reliable gains in literary machine translation."},"references":{"count":39,"sample":[{"doi":"10.18653/v1/2025.emnlp-main.1413","year":2025,"title":"Ademuyiwa, Andrew Caines, and Dietrich Klakow","work_id":"f5cdfa84-ebe3-406f-a41a-51b469c15afa","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Ramakrishna Appicharla, Baban Gain, Santanu Pal, and Asif Ekbal. 2025. https://arxiv.org/abs/2506.07583 Beyond the sentence: A survey on context-aware machine translation with large language models . ","work_id":"b432bd14-f865-4e99-8b6c-f0a9cb78167c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Eleftheria Briakou, Jiaming Luo, Colin Cherry, and Markus Freitag. 2024. Translating step-by-step: Decomposing the translation process for improved translation quality of long-form texts. In Proceedin","work_id":"9841de3c-da80-4737-b80f-9d75294aaca0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Pinzhen Chen, Zhicheng Guo, Barry Haddow, and Kenneth Heafield. 2024. Iterative translation refinement with large language models. In Proceedings of the 25th Annual Conference of the European Associat","work_id":"f47937df-e0b3-4ed4-ab92-890fb6573160","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","ref_index":5,"cited_arxiv_id":"2501.12948","is_internal_anchor":true}],"resolved_work":39,"snapshot_sha256":"e19530d1d8c21450168f9fe2697d2abc006f47585c3d8fa2aff09c7644ac9a2f","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"95a5339eab7da04dda0e7afef2637fd00aee7710a56653efa461b334e242abd8"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"3fcbbbbb-1b0a-4772-a3aa-0a65cc3e7f7e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pb23hpahBBV87pFpl9UXAC3dceOG4YMUWNBYbusMPCOrcC+L4w2gs1tUHv6gnMJWS+5+qghT5LcBsoqtmyPPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:45:53.216337Z"},"content_sha256":"29ae54d96c9265211073781102303a47592d2746ee7d7ad6a41b2bb4feec2975","schema_version":"1.0","event_id":"sha256:29ae54d96c9265211073781102303a47592d2746ee7d7ad6a41b2bb4feec2975"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NXG3YUB63DWKQRSY6GSLMD7BBZ/bundle.json","state_url":"https://pith.science/pith/NXG3YUB63DWKQRSY6GSLMD7BBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NXG3YUB63DWKQRSY6GSLMD7BBZ/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":"2026-05-30T13:45:53Z","links":{"resolver":"https://pith.science/pith/NXG3YUB63DWKQRSY6GSLMD7BBZ","bundle":"https://pith.science/pith/NXG3YUB63DWKQRSY6GSLMD7BBZ/bundle.json","state":"https://pith.science/pith/NXG3YUB63DWKQRSY6GSLMD7BBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NXG3YUB63DWKQRSY6GSLMD7BBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NXG3YUB63DWKQRSY6GSLMD7BBZ","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":"e73be54613a7714e9038f97eb3d2f8c92d91c21ebfcb89d540e737cc39d30ba1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T11:27:32Z","title_canon_sha256":"7fba05e92e83f58cdca23df1e608365ebbd229b69ac5c092d3a21d155f305bb5"},"schema_version":"1.0","source":{"id":"2605.13368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13368","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13368v1","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13368","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"NXG3YUB63DWK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NXG3YUB63DWKQRSY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NXG3YUB6","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:29ae54d96c9265211073781102303a47592d2746ee7d7ad6a41b2bb4feec2975","target":"graph","created_at":"2026-05-18T02:44:48Z","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":"Across nine translation-refinement granularity combinations and five refinement strategies, we find a robust recipe: document-level MT followed by segment-level refinement yields strong and stable improvements. In contrast, document-level refinement often makes fewer edits and leads to smaller or less reliable gains."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the observed patterns in refinement behavior and quality dimensions will generalize beyond the specific nine LLMs, seven language pairs, and literary texts tested in the study."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Document-level translation followed by segment-level refinement produces the most reliable gains in literary machine translation."}],"snapshot_sha256":"372853385b851e2261c878e020a453774d824a5efe24c83e2871acfc9be8a274"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"95a5339eab7da04dda0e7afef2637fd00aee7710a56653efa461b334e242abd8"},"paper":{"abstract_excerpt":"Iterative self-refinement is a simple inference-time strategy for machine translation: an LLM revises its own translation over multiple inference-time passes. Yet document-scale refinement remains poorly understood: 1) which pipelines work best, 2) what quality dimensions improve, and 3) how refiners behave. In this paper, we present a systematic study of document-level literary translation, covering nine LLMs and seven language pairs. Across nine translation-refinement granularity combinations and five refinement strategies, we find a robust recipe: document-level MT followed by segment-level","authors_text":"Bill Byrne, Dawei Zhu, Felix Hieber, Ke Tran, Leonardo Ribeiro, Michael Denkowski, Shaomu Tan, Sony Trenous","cross_cats":[],"headline":"Document-level translation followed by segment-level refinement produces the most reliable gains in literary machine translation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T11:27:32Z","title":"What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation"},"references":{"count":39,"internal_anchors":5,"resolved_work":39,"sample":[{"cited_arxiv_id":"","doi":"10.18653/v1/2025.emnlp-main.1413","is_internal_anchor":false,"ref_index":1,"title":"Ademuyiwa, Andrew Caines, and Dietrich Klakow","work_id":"f5cdfa84-ebe3-406f-a41a-51b469c15afa","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Ramakrishna Appicharla, Baban Gain, Santanu Pal, and Asif Ekbal. 2025. https://arxiv.org/abs/2506.07583 Beyond the sentence: A survey on context-aware machine translation with large language models . ","work_id":"b432bd14-f865-4e99-8b6c-f0a9cb78167c","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Eleftheria Briakou, Jiaming Luo, Colin Cherry, and Markus Freitag. 2024. Translating step-by-step: Decomposing the translation process for improved translation quality of long-form texts. In Proceedin","work_id":"9841de3c-da80-4737-b80f-9d75294aaca0","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Pinzhen Chen, Zhicheng Guo, Barry Haddow, and Kenneth Heafield. 2024. Iterative translation refinement with large language models. In Proceedings of the 25th Annual Conference of the European Associat","work_id":"f47937df-e0b3-4ed4-ab92-890fb6573160","year":2024},{"cited_arxiv_id":"2501.12948","doi":"","is_internal_anchor":true,"ref_index":5,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","year":2025}],"snapshot_sha256":"e19530d1d8c21450168f9fe2697d2abc006f47585c3d8fa2aff09c7644ac9a2f"},"source":{"id":"2605.13368","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:05:46.245306Z","id":"3fcbbbbb-1b0a-4772-a3aa-0a65cc3e7f7e","model_set":{"reader":"grok-4.3"},"one_line_summary":"Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Document-level translation followed by segment-level refinement produces the most reliable gains in literary machine translation.","strongest_claim":"Across nine translation-refinement granularity combinations and five refinement strategies, we find a robust recipe: document-level MT followed by segment-level refinement yields strong and stable improvements. In contrast, document-level refinement often makes fewer edits and leads to smaller or less reliable gains.","weakest_assumption":"The assumption that the observed patterns in refinement behavior and quality dimensions will generalize beyond the specific nine LLMs, seven language pairs, and literary texts tested in the study."}},"verdict_id":"3fcbbbbb-1b0a-4772-a3aa-0a65cc3e7f7e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f25316638eb0e933c4a907998425e5b735afcc910b6a98be828b0cdb79997c8b","target":"record","created_at":"2026-05-18T02:44:48Z","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":"e73be54613a7714e9038f97eb3d2f8c92d91c21ebfcb89d540e737cc39d30ba1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T11:27:32Z","title_canon_sha256":"7fba05e92e83f58cdca23df1e608365ebbd229b69ac5c092d3a21d155f305bb5"},"schema_version":"1.0","source":{"id":"2605.13368","kind":"arxiv","version":1}},"canonical_sha256":"6dcdbc503ed8eca84658f1a4b60fe10e4385a11635867779f50e2eb315dd9d0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dcdbc503ed8eca84658f1a4b60fe10e4385a11635867779f50e2eb315dd9d0f","first_computed_at":"2026-05-18T02:44:48.028504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:48.028504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PV0aICT/DB7aGDehjl+XujfO9KvW4jxPC18z50IYsU6XscGtBetUK5xQWtLTZpyT5JzYay9I23ZB04llNnU+Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:48.028958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f25316638eb0e933c4a907998425e5b735afcc910b6a98be828b0cdb79997c8b","sha256:29ae54d96c9265211073781102303a47592d2746ee7d7ad6a41b2bb4feec2975"],"state_sha256":"bda28370e45fc12f5a30fa32d7a47af84dcc34e56c98a12c3895d9901003dae8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T4kNpBsRXIoANYTj+xKa8u1g2bLaHINSFjRgC9/aKh3wooMUXtQjj+zd2z2fVQyAx0ATGUcuSRdTqATY8zPwBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:45:53.220631Z","bundle_sha256":"9d9e731a71fcb98f9c7d07f0c41601ab2f9744973a70f0f77106cd1a01a39ba9"}}