{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4K5LTY6DUMKYSOYV6E37L6DU4U","short_pith_number":"pith:4K5LTY6D","canonical_record":{"source":{"id":"2605.16867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-16T08:01:12Z","cross_cats_sorted":[],"title_canon_sha256":"b88b84142799998f4d98141799b484dfbc48440cdb0ac02ba1bd43f9394ce499","abstract_canon_sha256":"9de61d8f61c93516055d2ec1b9f28f405fe1bacae8fb0d28683207dfbd3ca34b"},"schema_version":"1.0"},"canonical_sha256":"e2bab9e3c3a315893b15f137f5f874e53fd8b3089a2e38fef5a07010396a791e","source":{"kind":"arxiv","id":"2605.16867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16867","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16867v1","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16867","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"4K5LTY6DUMKY","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"4K5LTY6DUMKYSOYV","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"4K5LTY6D","created_at":"2026-05-20T00:03:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4K5LTY6DUMKYSOYV6E37L6DU4U","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-16T08:01:12Z","cross_cats_sorted":[],"title_canon_sha256":"b88b84142799998f4d98141799b484dfbc48440cdb0ac02ba1bd43f9394ce499","abstract_canon_sha256":"9de61d8f61c93516055d2ec1b9f28f405fe1bacae8fb0d28683207dfbd3ca34b"},"schema_version":"1.0"},"canonical_sha256":"e2bab9e3c3a315893b15f137f5f874e53fd8b3089a2e38fef5a07010396a791e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:27.276742Z","signature_b64":"4NiCxuhglRVh8kZG0iYwuy0o2F4m/EgE0GolXWWosgfKdGJjSSpUMNXMCrZBQoOD0pL2eemiPaaU75+yurDLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2bab9e3c3a315893b15f137f5f874e53fd8b3089a2e38fef5a07010396a791e","last_reissued_at":"2026-05-20T00:03:27.275821Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:27.275821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16867","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":"2026-05-20T00:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fikigO9E7H5vUOSNtgGmdNYZaIJBSnyvOvNoGrzzPqXUwCBPJgdEcQjWKW9iv63e6Aw6oU7PPa6sXjqe64u1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T19:32:05.031985Z"},"content_sha256":"ad4e9266c838ec635e8ed8e8cb7cb5b32e4d791256f7e9a7e8c74a7f063a55a2","schema_version":"1.0","event_id":"sha256:ad4e9266c838ec635e8ed8e8cb7cb5b32e4d791256f7e9a7e8c74a7f063a55a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4K5LTY6DUMKYSOYV6E37L6DU4U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GoodServe routes agentic LLM requests across heterogeneous GPUs with predict-and-rectify decisions to raise goodput.","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Boning Huangfu, Boxiao Du, Chen Chen, Minchen Yu, Minyi Guo, Xiaoyi Fan, Yizhou Luo, Zijun Li","submitted_at":"2026-05-16T08:01:12Z","abstract_excerpt":"Large Language Models (LLMs) play a critical role in emerging agentic applications, where the timely completion of each entire inference is critical. Meanwhile, agentic LLM inferences are increasingly served on heterogeneous GPUs in operator's resource pools. Therefore, it is crucial to route incoming inference requests to appropriate GPUs so that their end-to-end latency requirements are satisfied whenever possible, thereby achieving high goodput. In this paper, we propose GoodServe, a goodput-optimized serving system for agentic inferences over heterogeneous resources. GoodServe performs inf"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our evaluations show that GoodServe improves goodput by up to 27.4% over existing routing methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the estimates of request output lengths as well as the GPU serving status can be done in an accurate and also practical manner.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GoodServe proposes a predict-and-rectify routing system for agentic LLM inferences on heterogeneous GPUs that improves goodput by up to 27.4%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GoodServe routes agentic LLM requests across heterogeneous GPUs with predict-and-rectify decisions to raise goodput.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b944b4a4d3403ce01160ad54c67c53998aabf913d657d4b7e8ec6977c4f6d1ea"},"source":{"id":"2605.16867","kind":"arxiv","version":1},"verdict":{"id":"f794dad9-a483-4ef9-87fa-7b38c1d6e0cd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T19:27:25.350833Z","strongest_claim":"Our evaluations show that GoodServe improves goodput by up to 27.4% over existing routing methods.","one_line_summary":"GoodServe proposes a predict-and-rectify routing system for agentic LLM inferences on heterogeneous GPUs that improves goodput by up to 27.4%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the estimates of request output lengths as well as the GPU serving status can be done in an accurate and also practical manner.","pith_extraction_headline":"GoodServe routes agentic LLM requests across heterogeneous GPUs with predict-and-rectify decisions to raise goodput."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16867/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T20:01:18.987212Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:40:47.374662Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.300945Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.377030Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"bd9423e4404a7bdf27094b8ea571d902e4cc68580e6c49204abf945e089c83f9"},"references":{"count":40,"sample":[{"doi":"","year":2025,"title":"Efficient and scalable agentic ai with heteroge- neous systems.arXiv preprint arXiv:2507.19635, 2025","work_id":"e941b6ff-1d8f-46df-aee7-fe49bd8f1908","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Ai-powered chat agent: Revolutionizing online shopping","work_id":"f3107bf2-14dc-4f8f-bd84-22d4ce143807","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Optimal scheduling algorithms for llm inference: Theory and practice.Proceedings of the ACM on Measurement and Analysis of Computing Systems, 9(3):1–43, 2025","work_id":"244ce15f-7e54-4fdc-a05b-65e16b98b68f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"LiteLLM: Python sdk and proxy server for unified llm api access","work_id":"4bc84121-f005-4358-92e2-3ab69b438e0d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Slice: Slo-driven scheduling for llm inference on edge computing devices.arXiv preprint arXiv:2510.18544, 2025","work_id":"4371671e-5e18-4b5a-84cb-f78fa219fd6f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":40,"snapshot_sha256":"c247b95a72359524bf4427b8c98802b1e124bbc50baf574b5e9583e325454cd9","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5b15ecc8691c78fdf571484348b15a7afc0dc9dbfbb0657021c65825a45c5a98"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"f794dad9-a483-4ef9-87fa-7b38c1d6e0cd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WkdjWrc7rqzV6ZWroR7mYj3n8kgOna17LRbrAI6Rlwa12Uk5keLf0ggd+Fni3amqd4jTjCcknhn4vmrlc1KlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T19:32:05.033407Z"},"content_sha256":"85707c16fa9c1904e7715aa883c23df8541415e614897cecd45dd47b72ad89eb","schema_version":"1.0","event_id":"sha256:85707c16fa9c1904e7715aa883c23df8541415e614897cecd45dd47b72ad89eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4K5LTY6DUMKYSOYV6E37L6DU4U/bundle.json","state_url":"https://pith.science/pith/4K5LTY6DUMKYSOYV6E37L6DU4U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4K5LTY6DUMKYSOYV6E37L6DU4U/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":"2026-05-23T19:32:05Z","links":{"resolver":"https://pith.science/pith/4K5LTY6DUMKYSOYV6E37L6DU4U","bundle":"https://pith.science/pith/4K5LTY6DUMKYSOYV6E37L6DU4U/bundle.json","state":"https://pith.science/pith/4K5LTY6DUMKYSOYV6E37L6DU4U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4K5LTY6DUMKYSOYV6E37L6DU4U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4K5LTY6DUMKYSOYV6E37L6DU4U","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":"9de61d8f61c93516055d2ec1b9f28f405fe1bacae8fb0d28683207dfbd3ca34b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-16T08:01:12Z","title_canon_sha256":"b88b84142799998f4d98141799b484dfbc48440cdb0ac02ba1bd43f9394ce499"},"schema_version":"1.0","source":{"id":"2605.16867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16867","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16867v1","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16867","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"4K5LTY6DUMKY","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"4K5LTY6DUMKYSOYV","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"4K5LTY6D","created_at":"2026-05-20T00:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:85707c16fa9c1904e7715aa883c23df8541415e614897cecd45dd47b72ad89eb","target":"graph","created_at":"2026-05-20T00:03:27Z","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":"Our evaluations show that GoodServe improves goodput by up to 27.4% over existing routing methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the estimates of request output lengths as well as the GPU serving status can be done in an accurate and also practical manner."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GoodServe proposes a predict-and-rectify routing system for agentic LLM inferences on heterogeneous GPUs that improves goodput by up to 27.4%."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GoodServe routes agentic LLM requests across heterogeneous GPUs with predict-and-rectify decisions to raise goodput."}],"snapshot_sha256":"b944b4a4d3403ce01160ad54c67c53998aabf913d657d4b7e8ec6977c4f6d1ea"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5b15ecc8691c78fdf571484348b15a7afc0dc9dbfbb0657021c65825a45c5a98"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T20:01:18.987212Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:40:47.374662Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.300945Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.377030Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16867/integrity.json","findings":[],"snapshot_sha256":"bd9423e4404a7bdf27094b8ea571d902e4cc68580e6c49204abf945e089c83f9","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) play a critical role in emerging agentic applications, where the timely completion of each entire inference is critical. Meanwhile, agentic LLM inferences are increasingly served on heterogeneous GPUs in operator's resource pools. Therefore, it is crucial to route incoming inference requests to appropriate GPUs so that their end-to-end latency requirements are satisfied whenever possible, thereby achieving high goodput. In this paper, we propose GoodServe, a goodput-optimized serving system for agentic inferences over heterogeneous resources. GoodServe performs inf","authors_text":"Boning Huangfu, Boxiao Du, Chen Chen, Minchen Yu, Minyi Guo, Xiaoyi Fan, Yizhou Luo, Zijun Li","cross_cats":[],"headline":"GoodServe routes agentic LLM requests across heterogeneous GPUs with predict-and-rectify decisions to raise goodput.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-16T08:01:12Z","title":"GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources"},"references":{"count":40,"internal_anchors":9,"resolved_work":40,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Efficient and scalable agentic ai with heteroge- neous systems.arXiv preprint arXiv:2507.19635, 2025","work_id":"e941b6ff-1d8f-46df-aee7-fe49bd8f1908","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Ai-powered chat agent: Revolutionizing online shopping","work_id":"f3107bf2-14dc-4f8f-bd84-22d4ce143807","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Optimal scheduling algorithms for llm inference: Theory and practice.Proceedings of the ACM on Measurement and Analysis of Computing Systems, 9(3):1–43, 2025","work_id":"244ce15f-7e54-4fdc-a05b-65e16b98b68f","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"LiteLLM: Python sdk and proxy server for unified llm api access","work_id":"4bc84121-f005-4358-92e2-3ab69b438e0d","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Slice: Slo-driven scheduling for llm inference on edge computing devices.arXiv preprint arXiv:2510.18544, 2025","work_id":"4371671e-5e18-4b5a-84cb-f78fa219fd6f","year":2025}],"snapshot_sha256":"c247b95a72359524bf4427b8c98802b1e124bbc50baf574b5e9583e325454cd9"},"source":{"id":"2605.16867","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T19:27:25.350833Z","id":"f794dad9-a483-4ef9-87fa-7b38c1d6e0cd","model_set":{"reader":"grok-4.3"},"one_line_summary":"GoodServe proposes a predict-and-rectify routing system for agentic LLM inferences on heterogeneous GPUs that improves goodput by up to 27.4%.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GoodServe routes agentic LLM requests across heterogeneous GPUs with predict-and-rectify decisions to raise goodput.","strongest_claim":"Our evaluations show that GoodServe improves goodput by up to 27.4% over existing routing methods.","weakest_assumption":"That the estimates of request output lengths as well as the GPU serving status can be done in an accurate and also practical manner."}},"verdict_id":"f794dad9-a483-4ef9-87fa-7b38c1d6e0cd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ad4e9266c838ec635e8ed8e8cb7cb5b32e4d791256f7e9a7e8c74a7f063a55a2","target":"record","created_at":"2026-05-20T00:03:27Z","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":"9de61d8f61c93516055d2ec1b9f28f405fe1bacae8fb0d28683207dfbd3ca34b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-16T08:01:12Z","title_canon_sha256":"b88b84142799998f4d98141799b484dfbc48440cdb0ac02ba1bd43f9394ce499"},"schema_version":"1.0","source":{"id":"2605.16867","kind":"arxiv","version":1}},"canonical_sha256":"e2bab9e3c3a315893b15f137f5f874e53fd8b3089a2e38fef5a07010396a791e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2bab9e3c3a315893b15f137f5f874e53fd8b3089a2e38fef5a07010396a791e","first_computed_at":"2026-05-20T00:03:27.275821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:27.275821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4NiCxuhglRVh8kZG0iYwuy0o2F4m/EgE0GolXWWosgfKdGJjSSpUMNXMCrZBQoOD0pL2eemiPaaU75+yurDLCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:27.276742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad4e9266c838ec635e8ed8e8cb7cb5b32e4d791256f7e9a7e8c74a7f063a55a2","sha256:85707c16fa9c1904e7715aa883c23df8541415e614897cecd45dd47b72ad89eb"],"state_sha256":"5f9ad66ddab19e43debd5ee46d385d72ffb57a1c61ab8363c21dfc674a6cdb36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cBEI3ARao3BaUJ52HYOXpIRNmy8x2XM+xY/fASSKibLFjw3H+sejVfVDHYjBqt+dw8eRr3QX2aNSiKp0KG32Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T19:32:05.038921Z","bundle_sha256":"ef10f1846a76339d0eec174bcb3944f9d5370f443b6a9283c7e0fb1e9554cd82"}}