{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LRAFZOQ3XVEAFU4ICVSRUH7GAC","short_pith_number":"pith:LRAFZOQ3","canonical_record":{"source":{"id":"2605.15215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T09:25:25Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"aed4f347a90ff71451c9203a3f07c72dd0d9d726d995daa7603beca7db96f8c0","abstract_canon_sha256":"a77aced08f6a82e033946ac1a51cbcdfdbcca0b2542e5663e3304a00369b48af"},"schema_version":"1.0"},"canonical_sha256":"5c405cba1bbd4802d38815651a1fe6008c28210b2ed35182e057bc2e3ac2a38c","source":{"kind":"arxiv","id":"2605.15215","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15215","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15215v1","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15215","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"LRAFZOQ3XVEA","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"LRAFZOQ3XVEAFU4I","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"LRAFZOQ3","created_at":"2026-05-20T00:00:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LRAFZOQ3XVEAFU4ICVSRUH7GAC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T09:25:25Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"aed4f347a90ff71451c9203a3f07c72dd0d9d726d995daa7603beca7db96f8c0","abstract_canon_sha256":"a77aced08f6a82e033946ac1a51cbcdfdbcca0b2542e5663e3304a00369b48af"},"schema_version":"1.0"},"canonical_sha256":"5c405cba1bbd4802d38815651a1fe6008c28210b2ed35182e057bc2e3ac2a38c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:46.683492Z","signature_b64":"MdzwZdltTMG72c11uSRndYBg2wEGF32A3RfHIe00pYoRCwmuln9A6nQu95R9ILzkuth98C03HH0sZ6bBHOHtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c405cba1bbd4802d38815651a1fe6008c28210b2ed35182e057bc2e3ac2a38c","last_reissued_at":"2026-05-20T00:00:46.682544Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:46.682544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15215","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":"2026-05-20T00:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/AtOG4Ihr27kcGyWGBSQ4QdvY0IB5JR97QVfB7DcHwthGgXS3vFuRL8R0fI9hrWmo00wZblyIVYZF2z/R3i+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:55:51.291215Z"},"content_sha256":"4cdd341678c44919ac08357d1dc51abb6e5eed59020eaea64d734f4fc2449996","schema_version":"1.0","event_id":"sha256:4cdd341678c44919ac08357d1dc51abb6e5eed59020eaea64d734f4fc2449996"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LRAFZOQ3XVEAFU4ICVSRUH7GAC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SkillSmith compiles agent skills offline into minimal boundary-guided interfaces to cut redundant context and reasoning in LLM systems.","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Bangzheng Pu, Dong Dong, Duling Xu, Jialin Li, Jiawei Guan, Zaifeng Pan, Zheng Chen","submitted_at":"2026-05-12T09:25:25Z","abstract_excerpt":"Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a runtime task, enabling specialized task-solving capabilities. We find that this execution paradigm introduces two major sources of redundancy: irrelevant context injection and repeated skill-specific reasoning and planning. To this end, we propose SkillSmith, a boundary-first compiler-runtime framework that compiles skill packages offline into minimal execu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On SkillsBench, SkillSmith reduces solve-stage token usage by 57.44%, thinking iterations by 42.99%, solve time by 50.57% (2.02x faster), and token-proportional monetary cost by 57.44% compared with using raw-skills; compiled artifacts from a stronger model can be reused by a smaller runtime model to improve accuracy where raw skill interpretation fails.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The extraction of fine-grained operational boundaries from skill descriptions is both feasible and lossless enough that the resulting minimal interfaces preserve all task-relevant behavior without requiring the agent to fall back to full skill text.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SkillSmith is a boundary-first compiler-runtime system that turns skill packages into minimal executable interfaces, cutting token usage 57%, thinking iterations 43%, and solve time 51% versus raw skill injection on SkillsBench.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SkillSmith compiles agent skills offline into minimal boundary-guided interfaces to cut redundant context and reasoning in LLM systems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"575824838ed80ff472abaf7d076922e3a5f7b8b66b6c2cca008ce8ff205b6778"},"source":{"id":"2605.15215","kind":"arxiv","version":1},"verdict":{"id":"2079733b-b3aa-410d-a593-d1065c919116","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:50:08.857771Z","strongest_claim":"On SkillsBench, SkillSmith reduces solve-stage token usage by 57.44%, thinking iterations by 42.99%, solve time by 50.57% (2.02x faster), and token-proportional monetary cost by 57.44% compared with using raw-skills; compiled artifacts from a stronger model can be reused by a smaller runtime model to improve accuracy where raw skill interpretation fails.","one_line_summary":"SkillSmith is a boundary-first compiler-runtime system that turns skill packages into minimal executable interfaces, cutting token usage 57%, thinking iterations 43%, and solve time 51% versus raw skill injection on SkillsBench.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The extraction of fine-grained operational boundaries from skill descriptions is both feasible and lossless enough that the resulting minimal interfaces preserve all task-relevant behavior without requiring the agent to fall back to full skill text.","pith_extraction_headline":"SkillSmith compiles agent skills offline into minimal boundary-guided interfaces to cut redundant context and reasoning in LLM systems."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15215/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T18:01:24.804510Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.640644Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.839651Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"93c4973eeed9fbaba3e014d7667dc3cca130ec10da48c80aff2f93d12b95bdd8"},"references":{"count":30,"sample":[{"doi":"","year":2022,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":1,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":null,"title":"Equipping agents for the real world with agent skills","work_id":"15cf6aa2-3f42-4207-967f-8d42e48599ae","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Agent skills","work_id":"22265264-de03-49d5-945e-0a4ae54442d2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Introducing Claude Opus 4.7","work_id":"0e72af39-e73a-4a5b-95dd-11107a91b2db","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1946,"title":"Prompting is programming: A query language for large language models.Proceedings of the ACM on Programming Languages, 7(PLDI):1946–1969, 2023","work_id":"2cb96ab5-06a8-4123-a061-292a5607e8cd","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":30,"snapshot_sha256":"37e78531853d0ccb8f7f3700f81fe4af35a188830765066857aa83d5e18ea29e","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ba5b942f6840c553204c1cee4a17301b03ce675c022b3dfeb4d40d63e2089cbe"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2079733b-b3aa-410d-a593-d1065c919116"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/lmHRgxucXGpo12JRTjeJ4c71lbJRKoEO9kYLZEgQLcFhoEPGjCsnY4T4mXFUzmrLporIjmEJtqK3IIG5SCsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:55:51.291972Z"},"content_sha256":"4fe74a2898e28e9794d49915dfe33e16255e27df42c9c1d9b77886012e754907","schema_version":"1.0","event_id":"sha256:4fe74a2898e28e9794d49915dfe33e16255e27df42c9c1d9b77886012e754907"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LRAFZOQ3XVEAFU4ICVSRUH7GAC/bundle.json","state_url":"https://pith.science/pith/LRAFZOQ3XVEAFU4ICVSRUH7GAC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LRAFZOQ3XVEAFU4ICVSRUH7GAC/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":"2026-05-25T22:55:51Z","links":{"resolver":"https://pith.science/pith/LRAFZOQ3XVEAFU4ICVSRUH7GAC","bundle":"https://pith.science/pith/LRAFZOQ3XVEAFU4ICVSRUH7GAC/bundle.json","state":"https://pith.science/pith/LRAFZOQ3XVEAFU4ICVSRUH7GAC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LRAFZOQ3XVEAFU4ICVSRUH7GAC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LRAFZOQ3XVEAFU4ICVSRUH7GAC","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":"a77aced08f6a82e033946ac1a51cbcdfdbcca0b2542e5663e3304a00369b48af","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T09:25:25Z","title_canon_sha256":"aed4f347a90ff71451c9203a3f07c72dd0d9d726d995daa7603beca7db96f8c0"},"schema_version":"1.0","source":{"id":"2605.15215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15215","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15215v1","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15215","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"LRAFZOQ3XVEA","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"LRAFZOQ3XVEAFU4I","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"LRAFZOQ3","created_at":"2026-05-20T00:00:46Z"}],"graph_snapshots":[{"event_id":"sha256:4fe74a2898e28e9794d49915dfe33e16255e27df42c9c1d9b77886012e754907","target":"graph","created_at":"2026-05-20T00:00:46Z","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":"On SkillsBench, SkillSmith reduces solve-stage token usage by 57.44%, thinking iterations by 42.99%, solve time by 50.57% (2.02x faster), and token-proportional monetary cost by 57.44% compared with using raw-skills; compiled artifacts from a stronger model can be reused by a smaller runtime model to improve accuracy where raw skill interpretation fails."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The extraction of fine-grained operational boundaries from skill descriptions is both feasible and lossless enough that the resulting minimal interfaces preserve all task-relevant behavior without requiring the agent to fall back to full skill text."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SkillSmith is a boundary-first compiler-runtime system that turns skill packages into minimal executable interfaces, cutting token usage 57%, thinking iterations 43%, and solve time 51% versus raw skill injection on SkillsBench."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SkillSmith compiles agent skills offline into minimal boundary-guided interfaces to cut redundant context and reasoning in LLM systems."}],"snapshot_sha256":"575824838ed80ff472abaf7d076922e3a5f7b8b66b6c2cca008ce8ff205b6778"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ba5b942f6840c553204c1cee4a17301b03ce675c022b3dfeb4d40d63e2089cbe"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:01:24.804510Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.640644Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.839651Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15215/integrity.json","findings":[],"snapshot_sha256":"93c4973eeed9fbaba3e014d7667dc3cca130ec10da48c80aff2f93d12b95bdd8","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a runtime task, enabling specialized task-solving capabilities. We find that this execution paradigm introduces two major sources of redundancy: irrelevant context injection and repeated skill-specific reasoning and planning. To this end, we propose SkillSmith, a boundary-first compiler-runtime framework that compiles skill packages offline into minimal execu","authors_text":"Bangzheng Pu, Dong Dong, Duling Xu, Jialin Li, Jiawei Guan, Zaifeng Pan, Zheng Chen","cross_cats":["cs.SE"],"headline":"SkillSmith compiles agent skills offline into minimal boundary-guided interfaces to cut redundant context and reasoning in LLM systems.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T09:25:25Z","title":"SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces"},"references":{"count":30,"internal_anchors":7,"resolved_work":30,"sample":[{"cited_arxiv_id":"2204.01691","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Equipping agents for the real world with agent skills","work_id":"15cf6aa2-3f42-4207-967f-8d42e48599ae","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Agent skills","work_id":"22265264-de03-49d5-945e-0a4ae54442d2","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Introducing Claude Opus 4.7","work_id":"0e72af39-e73a-4a5b-95dd-11107a91b2db","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Prompting is programming: A query language for large language models.Proceedings of the ACM on Programming Languages, 7(PLDI):1946–1969, 2023","work_id":"2cb96ab5-06a8-4123-a061-292a5607e8cd","year":1946}],"snapshot_sha256":"37e78531853d0ccb8f7f3700f81fe4af35a188830765066857aa83d5e18ea29e"},"source":{"id":"2605.15215","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T17:50:08.857771Z","id":"2079733b-b3aa-410d-a593-d1065c919116","model_set":{"reader":"grok-4.3"},"one_line_summary":"SkillSmith is a boundary-first compiler-runtime system that turns skill packages into minimal executable interfaces, cutting token usage 57%, thinking iterations 43%, and solve time 51% versus raw skill injection on SkillsBench.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SkillSmith compiles agent skills offline into minimal boundary-guided interfaces to cut redundant context and reasoning in LLM systems.","strongest_claim":"On SkillsBench, SkillSmith reduces solve-stage token usage by 57.44%, thinking iterations by 42.99%, solve time by 50.57% (2.02x faster), and token-proportional monetary cost by 57.44% compared with using raw-skills; compiled artifacts from a stronger model can be reused by a smaller runtime model to improve accuracy where raw skill interpretation fails.","weakest_assumption":"The extraction of fine-grained operational boundaries from skill descriptions is both feasible and lossless enough that the resulting minimal interfaces preserve all task-relevant behavior without requiring the agent to fall back to full skill text."}},"verdict_id":"2079733b-b3aa-410d-a593-d1065c919116"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4cdd341678c44919ac08357d1dc51abb6e5eed59020eaea64d734f4fc2449996","target":"record","created_at":"2026-05-20T00:00:46Z","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":"a77aced08f6a82e033946ac1a51cbcdfdbcca0b2542e5663e3304a00369b48af","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T09:25:25Z","title_canon_sha256":"aed4f347a90ff71451c9203a3f07c72dd0d9d726d995daa7603beca7db96f8c0"},"schema_version":"1.0","source":{"id":"2605.15215","kind":"arxiv","version":1}},"canonical_sha256":"5c405cba1bbd4802d38815651a1fe6008c28210b2ed35182e057bc2e3ac2a38c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c405cba1bbd4802d38815651a1fe6008c28210b2ed35182e057bc2e3ac2a38c","first_computed_at":"2026-05-20T00:00:46.682544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:46.682544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MdzwZdltTMG72c11uSRndYBg2wEGF32A3RfHIe00pYoRCwmuln9A6nQu95R9ILzkuth98C03HH0sZ6bBHOHtCg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:46.683492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cdd341678c44919ac08357d1dc51abb6e5eed59020eaea64d734f4fc2449996","sha256:4fe74a2898e28e9794d49915dfe33e16255e27df42c9c1d9b77886012e754907"],"state_sha256":"0c6ac1d58189e260c8b6c0977ce48a4a319d3241c0a5b5e08573fd960d0aebda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KImIAm/J5xk0o7tWj5mZavVRCZcbn6fsINjJ+21yti4l68N8hzvVfggNODjxditcgJMNPmDHZFgMNallbjTECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:55:51.295913Z","bundle_sha256":"452f516e3ec86a7ffcaca4bd468a89cf6eacb7ea23da486f40d94a5124c00e3d"}}