{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BD6QRVPDQMXYDLIYGLHPGSIEQ5","short_pith_number":"pith:BD6QRVPD","canonical_record":{"source":{"id":"2605.15246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T10:57:34Z","cross_cats_sorted":[],"title_canon_sha256":"b4b6075aa543763a76f44a984f8635c4f6a9b0e5aa98a504f73fc6f0b6366858","abstract_canon_sha256":"eba8f1801d42538c52a3d4f015a4f69eee6e60c6011e6199dbd1cb0131d1a19d"},"schema_version":"1.0"},"canonical_sha256":"08fd08d5e3832f81ad1832cef349048779cbb18dee499062c07cf6886c2a2f37","source":{"kind":"arxiv","id":"2605.15246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15246","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15246v1","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15246","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"pith_short_12","alias_value":"BD6QRVPDQMXY","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"pith_short_16","alias_value":"BD6QRVPDQMXYDLIY","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"pith_short_8","alias_value":"BD6QRVPD","created_at":"2026-05-20T00:00:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BD6QRVPDQMXYDLIYGLHPGSIEQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T10:57:34Z","cross_cats_sorted":[],"title_canon_sha256":"b4b6075aa543763a76f44a984f8635c4f6a9b0e5aa98a504f73fc6f0b6366858","abstract_canon_sha256":"eba8f1801d42538c52a3d4f015a4f69eee6e60c6011e6199dbd1cb0131d1a19d"},"schema_version":"1.0"},"canonical_sha256":"08fd08d5e3832f81ad1832cef349048779cbb18dee499062c07cf6886c2a2f37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:48.282547Z","signature_b64":"LjSymMc1TI83X7tkZuM37A2iqNoDkKrnLLGZJPZV3YA3v6g0sYF8a2MdL5cIgZu9uCOsaUNHrHKeuoTHA9ntCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08fd08d5e3832f81ad1832cef349048779cbb18dee499062c07cf6886c2a2f37","last_reissued_at":"2026-05-20T00:00:48.281378Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:48.281378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15246","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":"2026-05-20T00:00:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6roq/GbZCzqocIF9y5p+6f6iYWrVwBh9H49XSSr3hyo1Mei7AzZ5DOgEDqWWKHoaESAFMkMNVsnujCM7AgO7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T11:35:31.370934Z"},"content_sha256":"b9234c7d8ed8544eba6d6380b4dd875acbecdf8397a50d50f8d414970d49df09","schema_version":"1.0","event_id":"sha256:b9234c7d8ed8544eba6d6380b4dd875acbecdf8397a50d50f8d414970d49df09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BD6QRVPDQMXYDLIYGLHPGSIEQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Privacy Evaluation of Generative Models for Trajectory Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Generative models do not guarantee privacy for synthetic trajectory data","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chiara Pugliese, Chiara Renso, Emanuele Carlini, Francesco Lettich, Hanna Kavalionak, Ioannis Kontopoulos, Konstantinos Tserpes, Stavros Bouras","submitted_at":"2026-05-14T10:57:34Z","abstract_excerpt":"Trajectory data is fundamental to modern urban intelligence, yet its sensitivity raises significant privacy concerns. Generative models such as Generative Adversarial Networks, Variational Autoencoders, and Diffusion Models have been developed to generate realistic synthetic trajectory data by capturing underlying spatiotemporal distributions and mobility patterns. Although these models are often assumed to preserve privacy due to their generative nature, this assumption does not necessarily hold. In this work, we investigate the intersection of generative trajectory modeling and privacy evalu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Although these models are often assumed to preserve privacy due to their generative nature, this assumption does not necessarily hold, as demonstrated by the feasibility of using Membership Inference Attacks against representative models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That standard membership inference attack methods are directly applicable to trajectory generation tasks and that success on the chosen representative models indicates general privacy leakage risks across generative trajectory approaches.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Generative models for trajectory data do not inherently preserve privacy, as membership inference attacks can identify training data points in representative models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Generative models do not guarantee privacy for synthetic trajectory data","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c8274507458e87cd8d2ad8867aa68c76ac6b39ba7d22d5d82a9ba2df2d305320"},"source":{"id":"2605.15246","kind":"arxiv","version":1},"verdict":{"id":"2373dd91-b232-48f9-85a5-6b6b32fc0466","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:17:43.836005Z","strongest_claim":"Although these models are often assumed to preserve privacy due to their generative nature, this assumption does not necessarily hold, as demonstrated by the feasibility of using Membership Inference Attacks against representative models.","one_line_summary":"Generative models for trajectory data do not inherently preserve privacy, as membership inference attacks can identify training data points in representative models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That standard membership inference attack methods are directly applicable to trajectory generation tasks and that success on the chosen representative models indicates general privacy leakage risks across generative trajectory approaches.","pith_extraction_headline":"Generative models do not guarantee privacy for synthetic trajectory data"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15246/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.448589Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:27:10.784070Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T15:41:54.403358Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.820105Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fd65f836d43fa1408029f34fc65ce785a2bea3acd05593dc94777a6b59cfaff3"},"references":{"count":48,"sample":[{"doi":"","year":2013,"title":"Unique in the crowd: The privacy bounds of human mobility,","work_id":"4a7cf281-bc0e-4a60-aa11-5b1ee5d9b38c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Trajectory generation: a survey on methods and techniques,","work_id":"48a50ed1-fef0-440a-8a61-8998a15deedc","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"The secret sharer: Evaluating and testing unintended memorization in neural net- works,","work_id":"dd43f494-cf0c-46cc-8132-bb76780bbb25","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Sok: Can trajectory generation combine privacy and utility?","work_id":"db4e3255-337f-43ef-8227-59fe5a310447","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Mobility trajectory generation: a survey,","work_id":"a675eb6c-6692-4f88-88dd-322260ccf28a","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":48,"snapshot_sha256":"86fb9066835e9069be0cc49a0521a97b1e6ae58381d86215313f5a7e6cc3f06b","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f2a8fd4360cadc70450c105ec6623026c5d3dab71d4cf23e6dbb7782f7375e43"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2373dd91-b232-48f9-85a5-6b6b32fc0466"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pnbYt2AeoBWpas0QNeW/+6c0fm7MGxAG3R2cdULpPLR3vEcq156aFDAKO41dxTPzeV77Inf0A3BbjgWw9P8jBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T11:35:31.372123Z"},"content_sha256":"1fc32f517b1043b7d11aaad4c3c6f80040bd26354c09337de4430a2b948bf34b","schema_version":"1.0","event_id":"sha256:1fc32f517b1043b7d11aaad4c3c6f80040bd26354c09337de4430a2b948bf34b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BD6QRVPDQMXYDLIYGLHPGSIEQ5/bundle.json","state_url":"https://pith.science/pith/BD6QRVPDQMXYDLIYGLHPGSIEQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BD6QRVPDQMXYDLIYGLHPGSIEQ5/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":"2026-05-23T11:35:31Z","links":{"resolver":"https://pith.science/pith/BD6QRVPDQMXYDLIYGLHPGSIEQ5","bundle":"https://pith.science/pith/BD6QRVPDQMXYDLIYGLHPGSIEQ5/bundle.json","state":"https://pith.science/pith/BD6QRVPDQMXYDLIYGLHPGSIEQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BD6QRVPDQMXYDLIYGLHPGSIEQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BD6QRVPDQMXYDLIYGLHPGSIEQ5","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":"eba8f1801d42538c52a3d4f015a4f69eee6e60c6011e6199dbd1cb0131d1a19d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T10:57:34Z","title_canon_sha256":"b4b6075aa543763a76f44a984f8635c4f6a9b0e5aa98a504f73fc6f0b6366858"},"schema_version":"1.0","source":{"id":"2605.15246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15246","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15246v1","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15246","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"pith_short_12","alias_value":"BD6QRVPDQMXY","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"pith_short_16","alias_value":"BD6QRVPDQMXYDLIY","created_at":"2026-05-20T00:00:48Z"},{"alias_kind":"pith_short_8","alias_value":"BD6QRVPD","created_at":"2026-05-20T00:00:48Z"}],"graph_snapshots":[{"event_id":"sha256:1fc32f517b1043b7d11aaad4c3c6f80040bd26354c09337de4430a2b948bf34b","target":"graph","created_at":"2026-05-20T00:00:48Z","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":"Although these models are often assumed to preserve privacy due to their generative nature, this assumption does not necessarily hold, as demonstrated by the feasibility of using Membership Inference Attacks against representative models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That standard membership inference attack methods are directly applicable to trajectory generation tasks and that success on the chosen representative models indicates general privacy leakage risks across generative trajectory approaches."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Generative models for trajectory data do not inherently preserve privacy, as membership inference attacks can identify training data points in representative models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Generative models do not guarantee privacy for synthetic trajectory data"}],"snapshot_sha256":"c8274507458e87cd8d2ad8867aa68c76ac6b39ba7d22d5d82a9ba2df2d305320"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f2a8fd4360cadc70450c105ec6623026c5d3dab71d4cf23e6dbb7782f7375e43"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.448589Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:27:10.784070Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T15:41:54.403358Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.820105Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15246/integrity.json","findings":[],"snapshot_sha256":"fd65f836d43fa1408029f34fc65ce785a2bea3acd05593dc94777a6b59cfaff3","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Trajectory data is fundamental to modern urban intelligence, yet its sensitivity raises significant privacy concerns. Generative models such as Generative Adversarial Networks, Variational Autoencoders, and Diffusion Models have been developed to generate realistic synthetic trajectory data by capturing underlying spatiotemporal distributions and mobility patterns. Although these models are often assumed to preserve privacy due to their generative nature, this assumption does not necessarily hold. In this work, we investigate the intersection of generative trajectory modeling and privacy evalu","authors_text":"Chiara Pugliese, Chiara Renso, Emanuele Carlini, Francesco Lettich, Hanna Kavalionak, Ioannis Kontopoulos, Konstantinos Tserpes, Stavros Bouras","cross_cats":[],"headline":"Generative models do not guarantee privacy for synthetic trajectory data","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T10:57:34Z","title":"Privacy Evaluation of Generative Models for Trajectory Generation"},"references":{"count":48,"internal_anchors":3,"resolved_work":48,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Unique in the crowd: The privacy bounds of human mobility,","work_id":"4a7cf281-bc0e-4a60-aa11-5b1ee5d9b38c","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Trajectory generation: a survey on methods and techniques,","work_id":"48a50ed1-fef0-440a-8a61-8998a15deedc","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"The secret sharer: Evaluating and testing unintended memorization in neural net- works,","work_id":"dd43f494-cf0c-46cc-8132-bb76780bbb25","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Sok: Can trajectory generation combine privacy and utility?","work_id":"db4e3255-337f-43ef-8227-59fe5a310447","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Mobility trajectory generation: a survey,","work_id":"a675eb6c-6692-4f88-88dd-322260ccf28a","year":2023}],"snapshot_sha256":"86fb9066835e9069be0cc49a0521a97b1e6ae58381d86215313f5a7e6cc3f06b"},"source":{"id":"2605.15246","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T16:17:43.836005Z","id":"2373dd91-b232-48f9-85a5-6b6b32fc0466","model_set":{"reader":"grok-4.3"},"one_line_summary":"Generative models for trajectory data do not inherently preserve privacy, as membership inference attacks can identify training data points in representative models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Generative models do not guarantee privacy for synthetic trajectory data","strongest_claim":"Although these models are often assumed to preserve privacy due to their generative nature, this assumption does not necessarily hold, as demonstrated by the feasibility of using Membership Inference Attacks against representative models.","weakest_assumption":"That standard membership inference attack methods are directly applicable to trajectory generation tasks and that success on the chosen representative models indicates general privacy leakage risks across generative trajectory approaches."}},"verdict_id":"2373dd91-b232-48f9-85a5-6b6b32fc0466"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b9234c7d8ed8544eba6d6380b4dd875acbecdf8397a50d50f8d414970d49df09","target":"record","created_at":"2026-05-20T00:00:48Z","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":"eba8f1801d42538c52a3d4f015a4f69eee6e60c6011e6199dbd1cb0131d1a19d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T10:57:34Z","title_canon_sha256":"b4b6075aa543763a76f44a984f8635c4f6a9b0e5aa98a504f73fc6f0b6366858"},"schema_version":"1.0","source":{"id":"2605.15246","kind":"arxiv","version":1}},"canonical_sha256":"08fd08d5e3832f81ad1832cef349048779cbb18dee499062c07cf6886c2a2f37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08fd08d5e3832f81ad1832cef349048779cbb18dee499062c07cf6886c2a2f37","first_computed_at":"2026-05-20T00:00:48.281378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:48.281378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LjSymMc1TI83X7tkZuM37A2iqNoDkKrnLLGZJPZV3YA3v6g0sYF8a2MdL5cIgZu9uCOsaUNHrHKeuoTHA9ntCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:48.282547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9234c7d8ed8544eba6d6380b4dd875acbecdf8397a50d50f8d414970d49df09","sha256:1fc32f517b1043b7d11aaad4c3c6f80040bd26354c09337de4430a2b948bf34b"],"state_sha256":"948a3fabde608cb7256fdc3c2edf5d183543aeb6f140bd272b1f040e370459dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o7INZd6o9os7o/PPzWbXVZFjxXZ8yPxE/Q35PK0lMZkV9xB70nIPfrfW+sK4MdEEMMppvL1xH+1KhKLM6Sb1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T11:35:31.377530Z","bundle_sha256":"5c548f5e5bfc94cfed194cee1d17a94ecac7131962b4dc7dc59c7f7b8863bb27"}}