{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VTWKRKFVZPFARD3EPS2KQJM4GS","short_pith_number":"pith:VTWKRKFV","canonical_record":{"source":{"id":"2605.14142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T21:48:00Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"12265a45de3a5c7e16e0b39f26f4bb3ed2e53f88486f17d273b4008645d7d17e","abstract_canon_sha256":"46145b591dadf3cf1ec66b843547dfc7e36fdff69f1862c4b2b8259da133d419"},"schema_version":"1.0"},"canonical_sha256":"aceca8a8b5cbca088f647cb4a8259c34b7c1f6e871f7c2d08e906e71441bbaaa","source":{"kind":"arxiv","id":"2605.14142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14142","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14142v1","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14142","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"VTWKRKFVZPFA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VTWKRKFVZPFARD3E","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VTWKRKFV","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VTWKRKFVZPFARD3EPS2KQJM4GS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T21:48:00Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"12265a45de3a5c7e16e0b39f26f4bb3ed2e53f88486f17d273b4008645d7d17e","abstract_canon_sha256":"46145b591dadf3cf1ec66b843547dfc7e36fdff69f1862c4b2b8259da133d419"},"schema_version":"1.0"},"canonical_sha256":"aceca8a8b5cbca088f647cb4a8259c34b7c1f6e871f7c2d08e906e71441bbaaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:11.675434Z","signature_b64":"jId72TmSaMx432KnhBD8rgsbiXRp+DturVLf5Ziq0zuawOwm2syuJOM+S4AfER0lm/zLJ4cguRTUYdWawaH5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aceca8a8b5cbca088f647cb4a8259c34b7c1f6e871f7c2d08e906e71441bbaaa","last_reissued_at":"2026-05-17T23:39:11.674632Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:11.674632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14142","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":"2026-05-17T23:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DQ0dTXSVOypDsbC5oO1/rUR29qsIlS4cQINBl8af1L0Oyv+yNzA+04hDCLdKFg3TabedENIbZBWk0RimA+giCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:34:35.696679Z"},"content_sha256":"d66fdf562f5ce0ca52aee3f4b698e4f9a0e6f36d6c908f9c7f83b951f2aef609","schema_version":"1.0","event_id":"sha256:d66fdf562f5ce0ca52aee3f4b698e4f9a0e6f36d6c908f9c7f83b951f2aef609"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VTWKRKFVZPFARD3EPS2KQJM4GS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To discretize continually: Mean shift interacting particle systems for Bayesian inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Mean shift interacting particle systems approximate expectations from unnormalized densities by minimizing maximum mean discrepancy.","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Ayoub Belhadji, Daniel Sharp, Youssef M. Marzouk","submitted_at":"2026-05-13T21:48:00Z","abstract_excerpt":"Integration against a probability distribution given its unnormalized density is a central task in Bayesian inference and other fields. We introduce new methods for approximating such expectations with a small set of weighted samples -- i.e., a quadrature rule -- constructed via an interacting particle system that minimizes maximum mean discrepancy (MMD) to the target distribution. These methods extend the classical mean shift algorithm, as well as recent algorithms for optimal quantization of empirical distributions, to the case of continuous distributions. Crucially, our approach creates dyn"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The resulting mean shift interacting particle systems converge quickly, capture anisotropy and multi-modality, avoid mode collapse, and scale to high dimensions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed MMD-minimizing dynamics, when applied to unnormalized densities, produce particle configurations whose weighted averages accurately approximate the true expectations for the target distribution across the claimed regimes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Mean shift interacting particle systems generate weighted samples approximating expectations under unnormalized densities by minimizing MMD through normalizing-constant-invariant dynamics.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mean shift interacting particle systems approximate expectations from unnormalized densities by minimizing maximum mean discrepancy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"74b6fbe27821499e801cf7caaf3c686507904820558153d0b6fe784d14e01b25"},"source":{"id":"2605.14142","kind":"arxiv","version":1},"verdict":{"id":"5c7b91d6-1d2d-44a7-bc1a-bad201b85fc9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:01:33.548172Z","strongest_claim":"The resulting mean shift interacting particle systems converge quickly, capture anisotropy and multi-modality, avoid mode collapse, and scale to high dimensions.","one_line_summary":"Mean shift interacting particle systems generate weighted samples approximating expectations under unnormalized densities by minimizing MMD through normalizing-constant-invariant dynamics.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed MMD-minimizing dynamics, when applied to unnormalized densities, produce particle configurations whose weighted averages accurately approximate the true expectations for the target distribution across the claimed regimes.","pith_extraction_headline":"Mean shift interacting particle systems approximate expectations from unnormalized densities by minimizing maximum mean discrepancy."},"references":{"count":78,"sample":[{"doi":"10.1109/tac.2009","year":2009,"title":"I. Arasaratnam and S. Haykin. Cubature Kalman Filters.IEEE Transactions on Automatic Control, 54(6):1254–1269, June 2009. ISSN 0018-9286, 1558-2523. doi: 10.1109/TAC.2009. 2019800","work_id":"12d25893-2fbd-43d6-9d46-16102410b8b5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"M. Arbel, A. Korba, A. Salim, and A. Gretton. Maximum mean discrepancy gradient flow. Advances in Neural Information Processing Systems, 32, 2019","work_id":"000b25e3-110d-40ad-8378-c7e44857560a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"D. Aristoff and W. Bangerth. A Benchmark for the Bayesian Inversion of Coefficients in Partial Differential Equations.SIAM Review, 65(4):1074–1105, November 2023. ISSN 0036-1445, 1095-7200","work_id":"6f68ba3c-f53b-4125-9c2a-066f52ae037f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"F. Bach. On the equivalence between kernel quadrature rules and random feature expansions. The Journal of Machine Learning Research, 18(1):714–751, 2017","work_id":"c14023b3-21a0-4ecf-bcdd-93c8f8f1ef2a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"F. Bach, S. Lacoste-Julien, and G. Obozinski. On the equivalence between herding and condi- tional gradient algorithms. InProceedings of the 29th International Coference on International Conference on","work_id":"36e5f9d8-bda9-4d99-ad72-d8eb08bb4052","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":78,"snapshot_sha256":"0509e34a814db013c31f06d65ea69d31d2582cd01cf610dbe9f4d3235c02747e","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7d1102049830f1b6a94936b3fccdbc0adc0c9159ec62f4780bed961c54517998"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5c7b91d6-1d2d-44a7-bc1a-bad201b85fc9"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9RuuitU/PFQv0znF1Wd4aPIKcvGwpvwjpR2pX1uqfcfp7/vkSQt6XTj6rtYHrILCixrq22+NtLIWUvpPymPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:34:35.697774Z"},"content_sha256":"a7f578f8f372b9b21b16b6c0b941d7cc7aecc82a21dad31159cffe827668cf3b","schema_version":"1.0","event_id":"sha256:a7f578f8f372b9b21b16b6c0b941d7cc7aecc82a21dad31159cffe827668cf3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTWKRKFVZPFARD3EPS2KQJM4GS/bundle.json","state_url":"https://pith.science/pith/VTWKRKFVZPFARD3EPS2KQJM4GS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTWKRKFVZPFARD3EPS2KQJM4GS/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":"2026-05-21T13:34:35Z","links":{"resolver":"https://pith.science/pith/VTWKRKFVZPFARD3EPS2KQJM4GS","bundle":"https://pith.science/pith/VTWKRKFVZPFARD3EPS2KQJM4GS/bundle.json","state":"https://pith.science/pith/VTWKRKFVZPFARD3EPS2KQJM4GS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTWKRKFVZPFARD3EPS2KQJM4GS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VTWKRKFVZPFARD3EPS2KQJM4GS","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":"46145b591dadf3cf1ec66b843547dfc7e36fdff69f1862c4b2b8259da133d419","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T21:48:00Z","title_canon_sha256":"12265a45de3a5c7e16e0b39f26f4bb3ed2e53f88486f17d273b4008645d7d17e"},"schema_version":"1.0","source":{"id":"2605.14142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14142","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14142v1","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14142","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"VTWKRKFVZPFA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VTWKRKFVZPFARD3E","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VTWKRKFV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:a7f578f8f372b9b21b16b6c0b941d7cc7aecc82a21dad31159cffe827668cf3b","target":"graph","created_at":"2026-05-17T23:39:11Z","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":"The resulting mean shift interacting particle systems converge quickly, capture anisotropy and multi-modality, avoid mode collapse, and scale to high dimensions."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed MMD-minimizing dynamics, when applied to unnormalized densities, produce particle configurations whose weighted averages accurately approximate the true expectations for the target distribution across the claimed regimes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Mean shift interacting particle systems generate weighted samples approximating expectations under unnormalized densities by minimizing MMD through normalizing-constant-invariant dynamics."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Mean shift interacting particle systems approximate expectations from unnormalized densities by minimizing maximum mean discrepancy."}],"snapshot_sha256":"74b6fbe27821499e801cf7caaf3c686507904820558153d0b6fe784d14e01b25"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7d1102049830f1b6a94936b3fccdbc0adc0c9159ec62f4780bed961c54517998"},"paper":{"abstract_excerpt":"Integration against a probability distribution given its unnormalized density is a central task in Bayesian inference and other fields. We introduce new methods for approximating such expectations with a small set of weighted samples -- i.e., a quadrature rule -- constructed via an interacting particle system that minimizes maximum mean discrepancy (MMD) to the target distribution. These methods extend the classical mean shift algorithm, as well as recent algorithms for optimal quantization of empirical distributions, to the case of continuous distributions. Crucially, our approach creates dyn","authors_text":"Ayoub Belhadji, Daniel Sharp, Youssef M. Marzouk","cross_cats":["cs.LG","stat.CO"],"headline":"Mean shift interacting particle systems approximate expectations from unnormalized densities by minimizing maximum mean discrepancy.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T21:48:00Z","title":"To discretize continually: Mean shift interacting particle systems for Bayesian inference"},"references":{"count":78,"internal_anchors":2,"resolved_work":78,"sample":[{"cited_arxiv_id":"","doi":"10.1109/tac.2009","is_internal_anchor":false,"ref_index":1,"title":"I. Arasaratnam and S. Haykin. Cubature Kalman Filters.IEEE Transactions on Automatic Control, 54(6):1254–1269, June 2009. ISSN 0018-9286, 1558-2523. doi: 10.1109/TAC.2009. 2019800","work_id":"12d25893-2fbd-43d6-9d46-16102410b8b5","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"M. Arbel, A. Korba, A. Salim, and A. Gretton. Maximum mean discrepancy gradient flow. Advances in Neural Information Processing Systems, 32, 2019","work_id":"000b25e3-110d-40ad-8378-c7e44857560a","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"D. Aristoff and W. Bangerth. A Benchmark for the Bayesian Inversion of Coefficients in Partial Differential Equations.SIAM Review, 65(4):1074–1105, November 2023. ISSN 0036-1445, 1095-7200","work_id":"6f68ba3c-f53b-4125-9c2a-066f52ae037f","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"F. Bach. On the equivalence between kernel quadrature rules and random feature expansions. The Journal of Machine Learning Research, 18(1):714–751, 2017","work_id":"c14023b3-21a0-4ecf-bcdd-93c8f8f1ef2a","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"F. Bach, S. Lacoste-Julien, and G. Obozinski. On the equivalence between herding and condi- tional gradient algorithms. InProceedings of the 29th International Coference on International Conference on","work_id":"36e5f9d8-bda9-4d99-ad72-d8eb08bb4052","year":2012}],"snapshot_sha256":"0509e34a814db013c31f06d65ea69d31d2582cd01cf610dbe9f4d3235c02747e"},"source":{"id":"2605.14142","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:01:33.548172Z","id":"5c7b91d6-1d2d-44a7-bc1a-bad201b85fc9","model_set":{"reader":"grok-4.3"},"one_line_summary":"Mean shift interacting particle systems generate weighted samples approximating expectations under unnormalized densities by minimizing MMD through normalizing-constant-invariant dynamics.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Mean shift interacting particle systems approximate expectations from unnormalized densities by minimizing maximum mean discrepancy.","strongest_claim":"The resulting mean shift interacting particle systems converge quickly, capture anisotropy and multi-modality, avoid mode collapse, and scale to high dimensions.","weakest_assumption":"That the proposed MMD-minimizing dynamics, when applied to unnormalized densities, produce particle configurations whose weighted averages accurately approximate the true expectations for the target distribution across the claimed regimes."}},"verdict_id":"5c7b91d6-1d2d-44a7-bc1a-bad201b85fc9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d66fdf562f5ce0ca52aee3f4b698e4f9a0e6f36d6c908f9c7f83b951f2aef609","target":"record","created_at":"2026-05-17T23:39:11Z","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":"46145b591dadf3cf1ec66b843547dfc7e36fdff69f1862c4b2b8259da133d419","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T21:48:00Z","title_canon_sha256":"12265a45de3a5c7e16e0b39f26f4bb3ed2e53f88486f17d273b4008645d7d17e"},"schema_version":"1.0","source":{"id":"2605.14142","kind":"arxiv","version":1}},"canonical_sha256":"aceca8a8b5cbca088f647cb4a8259c34b7c1f6e871f7c2d08e906e71441bbaaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aceca8a8b5cbca088f647cb4a8259c34b7c1f6e871f7c2d08e906e71441bbaaa","first_computed_at":"2026-05-17T23:39:11.674632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:11.674632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jId72TmSaMx432KnhBD8rgsbiXRp+DturVLf5Ziq0zuawOwm2syuJOM+S4AfER0lm/zLJ4cguRTUYdWawaH5BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:11.675434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d66fdf562f5ce0ca52aee3f4b698e4f9a0e6f36d6c908f9c7f83b951f2aef609","sha256:a7f578f8f372b9b21b16b6c0b941d7cc7aecc82a21dad31159cffe827668cf3b"],"state_sha256":"43dffbd19ec8499fcd0a6a24af9f0d4d5ec41db15bb4989cb77f4859388bc8b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skFEf0vufMvZ29fq46+ruIIuhObyNDGI9RYt1irfqFItrVlM0COA7G4ySh9jk40c3Tab4mpUrOwZ7oYM/0SoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T13:34:35.701349Z","bundle_sha256":"220379094619d4c3c0bba1c6e8c9aa4cfc401607767f1ffd1dd4ffce95338c6f"}}