{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5PZ7SAXMN3BHKV4ER2D4YRI6R3","short_pith_number":"pith:5PZ7SAXM","canonical_record":{"source":{"id":"2207.01848","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T07:17:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"25f4e9ad94e4b3fbf7db28c4ab7bfaae622b37a48b0e6199a0f88a4dd20dac16","abstract_canon_sha256":"28acee69c2f4693367d647e5f9cdc9fc67a218e6b96d2d6eb8f36716d625ef9c"},"schema_version":"1.0"},"canonical_sha256":"ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2","source":{"kind":"arxiv","id":"2207.01848","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.01848","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2207.01848v6","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01848","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"5PZ7SAXMN3BH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"5PZ7SAXMN3BHKV4E","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"5PZ7SAXM","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5PZ7SAXMN3BHKV4ER2D4YRI6R3","target":"record","payload":{"canonical_record":{"source":{"id":"2207.01848","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T07:17:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"25f4e9ad94e4b3fbf7db28c4ab7bfaae622b37a48b0e6199a0f88a4dd20dac16","abstract_canon_sha256":"28acee69c2f4693367d647e5f9cdc9fc67a218e6b96d2d6eb8f36716d625ef9c"},"schema_version":"1.0"},"canonical_sha256":"ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.723553Z","signature_b64":"+Tp2i9icgth18o6TSXohx0OvYZlhJKy8mVkOumrX4CKTnl16u6hhoJ7ycOW75B5pZXLweBQg39HlULPp9iy0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2","last_reissued_at":"2026-05-17T23:38:53.722896Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.722896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.01848","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dgySTtDdjILqpm2mj1NFkDU9RQRK3nj5/cZf2FCD+rqr3eUaB6ux0x529ZeuG+giSvwQuA2MYwiguO1/21jUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:15:45.609124Z"},"content_sha256":"b5f7072a80ed3b09b3ac20cdb41a68660ff266935423519f25dcbdd45d5eb302","schema_version":"1.0","event_id":"sha256:b5f7072a80ed3b09b3ac20cdb41a68660ff266935423519f25dcbdd45d5eb302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5PZ7SAXMN3BHKV4ER2D4YRI6R3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Katharina Eggensperger, Noah Hollmann, Samuel M\\\"uller","submitted_at":"2022-07-05T07:17:43Z","abstract_excerpt":"We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods. TabPFN performs in-context learning (ICL), it learns to make predictions using sequences of labeled examples (x, f(x)) given in the input, without requiring further parameter updates. TabPFN is fully entailed in the weights of our network, which accepts training and test samples as a set-valued input and yields predictions for the entire test set in a single forward pass. "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230× speedup.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The prior over structural causal models used to generate the synthetic training data is sufficiently representative of the distribution of real-world small tabular classification problems so that the trained network generalizes without further adaptation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6852d01c272470356b71902230753f8d782dc64a638a8da6c23d6e6a48757865"},"source":{"id":"2207.01848","kind":"arxiv","version":6},"verdict":{"id":"1943ae2a-5d64-4d0b-bfcf-d12c23b1c328","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:58:24.217861Z","strongest_claim":"On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230× speedup.","one_line_summary":"TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The prior over structural causal models used to generate the synthetic training data is sufficiently representative of the distribution of real-world small tabular classification problems so that the trained network generalizes without further adaptation.","pith_extraction_headline":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning."},"references":{"count":41,"sample":[{"doi":"","year":2004,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","ref_index":1,"cited_arxiv_id":"2004.05150","is_internal_anchor":true},{"doi":"","year":null,"title":"V . Borisov, T. Leemann, K. Seßler, J. Haug, M. Pawelczyk, and G. Kasneci. Deep neural networks and tabular data: A survey. arXiv:2110.01889 [cs.LG],","work_id":"93f57855-ef13-447a-9bb3-7c52593fcd9f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"eb041f9e-11f2-4d39-b912-b66f075cd8ab","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"URL https://proceedings.neurips.cc/paper_files/paper/ 2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf. T. Chen and C. Guestrin. Xgboost: A scalable tree boosting system. In B. Krishnapuram, M. Sh","work_id":"466eef06-1c73-4be7-b5c0-e7a0aac54cb7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"arXiv preprint arXiv:2006.10029 , year=","work_id":"c3db4fa8-1334-4859-bdc9-38d1fc92426f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"28adc855b3cfd2ae0ddbf3638f6f56ac181fe03e7c985b0bb56fe19775b7de70","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dcbffae37fc8598935b1fd0cdb4752ac7d12cfd4950a079218cf981e56141047"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"1943ae2a-5d64-4d0b-bfcf-d12c23b1c328"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRQNmXx3DDgHdyHff2yXzPjPvp+t9K0hbPDHxYpkWiMzXNO8RqTBUweUcbAk6rkmySb/zUVq9IdW2vgTJ099Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:15:45.609687Z"},"content_sha256":"c21d216f9c355863db141eec50198f221452e49202805246ad311497d660067e","schema_version":"1.0","event_id":"sha256:c21d216f9c355863db141eec50198f221452e49202805246ad311497d660067e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/bundle.json","state_url":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/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":"2026-05-30T21:15:45Z","links":{"resolver":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3","bundle":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/bundle.json","state":"https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5PZ7SAXMN3BHKV4ER2D4YRI6R3","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":"28acee69c2f4693367d647e5f9cdc9fc67a218e6b96d2d6eb8f36716d625ef9c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T07:17:43Z","title_canon_sha256":"25f4e9ad94e4b3fbf7db28c4ab7bfaae622b37a48b0e6199a0f88a4dd20dac16"},"schema_version":"1.0","source":{"id":"2207.01848","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.01848","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2207.01848v6","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01848","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"5PZ7SAXMN3BH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"5PZ7SAXMN3BHKV4E","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"5PZ7SAXM","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:c21d216f9c355863db141eec50198f221452e49202805246ad311497d660067e","target":"graph","created_at":"2026-05-17T23:38:53Z","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 the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230× speedup."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The prior over structural causal models used to generate the synthetic training data is sufficiently representative of the distribution of real-world small tabular classification problems so that the trained network generalizes without further adaptation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning."}],"snapshot_sha256":"6852d01c272470356b71902230753f8d782dc64a638a8da6c23d6e6a48757865"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dcbffae37fc8598935b1fd0cdb4752ac7d12cfd4950a079218cf981e56141047"},"paper":{"abstract_excerpt":"We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods. TabPFN performs in-context learning (ICL), it learns to make predictions using sequences of labeled examples (x, f(x)) given in the input, without requiring further parameter updates. TabPFN is fully entailed in the weights of our network, which accepts training and test samples as a set-valued input and yields predictions for the entire test set in a single forward pass. ","authors_text":"Frank Hutter, Katharina Eggensperger, Noah Hollmann, Samuel M\\\"uller","cross_cats":["stat.ML"],"headline":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T07:17:43Z","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second"},"references":{"count":41,"internal_anchors":2,"resolved_work":41,"sample":[{"cited_arxiv_id":"2004.05150","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"V . Borisov, T. Leemann, K. Seßler, J. Haug, M. Pawelczyk, and G. Kasneci. Deep neural networks and tabular data: A survey. arXiv:2110.01889 [cs.LG],","work_id":"93f57855-ef13-447a-9bb3-7c52593fcd9f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Language models are few-shot learners","work_id":"eb041f9e-11f2-4d39-b912-b66f075cd8ab","year":1901},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"URL https://proceedings.neurips.cc/paper_files/paper/ 2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf. T. Chen and C. Guestrin. Xgboost: A scalable tree boosting system. In B. Krishnapuram, M. Sh","work_id":"466eef06-1c73-4be7-b5c0-e7a0aac54cb7","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"arXiv preprint arXiv:2006.10029 , year=","work_id":"c3db4fa8-1334-4859-bdc9-38d1fc92426f","year":2006}],"snapshot_sha256":"28adc855b3cfd2ae0ddbf3638f6f56ac181fe03e7c985b0bb56fe19775b7de70"},"source":{"id":"2207.01848","kind":"arxiv","version":6},"verdict":{"created_at":"2026-05-15T02:58:24.217861Z","id":"1943ae2a-5d64-4d0b-bfcf-d12c23b1c328","model_set":{"reader":"grok-4.3"},"one_line_summary":"TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning.","strongest_claim":"On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230× speedup.","weakest_assumption":"The prior over structural causal models used to generate the synthetic training data is sufficiently representative of the distribution of real-world small tabular classification problems so that the trained network generalizes without further adaptation."}},"verdict_id":"1943ae2a-5d64-4d0b-bfcf-d12c23b1c328"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b5f7072a80ed3b09b3ac20cdb41a68660ff266935423519f25dcbdd45d5eb302","target":"record","created_at":"2026-05-17T23:38:53Z","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":"28acee69c2f4693367d647e5f9cdc9fc67a218e6b96d2d6eb8f36716d625ef9c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T07:17:43Z","title_canon_sha256":"25f4e9ad94e4b3fbf7db28c4ab7bfaae622b37a48b0e6199a0f88a4dd20dac16"},"schema_version":"1.0","source":{"id":"2207.01848","kind":"arxiv","version":6}},"canonical_sha256":"ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2","first_computed_at":"2026-05-17T23:38:53.722896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.722896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Tp2i9icgth18o6TSXohx0OvYZlhJKy8mVkOumrX4CKTnl16u6hhoJ7ycOW75B5pZXLweBQg39HlULPp9iy0Cg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.723553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.01848","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5f7072a80ed3b09b3ac20cdb41a68660ff266935423519f25dcbdd45d5eb302","sha256:c21d216f9c355863db141eec50198f221452e49202805246ad311497d660067e"],"state_sha256":"197cf867393431f5f44942aac13862cee49d917f18bfa96d407dfee23afed28c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMkcXTUIn9VTEVQimvob80ylkpXB6xJkjfvMdgxL8xAq6+Eo/5GMNXmFECHalQxABSfAWuS5KUXjY1PyNNFZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T21:15:45.612694Z","bundle_sha256":"72f61768ee63352353909b0916e586a282f395f7c662c8ad3c4ad21a4337e26d"}}