{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WJCRQIERNWMDPNCSCWVDCZKC6K","short_pith_number":"pith:WJCRQIER","canonical_record":{"source":{"id":"2111.00396","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-31T03:32:18Z","cross_cats_sorted":[],"title_canon_sha256":"005efae14363ecad4d4a31266a29e0e4193008ccf62dff1cb1b8ee24ae6dda10","abstract_canon_sha256":"2de9430fa455ce79b6f7bcefb0568c063b3e18a85b032f11dfbd29592d4f6c6e"},"schema_version":"1.0"},"canonical_sha256":"b2451820916d9837b45215aa316542f2b0501ff691f06de49e8eec152c5b4dc7","source":{"kind":"arxiv","id":"2111.00396","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00396","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00396v3","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00396","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"WJCRQIERNWMD","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"WJCRQIERNWMDPNCS","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"WJCRQIER","created_at":"2026-07-05T04:46:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WJCRQIERNWMDPNCSCWVDCZKC6K","target":"record","payload":{"canonical_record":{"source":{"id":"2111.00396","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-31T03:32:18Z","cross_cats_sorted":[],"title_canon_sha256":"005efae14363ecad4d4a31266a29e0e4193008ccf62dff1cb1b8ee24ae6dda10","abstract_canon_sha256":"2de9430fa455ce79b6f7bcefb0568c063b3e18a85b032f11dfbd29592d4f6c6e"},"schema_version":"1.0"},"canonical_sha256":"b2451820916d9837b45215aa316542f2b0501ff691f06de49e8eec152c5b4dc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:12.498382Z","signature_b64":"piN3X+CAbMRWClvrHG6cQdHEYZvynjmRGWgJBiUMvj4ZuRMw+s3Mary4YVpen16do/t7+07TbShgZKzWFBFBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2451820916d9837b45215aa316542f2b0501ff691f06de49e8eec152c5b4dc7","last_reissued_at":"2026-07-05T04:46:12.497941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:12.497941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.00396","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HAWsDxfee1Ywf+GawE6mkIIxeOMn+yfsHL3aYYe/PmW7MmmpscFfdGUvooiWAwz3U9XzkuW8svmzXtkgHPuVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T01:34:53.830363Z"},"content_sha256":"8a1bc004bd0fc508a611be3b66bc50427e14bd20aa4847859955a8738521908c","schema_version":"1.0","event_id":"sha256:8a1bc004bd0fc508a611be3b66bc50427e14bd20aa4847859955a8738521908c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WJCRQIERNWMDPNCSCWVDCZKC6K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficiently Modeling Long Sequences with Structured State Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"S4 uses a low-rank correction to the state matrix A so state space models can be computed efficiently via Cauchy kernels while retaining long-range power.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albert Gu, Christopher R\\'e, Karan Goel","submitted_at":"2021-10-31T03:32:18Z","abstract_excerpt":"A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies. Although conventional models including RNNs, CNNs, and Transformers have specialized variants for capturing long dependencies, they still struggle to scale to very long sequences of $10000$ or more steps. A promising recent approach proposed modeling sequences by simulating the fundamental state space model (SSM) \\( x'(t) = Ax(t) + Bu(t), y(t) = Cx(t) + Du(t) \\), and showed that for appropriate choices of the "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"S4 achieves SoTA on every task from the Long Range Arena benchmark, including solving the challenging Path-X task of length 16k that all prior work fails on, while being as efficient as all competitors.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The low-rank correction to the state matrix A permits stable diagonalization and that the resulting Cauchy kernel computation fully preserves the theoretical long-range modeling strengths of the underlying SSM without introducing approximation errors that degrade performance on real data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while being faster than Transformers for generation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"S4 uses a low-rank correction to the state matrix A so state space models can be computed efficiently via Cauchy kernels while retaining long-range power.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d46a16c995ed952703432f6d20d6e55a67da4b2fc185dfbee4312c15927e9c65"},"source":{"id":"2111.00396","kind":"arxiv","version":3},"verdict":{"id":"51e801c0-08f1-43ad-b659-87bf96f2fef0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T10:37:10.486355Z","strongest_claim":"S4 achieves SoTA on every task from the Long Range Arena benchmark, including solving the challenging Path-X task of length 16k that all prior work fails on, while being as efficient as all competitors.","one_line_summary":"S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while being faster than Transformers for generation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The low-rank correction to the state matrix A permits stable diagonalization and that the resulting Cauchy kernel computation fully preserves the theoretical long-range modeling strengths of the underlying SSM without introducing approximation errors that degrade performance on real data.","pith_extraction_headline":"S4 uses a low-rank correction to the state matrix A so state space models can be computed efficiently via Cauchy kernels while retaining long-range power."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.00396/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":52,"sample":[{"doi":"","year":2016,"title":"Unitary evolution recurrent neural networks","work_id":"5bfc68ac-fe5f-4dc5-9c66-6b9f02500125","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Adaptive Input Representations for Neural Language Modeling","work_id":"84b64f8d-525e-4a27-b130-855b07cc501f","ref_index":2,"cited_arxiv_id":"1809.10853","is_internal_anchor":false},{"doi":"","year":2018,"title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","work_id":"04430f4e-b270-479c-9dcd-bee723164789","ref_index":3,"cited_arxiv_id":"1803.01271","is_internal_anchor":true},{"doi":"","year":2019,"title":"Trellis networks for sequence modeling","work_id":"dd7da183-a356-425b-9d58-e4bc66342ea4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Dilated recurrent neural networks","work_id":"cf88c8dc-70d8-4686-b0cc-cf8cdf0f86b2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":52,"snapshot_sha256":"0668360ae43bc1b68a99762f5794deba609c0ee5dfaaf6fe232f7b2ae4dd5943","internal_anchors":5},"formal_canon":{"evidence_count":3,"snapshot_sha256":"e59ea97cb81e40f02ee5e51fd4b11fe63ba20841ebedb6a23b2e317699b016f9"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"51e801c0-08f1-43ad-b659-87bf96f2fef0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vLCT/5JPJKD9gc2hsb/kTIq2VYzj6bUIu9l3jCwJlufofZan4banugf62jCfnFb1zu/8qpfLWv1eEgApJnYgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T01:34:53.830910Z"},"content_sha256":"baa0856fcc44e12c819c3ea18fffb4e03b31add04f142b1ffca7137dcc8296f3","schema_version":"1.0","event_id":"sha256:baa0856fcc44e12c819c3ea18fffb4e03b31add04f142b1ffca7137dcc8296f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WJCRQIERNWMDPNCSCWVDCZKC6K/bundle.json","state_url":"https://pith.science/pith/WJCRQIERNWMDPNCSCWVDCZKC6K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WJCRQIERNWMDPNCSCWVDCZKC6K/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":"2026-07-13T01:34:53Z","links":{"resolver":"https://pith.science/pith/WJCRQIERNWMDPNCSCWVDCZKC6K","bundle":"https://pith.science/pith/WJCRQIERNWMDPNCSCWVDCZKC6K/bundle.json","state":"https://pith.science/pith/WJCRQIERNWMDPNCSCWVDCZKC6K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WJCRQIERNWMDPNCSCWVDCZKC6K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WJCRQIERNWMDPNCSCWVDCZKC6K","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":"2de9430fa455ce79b6f7bcefb0568c063b3e18a85b032f11dfbd29592d4f6c6e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-31T03:32:18Z","title_canon_sha256":"005efae14363ecad4d4a31266a29e0e4193008ccf62dff1cb1b8ee24ae6dda10"},"schema_version":"1.0","source":{"id":"2111.00396","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00396","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00396v3","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00396","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"WJCRQIERNWMD","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"WJCRQIERNWMDPNCS","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"WJCRQIER","created_at":"2026-07-05T04:46:12Z"}],"graph_snapshots":[{"event_id":"sha256:baa0856fcc44e12c819c3ea18fffb4e03b31add04f142b1ffca7137dcc8296f3","target":"graph","created_at":"2026-07-05T04:46:12Z","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":"S4 achieves SoTA on every task from the Long Range Arena benchmark, including solving the challenging Path-X task of length 16k that all prior work fails on, while being as efficient as all competitors."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The low-rank correction to the state matrix A permits stable diagonalization and that the resulting Cauchy kernel computation fully preserves the theoretical long-range modeling strengths of the underlying SSM without introducing approximation errors that degrade performance on real data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while being faster than Transformers for generation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"S4 uses a low-rank correction to the state matrix A so state space models can be computed efficiently via Cauchy kernels while retaining long-range power."}],"snapshot_sha256":"d46a16c995ed952703432f6d20d6e55a67da4b2fc185dfbee4312c15927e9c65"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"e59ea97cb81e40f02ee5e51fd4b11fe63ba20841ebedb6a23b2e317699b016f9"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2111.00396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies. Although conventional models including RNNs, CNNs, and Transformers have specialized variants for capturing long dependencies, they still struggle to scale to very long sequences of $10000$ or more steps. A promising recent approach proposed modeling sequences by simulating the fundamental state space model (SSM) \\( x'(t) = Ax(t) + Bu(t), y(t) = Cx(t) + Du(t) \\), and showed that for appropriate choices of the ","authors_text":"Albert Gu, Christopher R\\'e, Karan Goel","cross_cats":[],"headline":"S4 uses a low-rank correction to the state matrix A so state space models can be computed efficiently via Cauchy kernels while retaining long-range power.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-31T03:32:18Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces"},"references":{"count":52,"internal_anchors":5,"resolved_work":52,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Unitary evolution recurrent neural networks","work_id":"5bfc68ac-fe5f-4dc5-9c66-6b9f02500125","year":2016},{"cited_arxiv_id":"1809.10853","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Adaptive Input Representations for Neural Language Modeling","work_id":"84b64f8d-525e-4a27-b130-855b07cc501f","year":2018},{"cited_arxiv_id":"1803.01271","doi":"","is_internal_anchor":true,"ref_index":3,"title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","work_id":"04430f4e-b270-479c-9dcd-bee723164789","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Trellis networks for sequence modeling","work_id":"dd7da183-a356-425b-9d58-e4bc66342ea4","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Dilated recurrent neural networks","work_id":"cf88c8dc-70d8-4686-b0cc-cf8cdf0f86b2","year":2017}],"snapshot_sha256":"0668360ae43bc1b68a99762f5794deba609c0ee5dfaaf6fe232f7b2ae4dd5943"},"source":{"id":"2111.00396","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-11T10:37:10.486355Z","id":"51e801c0-08f1-43ad-b659-87bf96f2fef0","model_set":{"reader":"grok-4.3"},"one_line_summary":"S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while being faster than Transformers for generation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"S4 uses a low-rank correction to the state matrix A so state space models can be computed efficiently via Cauchy kernels while retaining long-range power.","strongest_claim":"S4 achieves SoTA on every task from the Long Range Arena benchmark, including solving the challenging Path-X task of length 16k that all prior work fails on, while being as efficient as all competitors.","weakest_assumption":"The low-rank correction to the state matrix A permits stable diagonalization and that the resulting Cauchy kernel computation fully preserves the theoretical long-range modeling strengths of the underlying SSM without introducing approximation errors that degrade performance on real data."}},"verdict_id":"51e801c0-08f1-43ad-b659-87bf96f2fef0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8a1bc004bd0fc508a611be3b66bc50427e14bd20aa4847859955a8738521908c","target":"record","created_at":"2026-07-05T04:46:12Z","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":"2de9430fa455ce79b6f7bcefb0568c063b3e18a85b032f11dfbd29592d4f6c6e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-31T03:32:18Z","title_canon_sha256":"005efae14363ecad4d4a31266a29e0e4193008ccf62dff1cb1b8ee24ae6dda10"},"schema_version":"1.0","source":{"id":"2111.00396","kind":"arxiv","version":3}},"canonical_sha256":"b2451820916d9837b45215aa316542f2b0501ff691f06de49e8eec152c5b4dc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2451820916d9837b45215aa316542f2b0501ff691f06de49e8eec152c5b4dc7","first_computed_at":"2026-07-05T04:46:12.497941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:12.497941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"piN3X+CAbMRWClvrHG6cQdHEYZvynjmRGWgJBiUMvj4ZuRMw+s3Mary4YVpen16do/t7+07TbShgZKzWFBFBAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:12.498382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00396","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a1bc004bd0fc508a611be3b66bc50427e14bd20aa4847859955a8738521908c","sha256:baa0856fcc44e12c819c3ea18fffb4e03b31add04f142b1ffca7137dcc8296f3"],"state_sha256":"5ba75918e36ecf541a5eeacc9879b4d3d0e249ed3b5366f5cfc68d955ca4143f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1DYGZyI+NlNQv5XvDwFrvqGyDcaxwPhsP9O+FQ8RFPp+jVe+Ga7Hj8rWJlsGf3n8YRvZ8eDpzV2gq/4uvVjCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T01:34:53.833370Z","bundle_sha256":"17d00a9e69a66174fcc9bf134d52a32d16c84bfc0f99188f67bb871dcb656e1a"}}