{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4NVBCJJV3JX3UF6XGGCVHK22DZ","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"38f83b0b65db508330450c6154e16ae0088efbc6bbbbaa224404af58d776a32e","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T10:00:23Z","title_canon_sha256":"eb725248b003ae8dc6463d1d1adc6f6045a9af5e82703a8fbb0149686cc8bbb4"},"schema_version":"1.0","source":{"id":"2605.13283","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13283","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13283v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13283","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"4NVBCJJV3JX3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"4NVBCJJV3JX3UF6X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"4NVBCJJV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4406eeb64f1f24088a2c2792822f508dadb2e11b0ccd68b50570c7db258ab145","target":"graph","created_at":"2026-05-18T02:44:49Z","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 estimators yield non-asymptotic guarantees and attain near-optimal statistical rates under mild conditions, while remaining communication-efficient"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"mild conditions on the data distribution, sparsity level, and fraction of Byzantine machines (standard but unspecified in abstract; typically requires bounded moments and Byzantine fraction below 1/2)"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Local L1-regularized robust estimators plus server-side robust aggregation achieve near-optimal rates for high-dimensional sparse learning under Byzantine attacks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Local l1-regularized robust estimators plus server-side robust aggregation deliver non-asymptotic guarantees and near-optimal rates for Byzantine-robust distributed sparse learning."}],"snapshot_sha256":"931a1cd313433b232c29a5ac9441240578e4027418349fe94a9290a498d839bd"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We revisit Byzantine robust distributed estimation for high-dimensional sparse linear models. By combining local $\\ell_1$-regularized robust estimation with robust aggregation at the server, the framework applies to pseudo-Huber regression, quantile regression, and sparse SVM. We show that the resulting estimators yield non-asymptotic guarantees and attain near-optimal statistical rates under mild conditions, while remaining communication-efficient. Simulations confirm strong robustness in estimation, support recovery and classification accuracy under various Byzantine attacks.","authors_text":"Kangqiang Li, Lixin Zhang, Yuxuan Wang","cross_cats":["math.ST","stat.TH"],"headline":"Local l1-regularized robust estimators plus server-side robust aggregation deliver non-asymptotic guarantees and near-optimal rates for Byzantine-robust distributed sparse learning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T10:00:23Z","title":"Byzantine-Robust Distributed Sparse Learning Revisited"},"references":{"count":16,"internal_anchors":1,"resolved_work":16,"sample":[{"cited_arxiv_id":"1402.4624","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Sparse Quantile Huber Regression for Efficient and Robust Estimation","work_id":"2ca89efa-7258-429d-a5e8-e169cf94253c","year":null},{"cited_arxiv_id":"","doi":"10.1214/17-aos1587","is_internal_anchor":false,"ref_index":2,"title":"Distributed testing and estimation under sparse high dimensional models. Ann. Statist. 46, 1352–1382. doi:10.1214/17-AOS1587. Belloni,A.,Chernozhukov,V.,2011.𝓁 1-penalizedquantileregressioninhigh-dime","work_id":"d901821a-9e8a-4dc4-a53c-b106bb5d8e53","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"2023 , journal =","work_id":"cedbb8cd-4355-4661-9d7a-1d12a91d0dd9","year":2021},{"cited_arxiv_id":"","doi":"10.1111/rssb.12166","is_internal_anchor":false,"ref_index":4,"title":"Estimation of high dimensional mean regression in the absence of symmetry and light tail assumptions. J. R. Stat. Soc. B: Stat. Methodol. 79, 247–265. doi:10.1111/rssb.12166. Fan, J., Liu, H., Sun, Q.","work_id":"76326722-d8c8-4407-a4e1-61becdbeb9d6","year":null},{"cited_arxiv_id":"","doi":"10.1214/17-aos1568","is_internal_anchor":false,"ref_index":5,"title":"I-lamm for sparse learning: Simultaneous control of algorithmic complexity and statistical error. Ann. Statist. 46, 814–841. doi:10.1214/17-AOS1568. He, X., Pan, X., Tan, K.M., Zhou, W.X.,","work_id":"c546aea9-8b24-49dd-8df0-3ad21ab0c166","year":null}],"snapshot_sha256":"397490c10791ec916fb5731af52ad99796657a8ad60bd1c7bfd66f49f791cf92"},"source":{"id":"2605.13283","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:37:19.514915Z","id":"ee5a5ed2-8cc1-4210-a80e-8148a0fb3a90","model_set":{"reader":"grok-4.3"},"one_line_summary":"Local L1-regularized robust estimators plus server-side robust aggregation achieve near-optimal rates for high-dimensional sparse learning under Byzantine attacks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Local l1-regularized robust estimators plus server-side robust aggregation deliver non-asymptotic guarantees and near-optimal rates for Byzantine-robust distributed sparse learning.","strongest_claim":"the resulting estimators yield non-asymptotic guarantees and attain near-optimal statistical rates under mild conditions, while remaining communication-efficient","weakest_assumption":"mild conditions on the data distribution, sparsity level, and fraction of Byzantine machines (standard but unspecified in abstract; typically requires bounded moments and Byzantine fraction below 1/2)"}},"verdict_id":"ee5a5ed2-8cc1-4210-a80e-8148a0fb3a90"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e9a55c2477dc31e7529d5851c2c0e155d543f212edc532b3166df0c48c861675","target":"record","created_at":"2026-05-18T02:44:49Z","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":"38f83b0b65db508330450c6154e16ae0088efbc6bbbbaa224404af58d776a32e","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T10:00:23Z","title_canon_sha256":"eb725248b003ae8dc6463d1d1adc6f6045a9af5e82703a8fbb0149686cc8bbb4"},"schema_version":"1.0","source":{"id":"2605.13283","kind":"arxiv","version":1}},"canonical_sha256":"e36a112535da6fba17d7318553ab5a1e7b3cecfc4de2d543c10666270c2c7f37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e36a112535da6fba17d7318553ab5a1e7b3cecfc4de2d543c10666270c2c7f37","first_computed_at":"2026-05-18T02:44:49.175230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:49.175230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"odVB/z2U0aoL7IgTjl8OaaK6GJ/KQcJScEfSyh8VycfCzyznTkXhcqh8TFO0ukHs0cfwYuG1P69iuoPWcwXIAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:49.175726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13283","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9a55c2477dc31e7529d5851c2c0e155d543f212edc532b3166df0c48c861675","sha256:4406eeb64f1f24088a2c2792822f508dadb2e11b0ccd68b50570c7db258ab145","sha256:a9ee86415ba2e76a4e06df76c94a71b2f41e25774f4192e104e41c76b7baac55"],"state_sha256":"33d19a77976060a4cd48b27d87faddb79dcd65439b3fab75934896f4f25a1274"}