{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C6LDYY2ITBWW2BGKZ2U36D7OBA","short_pith_number":"pith:C6LDYY2I","canonical_record":{"source":{"id":"2410.20135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-26T10:14:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"172b002893c7c2a293864435be79975823c080a8478a75168ed3429e3d7d115d","abstract_canon_sha256":"947af95f49e2adad3643e4395fdbb1d4bf197ae6ca2f2535c65edc510be5d838"},"schema_version":"1.0"},"canonical_sha256":"17963c6348986d6d04cacea9bf0fee081493eedab5862ae374c6a5e571bdf7d9","source":{"kind":"arxiv","id":"2410.20135","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20135","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20135v1","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20135","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"C6LDYY2ITBWW","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"C6LDYY2ITBWW2BGK","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"C6LDYY2I","created_at":"2026-07-05T09:26:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C6LDYY2ITBWW2BGKZ2U36D7OBA","target":"record","payload":{"canonical_record":{"source":{"id":"2410.20135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-26T10:14:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"172b002893c7c2a293864435be79975823c080a8478a75168ed3429e3d7d115d","abstract_canon_sha256":"947af95f49e2adad3643e4395fdbb1d4bf197ae6ca2f2535c65edc510be5d838"},"schema_version":"1.0"},"canonical_sha256":"17963c6348986d6d04cacea9bf0fee081493eedab5862ae374c6a5e571bdf7d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:39.608764Z","signature_b64":"UHieVpdEJWJFcbXycFVgOL/SVpOEJw8g6FFETeK+mznmEKujPWl1wYa6TcEeBCzZOkQvjE5mO9ngwqaJ5/YWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17963c6348986d6d04cacea9bf0fee081493eedab5862ae374c6a5e571bdf7d9","last_reissued_at":"2026-07-05T09:26:39.608323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:39.608323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.20135","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":"2026-07-05T09:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nJD5yJEgZyAvzJpEE9ydy4Y/JvJ0koG20n1jb7ZJIWZFCpRan7MwIHq0Y2nGmbgWDR1ZRBhLXdldP9Wp7rViCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:26:13.317700Z"},"content_sha256":"aa579be3c9b99e0a0f60b7edcd6ea83461f716996848d3d9c4972b9441ea6fa9","schema_version":"1.0","event_id":"sha256:aa579be3c9b99e0a0f60b7edcd6ea83461f716996848d3d9c4972b9441ea6fa9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C6LDYY2ITBWW2BGKZ2U36D7OBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aniket Das, Arun Suggala, Dheeraj Nagaraj, Prateek Varshney, Soumyabrata Pal","submitted_at":"2024-10-26T10:14:17Z","abstract_excerpt":"We consider the problem of high-dimensional heavy-tailed statistical estimation in the streaming setting, which is much harder than the traditional batch setting due to memory constraints. We cast this problem as stochastic convex optimization with heavy tailed stochastic gradients, and prove that the widely used Clipped-SGD algorithm attains near-optimal sub-Gaussian statistical rates whenever the second moment of the stochastic gradient noise is finite. More precisely, with $T$ samples, we show that Clipped-SGD, for smooth and strongly convex objectives, achieves an error of $\\sqrt{\\frac{\\ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20135","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.20135/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTcbWtGDn+ayg8+tqU/8KYfT8QfX8kG+WDS00kYJnttkB0excvOfTGPKUFys0LiekEhlrgDHuHv6+8owh6atBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:26:13.318034Z"},"content_sha256":"dbd8b019540abf7967d264e70f4646251de5844f4eb88443c0bcdb0c3c621c28","schema_version":"1.0","event_id":"sha256:dbd8b019540abf7967d264e70f4646251de5844f4eb88443c0bcdb0c3c621c28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C6LDYY2ITBWW2BGKZ2U36D7OBA/bundle.json","state_url":"https://pith.science/pith/C6LDYY2ITBWW2BGKZ2U36D7OBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C6LDYY2ITBWW2BGKZ2U36D7OBA/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":"2026-08-21T15:26:13Z","links":{"resolver":"https://pith.science/pith/C6LDYY2ITBWW2BGKZ2U36D7OBA","bundle":"https://pith.science/pith/C6LDYY2ITBWW2BGKZ2U36D7OBA/bundle.json","state":"https://pith.science/pith/C6LDYY2ITBWW2BGKZ2U36D7OBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C6LDYY2ITBWW2BGKZ2U36D7OBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C6LDYY2ITBWW2BGKZ2U36D7OBA","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":"947af95f49e2adad3643e4395fdbb1d4bf197ae6ca2f2535c65edc510be5d838","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-26T10:14:17Z","title_canon_sha256":"172b002893c7c2a293864435be79975823c080a8478a75168ed3429e3d7d115d"},"schema_version":"1.0","source":{"id":"2410.20135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20135","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20135v1","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20135","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"C6LDYY2ITBWW","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"C6LDYY2ITBWW2BGK","created_at":"2026-07-05T09:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"C6LDYY2I","created_at":"2026-07-05T09:26:39Z"}],"graph_snapshots":[{"event_id":"sha256:dbd8b019540abf7967d264e70f4646251de5844f4eb88443c0bcdb0c3c621c28","target":"graph","created_at":"2026-07-05T09:26:39Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.20135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of high-dimensional heavy-tailed statistical estimation in the streaming setting, which is much harder than the traditional batch setting due to memory constraints. We cast this problem as stochastic convex optimization with heavy tailed stochastic gradients, and prove that the widely used Clipped-SGD algorithm attains near-optimal sub-Gaussian statistical rates whenever the second moment of the stochastic gradient noise is finite. More precisely, with $T$ samples, we show that Clipped-SGD, for smooth and strongly convex objectives, achieves an error of $\\sqrt{\\frac{\\ma","authors_text":"Aniket Das, Arun Suggala, Dheeraj Nagaraj, Prateek Varshney, Soumyabrata Pal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-26T10:14:17Z","title":"Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20135","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aa579be3c9b99e0a0f60b7edcd6ea83461f716996848d3d9c4972b9441ea6fa9","target":"record","created_at":"2026-07-05T09:26:39Z","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":"947af95f49e2adad3643e4395fdbb1d4bf197ae6ca2f2535c65edc510be5d838","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-26T10:14:17Z","title_canon_sha256":"172b002893c7c2a293864435be79975823c080a8478a75168ed3429e3d7d115d"},"schema_version":"1.0","source":{"id":"2410.20135","kind":"arxiv","version":1}},"canonical_sha256":"17963c6348986d6d04cacea9bf0fee081493eedab5862ae374c6a5e571bdf7d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17963c6348986d6d04cacea9bf0fee081493eedab5862ae374c6a5e571bdf7d9","first_computed_at":"2026-07-05T09:26:39.608323Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:39.608323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UHieVpdEJWJFcbXycFVgOL/SVpOEJw8g6FFETeK+mznmEKujPWl1wYa6TcEeBCzZOkQvjE5mO9ngwqaJ5/YWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:39.608764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa579be3c9b99e0a0f60b7edcd6ea83461f716996848d3d9c4972b9441ea6fa9","sha256:dbd8b019540abf7967d264e70f4646251de5844f4eb88443c0bcdb0c3c621c28"],"state_sha256":"fa83392185f11dec11850a81fa99f361f4dff0d58f2f195953b027780d2891dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6c+vbWX3MyV4a8LxYfopoxJYSLWMMxhaKD7t7iRNySM+C7/yzssAYmTyALIPJNYz9jqI7rDUByKDQEjBfsTpCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:26:13.321968Z","bundle_sha256":"4dfca81c8c0cab15fdf15f60646b6bf771b93da84e400063eb78b2da6dd49b78"}}