{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:L4AI5KFNMLYRJ6ZELHVFQ4E3YD","short_pith_number":"pith:L4AI5KFN","canonical_record":{"source":{"id":"2110.08577","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-10-16T14:04:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9c4bd11b3222d866a23287dc691f26954c80e310d59df89c812fadab2cc3378f","abstract_canon_sha256":"eca043cea0732e031b86b4eb606bdb8471562589d73d730d06aa4f937db97147"},"schema_version":"1.0"},"canonical_sha256":"5f008ea8ad62f114fb2459ea58709bc0dcc169ec6040efd31ddc2ed880f20c46","source":{"kind":"arxiv","id":"2110.08577","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08577","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08577v2","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08577","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"pith_short_12","alias_value":"L4AI5KFNMLYR","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"pith_short_16","alias_value":"L4AI5KFNMLYRJ6ZE","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"pith_short_8","alias_value":"L4AI5KFN","created_at":"2026-07-05T03:52:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:L4AI5KFNMLYRJ6ZELHVFQ4E3YD","target":"record","payload":{"canonical_record":{"source":{"id":"2110.08577","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-10-16T14:04:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9c4bd11b3222d866a23287dc691f26954c80e310d59df89c812fadab2cc3378f","abstract_canon_sha256":"eca043cea0732e031b86b4eb606bdb8471562589d73d730d06aa4f937db97147"},"schema_version":"1.0"},"canonical_sha256":"5f008ea8ad62f114fb2459ea58709bc0dcc169ec6040efd31ddc2ed880f20c46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:32.110915Z","signature_b64":"7DOCh2NkdnSxTgdCpyNUKg4TvnxZYLwuRZ+3VwHNHwVpLtBn77nlkOgwHPtRyrAm6mEe3wW54m6C59WQ7ogLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f008ea8ad62f114fb2459ea58709bc0dcc169ec6040efd31ddc2ed880f20c46","last_reissued_at":"2026-07-05T03:52:32.110461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:32.110461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.08577","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:52:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/Hrih9VSUfP3aDp5VQkRGynQ4uODhKKi3q6ORMiXIm7N8phRE+MXSCV7mXP3OZpG6uiSrp1/9X9remBtCqCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:44:04.452634Z"},"content_sha256":"0220f8b1826b2145bbfc8a25c91f76afc0c646bafb498afed78cd229615d7ab2","schema_version":"1.0","event_id":"sha256:0220f8b1826b2145bbfc8a25c91f76afc0c646bafb498afed78cd229615d7ab2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:L4AI5KFNMLYRJ6ZELHVFQ4E3YD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nys-Newton: Nystr\\\"om-Approximated Curvature for Stochastic Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Dinesh Singh, Hardik Tankaria, Makoto Yamada","submitted_at":"2021-10-16T14:04:51Z","abstract_excerpt":"Second-order optimization methods are among the most widely used optimization approaches for convex optimization problems, and have recently been used to optimize non-convex optimization problems such as deep learning models. The widely used second-order optimization methods such as quasi-Newton methods generally provide curvature information by approximating the Hessian using the secant equation. However, the secant equation becomes insipid in approximating the Newton step owing to its use of the first-order derivatives. In this study, we propose an approximate Newton sketch-based stochastic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08577","kind":"arxiv","version":2},"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/2110.08577/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":"2026-07-05T03:52:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84BG/ndxLcAGezLRrIa2YGax3S0cXxrvBBHEFFf7HTvnf+72gXY1mSgWBvDGCBmIITgVFDOtT6YO0bOpbNN5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:44:04.453147Z"},"content_sha256":"3d7395ccd757be25f8b0d642fe992de25d52cfe01d2711f6e709c0c95023e4f3","schema_version":"1.0","event_id":"sha256:3d7395ccd757be25f8b0d642fe992de25d52cfe01d2711f6e709c0c95023e4f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4AI5KFNMLYRJ6ZELHVFQ4E3YD/bundle.json","state_url":"https://pith.science/pith/L4AI5KFNMLYRJ6ZELHVFQ4E3YD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4AI5KFNMLYRJ6ZELHVFQ4E3YD/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":"2026-08-08T03:44:04Z","links":{"resolver":"https://pith.science/pith/L4AI5KFNMLYRJ6ZELHVFQ4E3YD","bundle":"https://pith.science/pith/L4AI5KFNMLYRJ6ZELHVFQ4E3YD/bundle.json","state":"https://pith.science/pith/L4AI5KFNMLYRJ6ZELHVFQ4E3YD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4AI5KFNMLYRJ6ZELHVFQ4E3YD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:L4AI5KFNMLYRJ6ZELHVFQ4E3YD","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":"eca043cea0732e031b86b4eb606bdb8471562589d73d730d06aa4f937db97147","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-10-16T14:04:51Z","title_canon_sha256":"9c4bd11b3222d866a23287dc691f26954c80e310d59df89c812fadab2cc3378f"},"schema_version":"1.0","source":{"id":"2110.08577","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08577","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08577v2","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08577","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"pith_short_12","alias_value":"L4AI5KFNMLYR","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"pith_short_16","alias_value":"L4AI5KFNMLYRJ6ZE","created_at":"2026-07-05T03:52:32Z"},{"alias_kind":"pith_short_8","alias_value":"L4AI5KFN","created_at":"2026-07-05T03:52:32Z"}],"graph_snapshots":[{"event_id":"sha256:3d7395ccd757be25f8b0d642fe992de25d52cfe01d2711f6e709c0c95023e4f3","target":"graph","created_at":"2026-07-05T03:52:32Z","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/2110.08577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Second-order optimization methods are among the most widely used optimization approaches for convex optimization problems, and have recently been used to optimize non-convex optimization problems such as deep learning models. The widely used second-order optimization methods such as quasi-Newton methods generally provide curvature information by approximating the Hessian using the secant equation. However, the secant equation becomes insipid in approximating the Newton step owing to its use of the first-order derivatives. In this study, we propose an approximate Newton sketch-based stochastic ","authors_text":"Dinesh Singh, Hardik Tankaria, Makoto Yamada","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-10-16T14:04:51Z","title":"Nys-Newton: Nystr\\\"om-Approximated Curvature for Stochastic Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08577","kind":"arxiv","version":2},"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":"sha256:0220f8b1826b2145bbfc8a25c91f76afc0c646bafb498afed78cd229615d7ab2","target":"record","created_at":"2026-07-05T03:52:32Z","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":"eca043cea0732e031b86b4eb606bdb8471562589d73d730d06aa4f937db97147","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-10-16T14:04:51Z","title_canon_sha256":"9c4bd11b3222d866a23287dc691f26954c80e310d59df89c812fadab2cc3378f"},"schema_version":"1.0","source":{"id":"2110.08577","kind":"arxiv","version":2}},"canonical_sha256":"5f008ea8ad62f114fb2459ea58709bc0dcc169ec6040efd31ddc2ed880f20c46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f008ea8ad62f114fb2459ea58709bc0dcc169ec6040efd31ddc2ed880f20c46","first_computed_at":"2026-07-05T03:52:32.110461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:52:32.110461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7DOCh2NkdnSxTgdCpyNUKg4TvnxZYLwuRZ+3VwHNHwVpLtBn77nlkOgwHPtRyrAm6mEe3wW54m6C59WQ7ogLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:52:32.110915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08577","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0220f8b1826b2145bbfc8a25c91f76afc0c646bafb498afed78cd229615d7ab2","sha256:3d7395ccd757be25f8b0d642fe992de25d52cfe01d2711f6e709c0c95023e4f3"],"state_sha256":"da4828877e1efdc9aef740bc324a6531f3089ac67a5584a07299f8503f806c93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZ29Ac6nKcGTUF89WhFB7/nQyYL3k0vQfitNfJCYnaWue9GM/WabBTWBJrIDjJr8ZMfDdBlKFAT62RLu/IUNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:44:04.456749Z","bundle_sha256":"9501bc3afdfcb4b141d6fa87fe161986a1dfbacf6c251e199a4934f8f9c715f9"}}