{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RL4CLPXQ5LWOLTG4VPEOTYIDUQ","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":"09a38a527a240f6c0b304d56ce454ab484555ae7edbebdd6887f73ac48928768","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T20:51:33Z","title_canon_sha256":"547c3e5e61bc53c6af78549bd8f951430946c1505224aeb22b53427f287d9a8d"},"schema_version":"1.0","source":{"id":"2002.09018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09018","created_at":"2026-07-05T02:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09018v2","created_at":"2026-07-05T02:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09018","created_at":"2026-07-05T02:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"RL4CLPXQ5LWO","created_at":"2026-07-05T02:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"RL4CLPXQ5LWOLTG4","created_at":"2026-07-05T02:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"RL4CLPXQ","created_at":"2026-07-05T02:20:27Z"}],"graph_snapshots":[{"event_id":"sha256:a9856b305f115e0a6b7be9fff7ba672e2d7aa06ae2d0ae870cf65cb05d2f3008","target":"graph","created_at":"2026-07-05T02:20:27Z","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/2002.09018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimization methods, that involve second derivatives and/or second order statistics of the data, are far less prevalent despite strong theoretical properties, due to their prohibitive computation, memory and communication costs. In an attempt to bridge this gap between theoretical and practical optimization, we present a scalable implementation of a second-order preconditioned method (concretely, a variant of full-matrix Adagr","authors_text":"Kevin Regan, Rohan Anil, Tomer Koren, Vineet Gupta, Yoram Singer","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T20:51:33Z","title":"Scalable Second Order Optimization for Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09018","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":"sha256:7dcc0ee73e0dc1b7a01d38811066f535e3c6e3b0411bd4c9e15e38cbd9f55a21","target":"record","created_at":"2026-07-05T02:20:27Z","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":"09a38a527a240f6c0b304d56ce454ab484555ae7edbebdd6887f73ac48928768","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T20:51:33Z","title_canon_sha256":"547c3e5e61bc53c6af78549bd8f951430946c1505224aeb22b53427f287d9a8d"},"schema_version":"1.0","source":{"id":"2002.09018","kind":"arxiv","version":2}},"canonical_sha256":"8af825bef0eaece5ccdcabc8e9e103a42e00c37c6f6d5a41b9541338d352b0f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8af825bef0eaece5ccdcabc8e9e103a42e00c37c6f6d5a41b9541338d352b0f5","first_computed_at":"2026-07-05T02:20:27.751420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:27.751420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jPthofBx/KXIkLHkqoPmT3IZCBAdEGjXNysJ/J1HzNu+HpLazP0Hc4XXTqI6Xl3aUdC5bavjdnOGONS1jYjUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:27.751896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.09018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dcc0ee73e0dc1b7a01d38811066f535e3c6e3b0411bd4c9e15e38cbd9f55a21","sha256:a9856b305f115e0a6b7be9fff7ba672e2d7aa06ae2d0ae870cf65cb05d2f3008"],"state_sha256":"cf0c7052e3cdba091c9d66fa53f9c6f16346afb67c6ca661abbfe47b46b447a6"}