{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GUQHU7CUVABJURR7BTKXB6Z5ET","short_pith_number":"pith:GUQHU7CU","canonical_record":{"source":{"id":"1901.09997","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-28T20:47:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"16ad633f4518c6f2f14c34a2641e1778836bae4ba89ba7b9e30ccdc290cd64aa","abstract_canon_sha256":"6be15c1634020b24a5573c89b34c9a5bd19e0aa304b5f6f761c708690d007532"},"schema_version":"1.0"},"canonical_sha256":"35207a7c54a8029a463f0cd570fb3d24ee80c62312788d1a56fbdf9fb121e02b","source":{"kind":"arxiv","id":"1901.09997","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09997","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09997v5","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09997","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"GUQHU7CUVABJ","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"GUQHU7CUVABJURR7","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"GUQHU7CU","created_at":"2026-07-05T03:01:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GUQHU7CUVABJURR7BTKXB6Z5ET","target":"record","payload":{"canonical_record":{"source":{"id":"1901.09997","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-28T20:47:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"16ad633f4518c6f2f14c34a2641e1778836bae4ba89ba7b9e30ccdc290cd64aa","abstract_canon_sha256":"6be15c1634020b24a5573c89b34c9a5bd19e0aa304b5f6f761c708690d007532"},"schema_version":"1.0"},"canonical_sha256":"35207a7c54a8029a463f0cd570fb3d24ee80c62312788d1a56fbdf9fb121e02b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:01:20.145921Z","signature_b64":"toTMpB6oiroIBVOolQd4Pjci1UvUZSFayrljhKfZjw3doDuA3jLTUStkGeGhgpi7dtjKPUhIWaqy6xL9a1dRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35207a7c54a8029a463f0cd570fb3d24ee80c62312788d1a56fbdf9fb121e02b","last_reissued_at":"2026-07-05T03:01:20.145444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:01:20.145444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.09997","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i66UBd7IegbeVyVFqlJPkgjpSt0Rgss9UvdCWqnEkZ88+FGPTyxlgJ0HKhr3qSTJspyBeZEl3wOvTrgUUXIHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:26:36.128249Z"},"content_sha256":"b06433d9722aaf19b601c23bae5a62e64ac7ec42f0530bc5da5478b7b493bbcb","schema_version":"1.0","event_id":"sha256:b06433d9722aaf19b601c23bae5a62e64ac7ec42f0530bc5da5478b7b493bbcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GUQHU7CUVABJURR7BTKXB6Z5ET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quasi-Newton Methods for Machine Learning: Forget the Past, Just Sample","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Albert S. Berahas, Majid Jahani, Martin Tak\\'a\\v{c}, Peter Richt\\'arik","submitted_at":"2019-01-28T20:47:18Z","abstract_excerpt":"We present two sampled quasi-Newton methods (sampled LBFGS and sampled LSR1) for solving empirical risk minimization problems that arise in machine learning. Contrary to the classical variants of these methods that sequentially build Hessian or inverse Hessian approximations as the optimization progresses, our proposed methods sample points randomly around the current iterate at every iteration to produce these approximations. As a result, the approximations constructed make use of more reliable (recent and local) information, and do not depend on past iterate information that could be signifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09997","kind":"arxiv","version":5},"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/1901.09997/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":"2026-07-05T03:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eszbt1j6o03ik1tTXd4Ix8uqOLCCYi3wrjERHcvmeaNv2SyLvJdH24WKxQcpOo71Z8ldJ3z3ycqKBvXy+1hmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:26:36.129156Z"},"content_sha256":"2287890ab293260f138e88d3c3bdbff1240e92f2fefb605778c2b3992492c6f3","schema_version":"1.0","event_id":"sha256:2287890ab293260f138e88d3c3bdbff1240e92f2fefb605778c2b3992492c6f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUQHU7CUVABJURR7BTKXB6Z5ET/bundle.json","state_url":"https://pith.science/pith/GUQHU7CUVABJURR7BTKXB6Z5ET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUQHU7CUVABJURR7BTKXB6Z5ET/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":"2026-08-04T19:26:36Z","links":{"resolver":"https://pith.science/pith/GUQHU7CUVABJURR7BTKXB6Z5ET","bundle":"https://pith.science/pith/GUQHU7CUVABJURR7BTKXB6Z5ET/bundle.json","state":"https://pith.science/pith/GUQHU7CUVABJURR7BTKXB6Z5ET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUQHU7CUVABJURR7BTKXB6Z5ET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GUQHU7CUVABJURR7BTKXB6Z5ET","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":"6be15c1634020b24a5573c89b34c9a5bd19e0aa304b5f6f761c708690d007532","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-28T20:47:18Z","title_canon_sha256":"16ad633f4518c6f2f14c34a2641e1778836bae4ba89ba7b9e30ccdc290cd64aa"},"schema_version":"1.0","source":{"id":"1901.09997","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09997","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09997v5","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09997","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"GUQHU7CUVABJ","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"GUQHU7CUVABJURR7","created_at":"2026-07-05T03:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"GUQHU7CU","created_at":"2026-07-05T03:01:20Z"}],"graph_snapshots":[{"event_id":"sha256:2287890ab293260f138e88d3c3bdbff1240e92f2fefb605778c2b3992492c6f3","target":"graph","created_at":"2026-07-05T03:01:20Z","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/1901.09997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present two sampled quasi-Newton methods (sampled LBFGS and sampled LSR1) for solving empirical risk minimization problems that arise in machine learning. Contrary to the classical variants of these methods that sequentially build Hessian or inverse Hessian approximations as the optimization progresses, our proposed methods sample points randomly around the current iterate at every iteration to produce these approximations. As a result, the approximations constructed make use of more reliable (recent and local) information, and do not depend on past iterate information that could be signifi","authors_text":"Albert S. Berahas, Majid Jahani, Martin Tak\\'a\\v{c}, Peter Richt\\'arik","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-28T20:47:18Z","title":"Quasi-Newton Methods for Machine Learning: Forget the Past, Just Sample"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09997","kind":"arxiv","version":5},"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:b06433d9722aaf19b601c23bae5a62e64ac7ec42f0530bc5da5478b7b493bbcb","target":"record","created_at":"2026-07-05T03:01:20Z","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":"6be15c1634020b24a5573c89b34c9a5bd19e0aa304b5f6f761c708690d007532","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-28T20:47:18Z","title_canon_sha256":"16ad633f4518c6f2f14c34a2641e1778836bae4ba89ba7b9e30ccdc290cd64aa"},"schema_version":"1.0","source":{"id":"1901.09997","kind":"arxiv","version":5}},"canonical_sha256":"35207a7c54a8029a463f0cd570fb3d24ee80c62312788d1a56fbdf9fb121e02b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35207a7c54a8029a463f0cd570fb3d24ee80c62312788d1a56fbdf9fb121e02b","first_computed_at":"2026-07-05T03:01:20.145444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:01:20.145444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"toTMpB6oiroIBVOolQd4Pjci1UvUZSFayrljhKfZjw3doDuA3jLTUStkGeGhgpi7dtjKPUhIWaqy6xL9a1dRCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:01:20.145921Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09997","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b06433d9722aaf19b601c23bae5a62e64ac7ec42f0530bc5da5478b7b493bbcb","sha256:2287890ab293260f138e88d3c3bdbff1240e92f2fefb605778c2b3992492c6f3"],"state_sha256":"ed8c38b8cd657db80da585e771e84ed318612ed041823f584ec0c19bb8e73173"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"au98X/gNxt8XQvuiggoAXt/jQdwPM2GUNbzb6y3d+iv6DykeimezzaE7/Dpb5QT9vyQ1ycBIbi5/1wlEEVFpAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:26:36.135714Z","bundle_sha256":"b35fd52a8224a80af05340ed415d5427e43c74ec86914ca6dfabbcb1bfe7f18e"}}