{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:YS7XHFKMWMZ4E3MM26KPMOVQGF","short_pith_number":"pith:YS7XHFKM","canonical_record":{"source":{"id":"1503.08316","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-28T15:51:48Z","cross_cats_sorted":[],"title_canon_sha256":"d66a5b191924593d402cdb9985791c89d88735cd582d997e93d28217b4629c5e","abstract_canon_sha256":"aba4177f2563319149044304a5846b731216b09b0d4acf8282ea1fcc536ca954"},"schema_version":"1.0"},"canonical_sha256":"c4bf73954cb333c26d8cd794f63ab031523f94c51df94e508e3ad236878fca77","source":{"kind":"arxiv","id":"1503.08316","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.08316","created_at":"2026-05-18T01:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"1503.08316v4","created_at":"2026-05-18T01:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.08316","created_at":"2026-05-18T01:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"YS7XHFKMWMZ4","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"YS7XHFKMWMZ4E3MM","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"YS7XHFKM","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:YS7XHFKMWMZ4E3MM26KPMOVQGF","target":"record","payload":{"canonical_record":{"source":{"id":"1503.08316","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-28T15:51:48Z","cross_cats_sorted":[],"title_canon_sha256":"d66a5b191924593d402cdb9985791c89d88735cd582d997e93d28217b4629c5e","abstract_canon_sha256":"aba4177f2563319149044304a5846b731216b09b0d4acf8282ea1fcc536ca954"},"schema_version":"1.0"},"canonical_sha256":"c4bf73954cb333c26d8cd794f63ab031523f94c51df94e508e3ad236878fca77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:55:41.752509Z","signature_b64":"KzJDiSyT8t6Twj0JYNDZOgAgUujLmlPb9bhAJhAIGXeRmgti2oO6bsKUtUBwg99Ab2W5wqXZloax+f14H5pvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4bf73954cb333c26d8cd794f63ab031523f94c51df94e508e3ad236878fca77","last_reissued_at":"2026-05-18T01:55:41.751976Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:55:41.751976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1503.08316","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:55:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pqbbOOVZCVvEjLFgDyZ6iPa/qLE11hmegzXXsmUuJL3+/Z/u48ovY7xTUEmvt6huJxYCWLG7FiYIoGICwXBEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:23:24.052362Z"},"content_sha256":"e0e593dd5b9536d8ce95f99930a88975851420c7dbb4054745616f5f9a5034a4","schema_version":"1.0","event_id":"sha256:e0e593dd5b9536d8ce95f99930a88975851420c7dbb4054745616f5f9a5034a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:YS7XHFKMWMZ4E3MM26KPMOVQGF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Variance Reduced Stochastic Newton Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Brian McWilliams, Thomas Hofmann","submitted_at":"2015-03-28T15:51:48Z","abstract_excerpt":"Quasi-Newton methods are widely used in practise for convex loss minimization problems. These methods exhibit good empirical performance on a wide variety of tasks and enjoy super-linear convergence to the optimal solution. For large-scale learning problems, stochastic Quasi-Newton methods have been recently proposed. However, these typically only achieve sub-linear convergence rates and have not been shown to consistently perform well in practice since noisy Hessian approximations can exacerbate the effect of high-variance stochastic gradient estimates. In this work we propose Vite, a novel s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.08316","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T01:55:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NAqpHlRw15PFUY5XZ9vn0ZCKw8o48RP9rSQD45rYsbDUuHCgDB0q8n6CVu773w3xNJ7O9q+RtpMpKFz0FcgvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:23:24.053030Z"},"content_sha256":"ceb601968ce98a2237bc2fd18af2f6e6bf002b2deaf293d34d4c63051e306c5b","schema_version":"1.0","event_id":"sha256:ceb601968ce98a2237bc2fd18af2f6e6bf002b2deaf293d34d4c63051e306c5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YS7XHFKMWMZ4E3MM26KPMOVQGF/bundle.json","state_url":"https://pith.science/pith/YS7XHFKMWMZ4E3MM26KPMOVQGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YS7XHFKMWMZ4E3MM26KPMOVQGF/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":"2026-05-25T19:23:24Z","links":{"resolver":"https://pith.science/pith/YS7XHFKMWMZ4E3MM26KPMOVQGF","bundle":"https://pith.science/pith/YS7XHFKMWMZ4E3MM26KPMOVQGF/bundle.json","state":"https://pith.science/pith/YS7XHFKMWMZ4E3MM26KPMOVQGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YS7XHFKMWMZ4E3MM26KPMOVQGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:YS7XHFKMWMZ4E3MM26KPMOVQGF","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":"aba4177f2563319149044304a5846b731216b09b0d4acf8282ea1fcc536ca954","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-28T15:51:48Z","title_canon_sha256":"d66a5b191924593d402cdb9985791c89d88735cd582d997e93d28217b4629c5e"},"schema_version":"1.0","source":{"id":"1503.08316","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.08316","created_at":"2026-05-18T01:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"1503.08316v4","created_at":"2026-05-18T01:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.08316","created_at":"2026-05-18T01:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"YS7XHFKMWMZ4","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"YS7XHFKMWMZ4E3MM","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"YS7XHFKM","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:ceb601968ce98a2237bc2fd18af2f6e6bf002b2deaf293d34d4c63051e306c5b","target":"graph","created_at":"2026-05-18T01:55:41Z","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"},"paper":{"abstract_excerpt":"Quasi-Newton methods are widely used in practise for convex loss minimization problems. These methods exhibit good empirical performance on a wide variety of tasks and enjoy super-linear convergence to the optimal solution. For large-scale learning problems, stochastic Quasi-Newton methods have been recently proposed. However, these typically only achieve sub-linear convergence rates and have not been shown to consistently perform well in practice since noisy Hessian approximations can exacerbate the effect of high-variance stochastic gradient estimates. In this work we propose Vite, a novel s","authors_text":"Aurelien Lucchi, Brian McWilliams, Thomas Hofmann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-28T15:51:48Z","title":"A Variance Reduced Stochastic Newton Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.08316","kind":"arxiv","version":4},"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:e0e593dd5b9536d8ce95f99930a88975851420c7dbb4054745616f5f9a5034a4","target":"record","created_at":"2026-05-18T01:55:41Z","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":"aba4177f2563319149044304a5846b731216b09b0d4acf8282ea1fcc536ca954","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-28T15:51:48Z","title_canon_sha256":"d66a5b191924593d402cdb9985791c89d88735cd582d997e93d28217b4629c5e"},"schema_version":"1.0","source":{"id":"1503.08316","kind":"arxiv","version":4}},"canonical_sha256":"c4bf73954cb333c26d8cd794f63ab031523f94c51df94e508e3ad236878fca77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4bf73954cb333c26d8cd794f63ab031523f94c51df94e508e3ad236878fca77","first_computed_at":"2026-05-18T01:55:41.751976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:55:41.751976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KzJDiSyT8t6Twj0JYNDZOgAgUujLmlPb9bhAJhAIGXeRmgti2oO6bsKUtUBwg99Ab2W5wqXZloax+f14H5pvCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:55:41.752509Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.08316","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0e593dd5b9536d8ce95f99930a88975851420c7dbb4054745616f5f9a5034a4","sha256:ceb601968ce98a2237bc2fd18af2f6e6bf002b2deaf293d34d4c63051e306c5b"],"state_sha256":"575397a2054fd20655ce5cd5edcfacbe147b354cf2329968a510dc3192ec2101"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8lin/n5taX+m2xx5CcBqX3uw3wTBxlW+r6mmLHzk1F3jDjqFfvSFjoqV6gRdw/x47bgz9VIz+Uqoulmu/aQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:23:24.056818Z","bundle_sha256":"5d5acf9bbdd428b7073522ee21c613bc6a5f8f48d3f49fa247d5732e104c350d"}}