{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SYPQV4Q2JHAXOTSBXCA2EQX2H6","short_pith_number":"pith:SYPQV4Q2","canonical_record":{"source":{"id":"1802.03801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-11T19:35:46Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c916f893dd7b3d29b263652609f34cef12ebaef0e68c0f97f52dc3df35505397","abstract_canon_sha256":"cb8cf359ba22a1c155c0479c44204bc24b3b5b4e18ecd09b5dafd062926a6956"},"schema_version":"1.0"},"canonical_sha256":"961f0af21a49c1774e41b881a242fa3fa7c7532f3cfeaa9cb911060538c0a326","source":{"kind":"arxiv","id":"1802.03801","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03801","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03801v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03801","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"SYPQV4Q2JHAX","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SYPQV4Q2JHAXOTSB","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SYPQV4Q2","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SYPQV4Q2JHAXOTSBXCA2EQX2H6","target":"record","payload":{"canonical_record":{"source":{"id":"1802.03801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-11T19:35:46Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c916f893dd7b3d29b263652609f34cef12ebaef0e68c0f97f52dc3df35505397","abstract_canon_sha256":"cb8cf359ba22a1c155c0479c44204bc24b3b5b4e18ecd09b5dafd062926a6956"},"schema_version":"1.0"},"canonical_sha256":"961f0af21a49c1774e41b881a242fa3fa7c7532f3cfeaa9cb911060538c0a326","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:17.962502Z","signature_b64":"XlmWFh9GJE9Q112Mp0wVoLDBU83h5nezxBpd5lIPy7lx/IejJUaoI0hu+gp3zD+zO7PDrMz9Uqi7XVG3BFk8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"961f0af21a49c1774e41b881a242fa3fa7c7532f3cfeaa9cb911060538c0a326","last_reissued_at":"2026-05-18T00:11:17.961858Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:17.961858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.03801","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":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SEygsoxvOtAqswHZMGtSgXmJhATQdBDrSrKL/D7rm7680d/yHnehafZY2VXP2L2YKzEOW+HFGGMV2EGwhLiaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:24:35.800345Z"},"content_sha256":"e57d9db32f4944d6247bf643747a4f4ef8df5105b6314aa56e1561d08ff87806","schema_version":"1.0","event_id":"sha256:e57d9db32f4944d6247bf643747a4f4ef8df5105b6314aa56e1561d08ff87806"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SYPQV4Q2JHAXOTSBXCA2EQX2H6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SGD and Hogwild! Convergence Without the Bounded Gradients Assumption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Katya Scheinberg, Lam M. Nguyen, Marten van Dijk, Martin Tak\\'a\\v{c}, Peter Richt\\'arik, Phuong Ha Nguyen","submitted_at":"2018-02-11T19:35:46Z","abstract_excerpt":"Stochastic gradient descent (SGD) is the optimization algorithm of choice in many machine learning applications such as regularized empirical risk minimization and training deep neural networks. The classical convergence analysis of SGD is carried out under the assumption that the norm of the stochastic gradient is uniformly bounded. While this might hold for some loss functions, it is always violated for cases where the objective function is strongly convex. In (Bottou et al.,2016), a new analysis of convergence of SGD is performed under the assumption that stochastic gradients are bounded wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03801","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":""},"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":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y5vLcT4PBZltUa7wLyV3F3UZl7/Hqp3fixZJcxTiRnPEGA4jyhNxplH2raATJM5yUoVi6jNLOcFu/b344cSfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:24:35.800857Z"},"content_sha256":"5ee9ad7c89180802c26b387edea00ed1798106f701a8e7b388bbf053d22e6427","schema_version":"1.0","event_id":"sha256:5ee9ad7c89180802c26b387edea00ed1798106f701a8e7b388bbf053d22e6427"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYPQV4Q2JHAXOTSBXCA2EQX2H6/bundle.json","state_url":"https://pith.science/pith/SYPQV4Q2JHAXOTSBXCA2EQX2H6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYPQV4Q2JHAXOTSBXCA2EQX2H6/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":"2026-05-26T00:24:35Z","links":{"resolver":"https://pith.science/pith/SYPQV4Q2JHAXOTSBXCA2EQX2H6","bundle":"https://pith.science/pith/SYPQV4Q2JHAXOTSBXCA2EQX2H6/bundle.json","state":"https://pith.science/pith/SYPQV4Q2JHAXOTSBXCA2EQX2H6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYPQV4Q2JHAXOTSBXCA2EQX2H6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SYPQV4Q2JHAXOTSBXCA2EQX2H6","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":"cb8cf359ba22a1c155c0479c44204bc24b3b5b4e18ecd09b5dafd062926a6956","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-11T19:35:46Z","title_canon_sha256":"c916f893dd7b3d29b263652609f34cef12ebaef0e68c0f97f52dc3df35505397"},"schema_version":"1.0","source":{"id":"1802.03801","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03801","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03801v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03801","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"SYPQV4Q2JHAX","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SYPQV4Q2JHAXOTSB","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SYPQV4Q2","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:5ee9ad7c89180802c26b387edea00ed1798106f701a8e7b388bbf053d22e6427","target":"graph","created_at":"2026-05-18T00:11:17Z","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":"Stochastic gradient descent (SGD) is the optimization algorithm of choice in many machine learning applications such as regularized empirical risk minimization and training deep neural networks. The classical convergence analysis of SGD is carried out under the assumption that the norm of the stochastic gradient is uniformly bounded. While this might hold for some loss functions, it is always violated for cases where the objective function is strongly convex. In (Bottou et al.,2016), a new analysis of convergence of SGD is performed under the assumption that stochastic gradients are bounded wi","authors_text":"Katya Scheinberg, Lam M. Nguyen, Marten van Dijk, Martin Tak\\'a\\v{c}, Peter Richt\\'arik, Phuong Ha Nguyen","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-11T19:35:46Z","title":"SGD and Hogwild! Convergence Without the Bounded Gradients Assumption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03801","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:e57d9db32f4944d6247bf643747a4f4ef8df5105b6314aa56e1561d08ff87806","target":"record","created_at":"2026-05-18T00:11:17Z","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":"cb8cf359ba22a1c155c0479c44204bc24b3b5b4e18ecd09b5dafd062926a6956","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-11T19:35:46Z","title_canon_sha256":"c916f893dd7b3d29b263652609f34cef12ebaef0e68c0f97f52dc3df35505397"},"schema_version":"1.0","source":{"id":"1802.03801","kind":"arxiv","version":2}},"canonical_sha256":"961f0af21a49c1774e41b881a242fa3fa7c7532f3cfeaa9cb911060538c0a326","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"961f0af21a49c1774e41b881a242fa3fa7c7532f3cfeaa9cb911060538c0a326","first_computed_at":"2026-05-18T00:11:17.961858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:17.961858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XlmWFh9GJE9Q112Mp0wVoLDBU83h5nezxBpd5lIPy7lx/IejJUaoI0hu+gp3zD+zO7PDrMz9Uqi7XVG3BFk8Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:17.962502Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03801","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e57d9db32f4944d6247bf643747a4f4ef8df5105b6314aa56e1561d08ff87806","sha256:5ee9ad7c89180802c26b387edea00ed1798106f701a8e7b388bbf053d22e6427"],"state_sha256":"7863b36e39e4053fad272817f2042a291fb118f3643c824c0d0ae9606cd8361c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CK4JsaoFIuE5NJWVXxc8a+PAqibVKGuojG7OGnMOncQ3H2OdLXEzVW/0ToCGfQ27MrpfYQCD++pfBr8tYIa6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:24:35.803195Z","bundle_sha256":"1cdfbade4e7ef01d61698b1f527d19e6e0c2cdf55bd8e991c7d724899f33c350"}}