{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YJGNZ3J7BMVXOXPME246CS265J","short_pith_number":"pith:YJGNZ3J7","canonical_record":{"source":{"id":"1902.04811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T09:44:02Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"982a5c982193b84f10afe9d2b9c3578aa829c39e28753d167db422f394554008","abstract_canon_sha256":"a23b5866a71a9ec3f309af673a964c2bdc3c4afeb68a2b44b897d0a508887ee7"},"schema_version":"1.0"},"canonical_sha256":"c24cdced3f0b2b775dec26b9e14b5eea66eee3c4e150feed5793de96461f8479","source":{"kind":"arxiv","id":"1902.04811","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04811","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04811v2","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04811","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"pith_short_12","alias_value":"YJGNZ3J7BMVX","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"pith_short_16","alias_value":"YJGNZ3J7BMVXOXPM","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"pith_short_8","alias_value":"YJGNZ3J7","created_at":"2026-07-05T00:02:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YJGNZ3J7BMVXOXPME246CS265J","target":"record","payload":{"canonical_record":{"source":{"id":"1902.04811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T09:44:02Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"982a5c982193b84f10afe9d2b9c3578aa829c39e28753d167db422f394554008","abstract_canon_sha256":"a23b5866a71a9ec3f309af673a964c2bdc3c4afeb68a2b44b897d0a508887ee7"},"schema_version":"1.0"},"canonical_sha256":"c24cdced3f0b2b775dec26b9e14b5eea66eee3c4e150feed5793de96461f8479","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:12.595115Z","signature_b64":"uJ2mJO9Rgo3sQ3BVt2/9ddA3vqWo/YbepEOSmWjYdCL4+KkmKoohboBhS497lbXptxCkYxVD+fpw4iecRyA8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c24cdced3f0b2b775dec26b9e14b5eea66eee3c4e150feed5793de96461f8479","last_reissued_at":"2026-07-05T00:02:12.594629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:12.594629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.04811","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":"2026-07-05T00:02:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UMkPhcyhJ6oNtGj7tyO+EzD87k0Q8aS6gLh+7VOef3D317pJ8KnuemT/gOcLvefRyqXfh7+6+nJzM7brlt7WCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:06:07.743670Z"},"content_sha256":"d9219bb2c715c978d97201a1b31510b988fb29fd051c2f11f6d72d19596ccab3","schema_version":"1.0","event_id":"sha256:d9219bb2c715c978d97201a1b31510b988fb29fd051c2f11f6d72d19596ccab3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YJGNZ3J7BMVXOXPME246CS265J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Michael I. Jordan, Praneeth Netrapalli, Rong Ge, Sham M. Kakade","submitted_at":"2019-02-13T09:44:02Z","abstract_excerpt":"Gradient descent (GD) and stochastic gradient descent (SGD) are the workhorses of large-scale machine learning. While classical theory focused on analyzing the performance of these methods in convex optimization problems, the most notable successes in machine learning have involved nonconvex optimization, and a gap has arisen between theory and practice. Indeed, traditional analyses of GD and SGD show that both algorithms converge to stationary points efficiently. But these analyses do not take into account the possibility of converging to saddle points. More recent theory has shown that GD an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04811","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/1902.04811/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":"2026-07-05T00:02:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lUyurPKyqLX04MwLU1Q1GuhuBQFN7be3RroQuUcgEN+1v96Az1QFW1tU/IANnyfCYPaxdZCh25CqwQGSiWx9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:06:07.744189Z"},"content_sha256":"ba07a84fe04d3f705aa2f7e094d4ec42c735af1ccbfb8fd44b45f9fef65e6773","schema_version":"1.0","event_id":"sha256:ba07a84fe04d3f705aa2f7e094d4ec42c735af1ccbfb8fd44b45f9fef65e6773"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJGNZ3J7BMVXOXPME246CS265J/bundle.json","state_url":"https://pith.science/pith/YJGNZ3J7BMVXOXPME246CS265J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJGNZ3J7BMVXOXPME246CS265J/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":"2026-08-09T21:06:07Z","links":{"resolver":"https://pith.science/pith/YJGNZ3J7BMVXOXPME246CS265J","bundle":"https://pith.science/pith/YJGNZ3J7BMVXOXPME246CS265J/bundle.json","state":"https://pith.science/pith/YJGNZ3J7BMVXOXPME246CS265J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJGNZ3J7BMVXOXPME246CS265J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YJGNZ3J7BMVXOXPME246CS265J","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":"a23b5866a71a9ec3f309af673a964c2bdc3c4afeb68a2b44b897d0a508887ee7","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T09:44:02Z","title_canon_sha256":"982a5c982193b84f10afe9d2b9c3578aa829c39e28753d167db422f394554008"},"schema_version":"1.0","source":{"id":"1902.04811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04811","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04811v2","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04811","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"pith_short_12","alias_value":"YJGNZ3J7BMVX","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"pith_short_16","alias_value":"YJGNZ3J7BMVXOXPM","created_at":"2026-07-05T00:02:12Z"},{"alias_kind":"pith_short_8","alias_value":"YJGNZ3J7","created_at":"2026-07-05T00:02:12Z"}],"graph_snapshots":[{"event_id":"sha256:ba07a84fe04d3f705aa2f7e094d4ec42c735af1ccbfb8fd44b45f9fef65e6773","target":"graph","created_at":"2026-07-05T00:02:12Z","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/1902.04811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient descent (GD) and stochastic gradient descent (SGD) are the workhorses of large-scale machine learning. While classical theory focused on analyzing the performance of these methods in convex optimization problems, the most notable successes in machine learning have involved nonconvex optimization, and a gap has arisen between theory and practice. Indeed, traditional analyses of GD and SGD show that both algorithms converge to stationary points efficiently. But these analyses do not take into account the possibility of converging to saddle points. More recent theory has shown that GD an","authors_text":"Chi Jin, Michael I. Jordan, Praneeth Netrapalli, Rong Ge, Sham M. Kakade","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T09:44:02Z","title":"On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04811","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:d9219bb2c715c978d97201a1b31510b988fb29fd051c2f11f6d72d19596ccab3","target":"record","created_at":"2026-07-05T00:02:12Z","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":"a23b5866a71a9ec3f309af673a964c2bdc3c4afeb68a2b44b897d0a508887ee7","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T09:44:02Z","title_canon_sha256":"982a5c982193b84f10afe9d2b9c3578aa829c39e28753d167db422f394554008"},"schema_version":"1.0","source":{"id":"1902.04811","kind":"arxiv","version":2}},"canonical_sha256":"c24cdced3f0b2b775dec26b9e14b5eea66eee3c4e150feed5793de96461f8479","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c24cdced3f0b2b775dec26b9e14b5eea66eee3c4e150feed5793de96461f8479","first_computed_at":"2026-07-05T00:02:12.594629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:12.594629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uJ2mJO9Rgo3sQ3BVt2/9ddA3vqWo/YbepEOSmWjYdCL4+KkmKoohboBhS497lbXptxCkYxVD+fpw4iecRyA8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:12.595115Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.04811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9219bb2c715c978d97201a1b31510b988fb29fd051c2f11f6d72d19596ccab3","sha256:ba07a84fe04d3f705aa2f7e094d4ec42c735af1ccbfb8fd44b45f9fef65e6773"],"state_sha256":"3dd6a46a22f839ffff0843f935d01a290472f4864bdb8ccc1618b13b4c0c708b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DKoGEHyvjEMbFV4V23WCQHQ6pw1D3TT30ErE3rubW5RhhHKHLj65JsByLH+N2CTOCCgugV9UHdZKM7yElEDEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:06:07.747638Z","bundle_sha256":"674e051c8ef8d6377a3ed20f1a2a62f82b0bfb2b53f7c36e7bb2844abec1ae22"}}