{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5YGXXO4KMXXFLUJAIZIM5DXSKM","short_pith_number":"pith:5YGXXO4K","canonical_record":{"source":{"id":"1909.01994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T15:52:08Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e406386dfd913b69fb214d5dcec68c8edee6ce00eaf452203cd1f8e2974ff083","abstract_canon_sha256":"e26e5188ebd14c4ed3ae1d386e96e77d0b47f03b34234e78cd391d1fe514407f"},"schema_version":"1.0"},"canonical_sha256":"ee0d7bbb8a65ee55d1204650ce8ef25303b6f0f2ae5a58cccc9b026e7e6689aa","source":{"kind":"arxiv","id":"1909.01994","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01994","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01994v1","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01994","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"5YGXXO4KMXXF","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"5YGXXO4KMXXFLUJA","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"5YGXXO4K","created_at":"2026-07-05T00:02:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5YGXXO4KMXXFLUJAIZIM5DXSKM","target":"record","payload":{"canonical_record":{"source":{"id":"1909.01994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T15:52:08Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e406386dfd913b69fb214d5dcec68c8edee6ce00eaf452203cd1f8e2974ff083","abstract_canon_sha256":"e26e5188ebd14c4ed3ae1d386e96e77d0b47f03b34234e78cd391d1fe514407f"},"schema_version":"1.0"},"canonical_sha256":"ee0d7bbb8a65ee55d1204650ce8ef25303b6f0f2ae5a58cccc9b026e7e6689aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:29.461182Z","signature_b64":"DFC3oJqT3PO6ee/7cWP3HCd0F5ZoDWEFF8fatgkxCgxprOb6z6qS5Y74Eodv8jqCPFxX5BxvJVmXu2knxWlNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee0d7bbb8a65ee55d1204650ce8ef25303b6f0f2ae5a58cccc9b026e7e6689aa","last_reissued_at":"2026-07-05T00:02:29.460257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:29.460257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.01994","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2cS5ykrm8VrHzyzfM6NzqP3GxnS9FL2pS/IcLx+WtPXXHemAwJh/LKFzMs2v+CBcWECM67tGdrbt6U9sKVeIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:43:07.097074Z"},"content_sha256":"305e6d44db21ce72b23161659334647cb15742ca00b0a0ae3b4ec3160f720482","schema_version":"1.0","event_id":"sha256:305e6d44db21ce72b23161659334647cb15742ca00b0a0ae3b4ec3160f720482"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5YGXXO4KMXXFLUJAIZIM5DXSKM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quasi-Newton Optimization Methods For Deep Learning Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacob Rafati, Roummel F. Marcia","submitted_at":"2019-09-04T15:52:08Z","abstract_excerpt":"Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machine learning, such as deep learning and deep reinforcement learning (RL), are generally restricted to the class of first-order algorithms, like stochastic gradient descent (SGD). While SGD iterates are inexpensive to compute, they have slow theoretical convergence rates. Furthermore, they require exhaustive trial-and-error to fine-tune many learning parameters. Using second-order curvature information to find search di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01994","kind":"arxiv","version":1},"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/1909.01994/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":"2026-07-05T00:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hdo4VXbwnFOsF4GS608VpaW9+M3bSgjWbeFlYW2di5oZ1q7a+lGSmITkfxZ1BsM8kI0kmMrFLEFDMc1Kvx1lDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:43:07.097586Z"},"content_sha256":"c9d3c6de741246fb7a8a45c6e07099d2e8e3e1689251a44d1d8e6b4bdecc1249","schema_version":"1.0","event_id":"sha256:c9d3c6de741246fb7a8a45c6e07099d2e8e3e1689251a44d1d8e6b4bdecc1249"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YGXXO4KMXXFLUJAIZIM5DXSKM/bundle.json","state_url":"https://pith.science/pith/5YGXXO4KMXXFLUJAIZIM5DXSKM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YGXXO4KMXXFLUJAIZIM5DXSKM/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":"2026-08-22T23:43:07Z","links":{"resolver":"https://pith.science/pith/5YGXXO4KMXXFLUJAIZIM5DXSKM","bundle":"https://pith.science/pith/5YGXXO4KMXXFLUJAIZIM5DXSKM/bundle.json","state":"https://pith.science/pith/5YGXXO4KMXXFLUJAIZIM5DXSKM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YGXXO4KMXXFLUJAIZIM5DXSKM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5YGXXO4KMXXFLUJAIZIM5DXSKM","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":"e26e5188ebd14c4ed3ae1d386e96e77d0b47f03b34234e78cd391d1fe514407f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T15:52:08Z","title_canon_sha256":"e406386dfd913b69fb214d5dcec68c8edee6ce00eaf452203cd1f8e2974ff083"},"schema_version":"1.0","source":{"id":"1909.01994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01994","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01994v1","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01994","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"5YGXXO4KMXXF","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"5YGXXO4KMXXFLUJA","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"5YGXXO4K","created_at":"2026-07-05T00:02:29Z"}],"graph_snapshots":[{"event_id":"sha256:c9d3c6de741246fb7a8a45c6e07099d2e8e3e1689251a44d1d8e6b4bdecc1249","target":"graph","created_at":"2026-07-05T00:02:29Z","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/1909.01994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machine learning, such as deep learning and deep reinforcement learning (RL), are generally restricted to the class of first-order algorithms, like stochastic gradient descent (SGD). While SGD iterates are inexpensive to compute, they have slow theoretical convergence rates. Furthermore, they require exhaustive trial-and-error to fine-tune many learning parameters. Using second-order curvature information to find search di","authors_text":"Jacob Rafati, Roummel F. Marcia","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01994","kind":"arxiv","version":1},"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":"sha256:305e6d44db21ce72b23161659334647cb15742ca00b0a0ae3b4ec3160f720482","target":"record","created_at":"2026-07-05T00:02:29Z","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":"e26e5188ebd14c4ed3ae1d386e96e77d0b47f03b34234e78cd391d1fe514407f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T15:52:08Z","title_canon_sha256":"e406386dfd913b69fb214d5dcec68c8edee6ce00eaf452203cd1f8e2974ff083"},"schema_version":"1.0","source":{"id":"1909.01994","kind":"arxiv","version":1}},"canonical_sha256":"ee0d7bbb8a65ee55d1204650ce8ef25303b6f0f2ae5a58cccc9b026e7e6689aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee0d7bbb8a65ee55d1204650ce8ef25303b6f0f2ae5a58cccc9b026e7e6689aa","first_computed_at":"2026-07-05T00:02:29.460257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:29.460257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DFC3oJqT3PO6ee/7cWP3HCd0F5ZoDWEFF8fatgkxCgxprOb6z6qS5Y74Eodv8jqCPFxX5BxvJVmXu2knxWlNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:29.461182Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:305e6d44db21ce72b23161659334647cb15742ca00b0a0ae3b4ec3160f720482","sha256:c9d3c6de741246fb7a8a45c6e07099d2e8e3e1689251a44d1d8e6b4bdecc1249"],"state_sha256":"4d9235ba7dd5df6e1327a194dce460893c0bf9686e31d636cd45381da20922d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2NS6E+Hg8r2+G+N3bYFVxIUp2ET5ahqwQN21a+Dg5woWyiZIexk47dGuuwJIMCljxwSehnTgiMRuKYq+BYMZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:43:07.101905Z","bundle_sha256":"ab3e6e47fd3029b4edb8d1a6b19806e37c5ce186831c9c4ff0963446a0519aac"}}