{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3Y2FRNGMC2BCSS4R6JQQMJONB2","short_pith_number":"pith:3Y2FRNGM","canonical_record":{"source":{"id":"2502.12298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-17T20:20:11Z","cross_cats_sorted":["cs.IT","cs.LG","cs.NA","math.IT","math.NA","stat.ML"],"title_canon_sha256":"4b64b49d82e988b091abe5e041e41e4572b10b59ec9ea5af26126de82f6e97a5","abstract_canon_sha256":"72cb8638e6f7797991b76fe41dfafcbd66a5fdfd36bf3414d67c7101cd81e1cf"},"schema_version":"1.0"},"canonical_sha256":"de3458b4cc1682294b91f2610625cd0eacf7ebd9ebc739ade5e33397f0a9fd4b","source":{"kind":"arxiv","id":"2502.12298","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12298","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12298v1","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12298","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"3Y2FRNGMC2BC","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"3Y2FRNGMC2BCSS4R","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"3Y2FRNGM","created_at":"2026-07-05T10:15:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3Y2FRNGMC2BCSS4R6JQQMJONB2","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-17T20:20:11Z","cross_cats_sorted":["cs.IT","cs.LG","cs.NA","math.IT","math.NA","stat.ML"],"title_canon_sha256":"4b64b49d82e988b091abe5e041e41e4572b10b59ec9ea5af26126de82f6e97a5","abstract_canon_sha256":"72cb8638e6f7797991b76fe41dfafcbd66a5fdfd36bf3414d67c7101cd81e1cf"},"schema_version":"1.0"},"canonical_sha256":"de3458b4cc1682294b91f2610625cd0eacf7ebd9ebc739ade5e33397f0a9fd4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:53.141682Z","signature_b64":"o5z0FqZaUZluTxKkSvkd37DWSA49nHQrshAJ1aNUS/7w82Oa8ipgR3lMwgWKkAQstfZv5bt5BYrV5s4tDGEHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de3458b4cc1682294b91f2610625cd0eacf7ebd9ebc739ade5e33397f0a9fd4b","last_reissued_at":"2026-07-05T10:15:53.141172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:53.141172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12298","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":"2026-07-05T10:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjEedHvJZlGTwh4WqCLKj1OxR8xr5Cx5szRR3D9v51hk/e0Y/r9YxSknPeLgpMVb4fR3jwDbkHyDSx2C03FKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:06:29.493544Z"},"content_sha256":"ced997f24023c2faa2a8d86ef25a460c9ae6ffad1f2655d92cc0578e1fb8704b","schema_version":"1.0","event_id":"sha256:ced997f24023c2faa2a8d86ef25a460c9ae6ffad1f2655d92cc0578e1fb8704b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3Y2FRNGMC2BCSS4R6JQQMJONB2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","cs.NA","math.IT","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Aditya Ranganath, Mukesh Singhal, Roummel Marcia","submitted_at":"2025-02-17T20:20:11Z","abstract_excerpt":"Stochastic gradient descent and other first-order variants, such as Adam and AdaGrad, are commonly used in the field of deep learning due to their computational efficiency and low-storage memory requirements. However, these methods do not exploit curvature information. Consequently, iterates can converge to saddle points or poor local minima. On the other hand, Quasi-Newton methods compute Hessian approximations which exploit this information with a comparable computational budget. Quasi-Newton methods re-use previously computed iterates and gradients to compute a low-rank structured update. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12298","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/2502.12298/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":"2026-07-05T10:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"092qoSU6SptZK0LLClRw3S7naFJjs1ZNwn2uDAixI+gSDYfqoDdTQTjFHRq5bTATzR8qmC/L2GB2u5KjbIzRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:06:29.494142Z"},"content_sha256":"ccf7cc15c04e7b659908345f8d85f5a27acfd4b04d9cf374d607691c95e4e97a","schema_version":"1.0","event_id":"sha256:ccf7cc15c04e7b659908345f8d85f5a27acfd4b04d9cf374d607691c95e4e97a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3Y2FRNGMC2BCSS4R6JQQMJONB2/bundle.json","state_url":"https://pith.science/pith/3Y2FRNGMC2BCSS4R6JQQMJONB2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3Y2FRNGMC2BCSS4R6JQQMJONB2/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":"2026-08-07T00:06:29Z","links":{"resolver":"https://pith.science/pith/3Y2FRNGMC2BCSS4R6JQQMJONB2","bundle":"https://pith.science/pith/3Y2FRNGMC2BCSS4R6JQQMJONB2/bundle.json","state":"https://pith.science/pith/3Y2FRNGMC2BCSS4R6JQQMJONB2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3Y2FRNGMC2BCSS4R6JQQMJONB2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3Y2FRNGMC2BCSS4R6JQQMJONB2","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":"72cb8638e6f7797991b76fe41dfafcbd66a5fdfd36bf3414d67c7101cd81e1cf","cross_cats_sorted":["cs.IT","cs.LG","cs.NA","math.IT","math.NA","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-17T20:20:11Z","title_canon_sha256":"4b64b49d82e988b091abe5e041e41e4572b10b59ec9ea5af26126de82f6e97a5"},"schema_version":"1.0","source":{"id":"2502.12298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12298","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12298v1","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12298","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"3Y2FRNGMC2BC","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"3Y2FRNGMC2BCSS4R","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"3Y2FRNGM","created_at":"2026-07-05T10:15:53Z"}],"graph_snapshots":[{"event_id":"sha256:ccf7cc15c04e7b659908345f8d85f5a27acfd4b04d9cf374d607691c95e4e97a","target":"graph","created_at":"2026-07-05T10:15:53Z","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/2502.12298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic gradient descent and other first-order variants, such as Adam and AdaGrad, are commonly used in the field of deep learning due to their computational efficiency and low-storage memory requirements. However, these methods do not exploit curvature information. Consequently, iterates can converge to saddle points or poor local minima. On the other hand, Quasi-Newton methods compute Hessian approximations which exploit this information with a comparable computational budget. Quasi-Newton methods re-use previously computed iterates and gradients to compute a low-rank structured update. T","authors_text":"Aditya Ranganath, Mukesh Singhal, Roummel Marcia","cross_cats":["cs.IT","cs.LG","cs.NA","math.IT","math.NA","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-17T20:20:11Z","title":"Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12298","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:ced997f24023c2faa2a8d86ef25a460c9ae6ffad1f2655d92cc0578e1fb8704b","target":"record","created_at":"2026-07-05T10:15:53Z","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":"72cb8638e6f7797991b76fe41dfafcbd66a5fdfd36bf3414d67c7101cd81e1cf","cross_cats_sorted":["cs.IT","cs.LG","cs.NA","math.IT","math.NA","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-17T20:20:11Z","title_canon_sha256":"4b64b49d82e988b091abe5e041e41e4572b10b59ec9ea5af26126de82f6e97a5"},"schema_version":"1.0","source":{"id":"2502.12298","kind":"arxiv","version":1}},"canonical_sha256":"de3458b4cc1682294b91f2610625cd0eacf7ebd9ebc739ade5e33397f0a9fd4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de3458b4cc1682294b91f2610625cd0eacf7ebd9ebc739ade5e33397f0a9fd4b","first_computed_at":"2026-07-05T10:15:53.141172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:53.141172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o5z0FqZaUZluTxKkSvkd37DWSA49nHQrshAJ1aNUS/7w82Oa8ipgR3lMwgWKkAQstfZv5bt5BYrV5s4tDGEHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:53.141682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ced997f24023c2faa2a8d86ef25a460c9ae6ffad1f2655d92cc0578e1fb8704b","sha256:ccf7cc15c04e7b659908345f8d85f5a27acfd4b04d9cf374d607691c95e4e97a"],"state_sha256":"a800ce63e188e74e521eb6489430fcae4978cc6851b9a00571b8c6dbe6728452"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"axv4LH2yQmkzyndp92IMO5Bpjhydo1nAsywGNXbhymVqKDwWBVyehjZVVCEsL9vol5y0ENosUlsHnQrwiRbIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:06:29.502182Z","bundle_sha256":"9ea09047cd3e84a5a5425fadf20ad8150900a6a0e496ca900c7f3047e8326213"}}