{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UK2MV5ZJRMFWLVWZTIVFZMM5HU","short_pith_number":"pith:UK2MV5ZJ","schema_version":"1.0","canonical_sha256":"a2b4caf7298b0b65d6d99a2a5cb19d3d06df49959ba6b7614aa0727fbac2dfba","source":{"kind":"arxiv","id":"1912.07145","version":3},"attestation_state":"computed","paper":{"title":"PyHessian: Neural Networks Through the Lens of the Hessian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Amir Gholami, Kurt Keutzer, Michael Mahoney, Zhewei Yao","submitted_at":"2019-12-16T00:55:34Z","abstract_excerpt":"We present PYHESSIAN, a new scalable framework that enables fast computation of Hessian (i.e., second-order derivative) information for deep neural networks. PYHESSIAN enables fast computations of the top Hessian eigenvalues, the Hessian trace, and the full Hessian eigenvalue/spectral density, and it supports distributed-memory execution on cloud/supercomputer systems and is available as open source. This general framework can be used to analyze neural network models, including the topology of the loss landscape (i.e., curvature information) to gain insight into the behavior of different model"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.07145","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-16T00:55:34Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"62d11f5030c1779cff89ffeb82b5a5aa1e47c7f4a05a71599bb66e241c4d1911","abstract_canon_sha256":"f2c7d73308fd44e35543271f4873a0ac3624d500ea404ac0a7c71df478921724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:16.026104Z","signature_b64":"b8oooDVOFzVcsFD2ac+SyVtYrr3FMH5DxkJFxxAv5JqfDZC+7WxPO2LaFTNjbfbAFa9JpcdVIpmYE6qzE2duBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2b4caf7298b0b65d6d99a2a5cb19d3d06df49959ba6b7614aa0727fbac2dfba","last_reissued_at":"2026-07-05T02:33:16.025665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:16.025665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PyHessian: Neural Networks Through the Lens of the Hessian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Amir Gholami, Kurt Keutzer, Michael Mahoney, Zhewei Yao","submitted_at":"2019-12-16T00:55:34Z","abstract_excerpt":"We present PYHESSIAN, a new scalable framework that enables fast computation of Hessian (i.e., second-order derivative) information for deep neural networks. PYHESSIAN enables fast computations of the top Hessian eigenvalues, the Hessian trace, and the full Hessian eigenvalue/spectral density, and it supports distributed-memory execution on cloud/supercomputer systems and is available as open source. This general framework can be used to analyze neural network models, including the topology of the loss landscape (i.e., curvature information) to gain insight into the behavior of different model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07145","kind":"arxiv","version":3},"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/1912.07145/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.07145","created_at":"2026-07-05T02:33:16.025724+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.07145v3","created_at":"2026-07-05T02:33:16.025724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07145","created_at":"2026-07-05T02:33:16.025724+00:00"},{"alias_kind":"pith_short_12","alias_value":"UK2MV5ZJRMFW","created_at":"2026-07-05T02:33:16.025724+00:00"},{"alias_kind":"pith_short_16","alias_value":"UK2MV5ZJRMFWLVWZ","created_at":"2026-07-05T02:33:16.025724+00:00"},{"alias_kind":"pith_short_8","alias_value":"UK2MV5ZJ","created_at":"2026-07-05T02:33:16.025724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23434","citing_title":"When Does Removing LayerNorm Help? Activation Bounding as a Regime-Dependent Implicit Regularizer","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU","json":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU.json","graph_json":"https://pith.science/api/pith-number/UK2MV5ZJRMFWLVWZTIVFZMM5HU/graph.json","events_json":"https://pith.science/api/pith-number/UK2MV5ZJRMFWLVWZTIVFZMM5HU/events.json","paper":"https://pith.science/paper/UK2MV5ZJ"},"agent_actions":{"view_html":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU","download_json":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU.json","view_paper":"https://pith.science/paper/UK2MV5ZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.07145&json=true","fetch_graph":"https://pith.science/api/pith-number/UK2MV5ZJRMFWLVWZTIVFZMM5HU/graph.json","fetch_events":"https://pith.science/api/pith-number/UK2MV5ZJRMFWLVWZTIVFZMM5HU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU/action/storage_attestation","attest_author":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU/action/author_attestation","sign_citation":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU/action/citation_signature","submit_replication":"https://pith.science/pith/UK2MV5ZJRMFWLVWZTIVFZMM5HU/action/replication_record"}},"created_at":"2026-07-05T02:33:16.025724+00:00","updated_at":"2026-07-05T02:33:16.025724+00:00"}