{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:V4SCL3ITBPYUVXZB3ULAZOAUTM","short_pith_number":"pith:V4SCL3IT","canonical_record":{"source":{"id":"1706.03662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T14:39:48Z","cross_cats_sorted":[],"title_canon_sha256":"d3da0a8e5a930bfb4791046bbd7f395cfc1d01c1ac29a352c0a6ff104914706b","abstract_canon_sha256":"fdb3daa7220985cfbc1f443b1eb3514ddd4d40409150b423a2b7a33f1ca4d475"},"schema_version":"1.0"},"canonical_sha256":"af2425ed130bf14adf21dd160cb8149b32bad8ffd2b2a645a90cdefac3ecb38b","source":{"kind":"arxiv","id":"1706.03662","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03662","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03662v2","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03662","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"V4SCL3ITBPYU","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V4SCL3ITBPYUVXZB","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V4SCL3IT","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:V4SCL3ITBPYUVXZB3ULAZOAUTM","target":"record","payload":{"canonical_record":{"source":{"id":"1706.03662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T14:39:48Z","cross_cats_sorted":[],"title_canon_sha256":"d3da0a8e5a930bfb4791046bbd7f395cfc1d01c1ac29a352c0a6ff104914706b","abstract_canon_sha256":"fdb3daa7220985cfbc1f443b1eb3514ddd4d40409150b423a2b7a33f1ca4d475"},"schema_version":"1.0"},"canonical_sha256":"af2425ed130bf14adf21dd160cb8149b32bad8ffd2b2a645a90cdefac3ecb38b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:28.368992Z","signature_b64":"FzbSbCgiWxEWkbH4Nij7Q+PyTyVsWdhAxZRSLhcXpfi+NGF97wQ51oDEby2CjwA88nGNLLcXoDqfJnNp5x+bDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af2425ed130bf14adf21dd160cb8149b32bad8ffd2b2a645a90cdefac3ecb38b","last_reissued_at":"2026-05-18T00:42:28.368525Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:28.368525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.03662","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":"2026-05-18T00:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mY7BDH2EzKDEIvWS4If0yBHEA9tVUFtJrN/vYwoUnBAeRJv4YDO2cP2GWvkrG4aW3Teb0SLHzS3uoMvDiYCDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:01:43.652245Z"},"content_sha256":"4c2cf49cb223a4bdc02893d90f6389e78145d80e02c55aaa8f40ca05be566896","schema_version":"1.0","event_id":"sha256:4c2cf49cb223a4bdc02893d90f6389e78145d80e02c55aaa8f40ca05be566896"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:V4SCL3ITBPYUVXZB3ULAZOAUTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Practical Gauss-Newton Optimisation for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Aleksandar Botev, David Barber, Hippolyt Ritter","submitted_at":"2017-06-12T14:39:48Z","abstract_excerpt":"We present an efficient block-diagonal ap- proximation to the Gauss-Newton matrix for feedforward neural networks. Our result- ing algorithm is competitive against state- of-the-art first order optimisation methods, with sometimes significant improvement in optimisation performance. Unlike first-order methods, for which hyperparameter tuning of the optimisation parameters is often a labo- rious process, our approach can provide good performance even when used with default set- tings. A side result of our work is that for piecewise linear transfer functions, the net- work objective function can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03662","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":"2026-05-18T00:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8fDLkpb231JYB9JnQOkjVWU+n49AkzzDl1cnKlhcIBIvUW8dXl5qbZpZSP9WEO+4JYgE3oTXDmGwRyxRyRjTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:01:43.652721Z"},"content_sha256":"3424f270fd6ed6790614b5d3ec367a2929aca917f9aa1efcf97acd6733d83974","schema_version":"1.0","event_id":"sha256:3424f270fd6ed6790614b5d3ec367a2929aca917f9aa1efcf97acd6733d83974"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4SCL3ITBPYUVXZB3ULAZOAUTM/bundle.json","state_url":"https://pith.science/pith/V4SCL3ITBPYUVXZB3ULAZOAUTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4SCL3ITBPYUVXZB3ULAZOAUTM/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":"2026-08-06T21:01:43Z","links":{"resolver":"https://pith.science/pith/V4SCL3ITBPYUVXZB3ULAZOAUTM","bundle":"https://pith.science/pith/V4SCL3ITBPYUVXZB3ULAZOAUTM/bundle.json","state":"https://pith.science/pith/V4SCL3ITBPYUVXZB3ULAZOAUTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4SCL3ITBPYUVXZB3ULAZOAUTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:V4SCL3ITBPYUVXZB3ULAZOAUTM","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":"fdb3daa7220985cfbc1f443b1eb3514ddd4d40409150b423a2b7a33f1ca4d475","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T14:39:48Z","title_canon_sha256":"d3da0a8e5a930bfb4791046bbd7f395cfc1d01c1ac29a352c0a6ff104914706b"},"schema_version":"1.0","source":{"id":"1706.03662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03662","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03662v2","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03662","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"V4SCL3ITBPYU","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V4SCL3ITBPYUVXZB","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V4SCL3IT","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:3424f270fd6ed6790614b5d3ec367a2929aca917f9aa1efcf97acd6733d83974","target":"graph","created_at":"2026-05-18T00:42:28Z","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":"We present an efficient block-diagonal ap- proximation to the Gauss-Newton matrix for feedforward neural networks. Our result- ing algorithm is competitive against state- of-the-art first order optimisation methods, with sometimes significant improvement in optimisation performance. Unlike first-order methods, for which hyperparameter tuning of the optimisation parameters is often a labo- rious process, our approach can provide good performance even when used with default set- tings. A side result of our work is that for piecewise linear transfer functions, the net- work objective function can","authors_text":"Aleksandar Botev, David Barber, Hippolyt Ritter","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T14:39:48Z","title":"Practical Gauss-Newton Optimisation for Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03662","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":"sha256:4c2cf49cb223a4bdc02893d90f6389e78145d80e02c55aaa8f40ca05be566896","target":"record","created_at":"2026-05-18T00:42:28Z","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":"fdb3daa7220985cfbc1f443b1eb3514ddd4d40409150b423a2b7a33f1ca4d475","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T14:39:48Z","title_canon_sha256":"d3da0a8e5a930bfb4791046bbd7f395cfc1d01c1ac29a352c0a6ff104914706b"},"schema_version":"1.0","source":{"id":"1706.03662","kind":"arxiv","version":2}},"canonical_sha256":"af2425ed130bf14adf21dd160cb8149b32bad8ffd2b2a645a90cdefac3ecb38b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af2425ed130bf14adf21dd160cb8149b32bad8ffd2b2a645a90cdefac3ecb38b","first_computed_at":"2026-05-18T00:42:28.368525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:28.368525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FzbSbCgiWxEWkbH4Nij7Q+PyTyVsWdhAxZRSLhcXpfi+NGF97wQ51oDEby2CjwA88nGNLLcXoDqfJnNp5x+bDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:28.368992Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.03662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c2cf49cb223a4bdc02893d90f6389e78145d80e02c55aaa8f40ca05be566896","sha256:3424f270fd6ed6790614b5d3ec367a2929aca917f9aa1efcf97acd6733d83974"],"state_sha256":"bd07545fad03636f929c96516d652ca27338b8bb07bf3135202aa745d4a89d37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2yqRkUvxcL57NMyqWa1UBGZY/RzzN5uJQluZMD0oRO7dj+pn+Mka8QMSZ80BphfsQp7Vx7njpVA08FDcA2GZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:01:43.658047Z","bundle_sha256":"42f65401634e887e41fe56a5d0998cceceebaa843d3ec4be0155e2e591b71799"}}