{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KJLMSZFB4SSLE2MRV5LQ4FPHOJ","short_pith_number":"pith:KJLMSZFB","canonical_record":{"source":{"id":"1802.06502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-19T02:31:24Z","cross_cats_sorted":[],"title_canon_sha256":"d4e8025d019ce3f0f6d586879203a7b400477601fb9a19dca0e1fd5b13217846","abstract_canon_sha256":"3672644e7dae9f683674683072a37ff1b18cb9eee0255a6ec216d274309abc63"},"schema_version":"1.0"},"canonical_sha256":"5256c964a1e4a4b26991af570e15e7724a62657797f5064b7e22e71e1cc4ca93","source":{"kind":"arxiv","id":"1802.06502","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06502","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06502v3","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06502","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"KJLMSZFB4SSL","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KJLMSZFB4SSLE2MR","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KJLMSZFB","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KJLMSZFB4SSLE2MRV5LQ4FPHOJ","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-19T02:31:24Z","cross_cats_sorted":[],"title_canon_sha256":"d4e8025d019ce3f0f6d586879203a7b400477601fb9a19dca0e1fd5b13217846","abstract_canon_sha256":"3672644e7dae9f683674683072a37ff1b18cb9eee0255a6ec216d274309abc63"},"schema_version":"1.0"},"canonical_sha256":"5256c964a1e4a4b26991af570e15e7724a62657797f5064b7e22e71e1cc4ca93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:59.264701Z","signature_b64":"nFI20t+/8kajtjYchXbRQJ/EwTh36XBLTIwaaPQ6QptXN/j9FiOwgd2GYx81YCwCxdpByy2RXIrCVAHpej2SCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5256c964a1e4a4b26991af570e15e7724a62657797f5064b7e22e71e1cc4ca93","last_reissued_at":"2026-05-17T23:58:59.264133Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:59.264133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06502","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uoGTfiZ/IAb8wB2EbiUM9tUhCbo+L537JBHlQE5hyCiMbNszvmbMWR+Q9RI5PwQJxRfZ53HtCBanJMTQCDmuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:52:28.550668Z"},"content_sha256":"37d99d6eb35f590af2599aa20c0cf19d35edc062c6dd71c16646a7497c7b5376","schema_version":"1.0","event_id":"sha256:37d99d6eb35f590af2599aa20c0cf19d35edc062c6dd71c16646a7497c7b5376"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KJLMSZFB4SSLE2MRV5LQ4FPHOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EA-CG: An Approximate Second-Order Method for Training Fully-Connected Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chun-Nan Chou, Edward Y. Chang, Sheng-Wei Chen","submitted_at":"2018-02-19T02:31:24Z","abstract_excerpt":"For training fully-connected neural networks (FCNNs), we propose a practical approximate second-order method including: 1) an approximation of the Hessian matrix and 2) a conjugate gradient (CG) based method. Our proposed approximate Hessian matrix is memory-efficient and can be applied to any FCNNs where the activation and criterion functions are twice differentiable. We devise a CG-based method incorporating one-rank approximation to derive Newton directions for training FCNNs, which significantly reduces both space and time complexity. This CG-based method can be employed to solve any linea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06502","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":""},"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":"2026-05-17T23:58:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GLjHvK3zi2wUEjQWKeWHbEiEshJDOpW2opR2SFENpJBBMuILvDux1DZOWcWcORTUzn8KgcCujPMarm33jaJECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:52:28.551014Z"},"content_sha256":"498271dc1947d89e0ace41ef032033a7ce7c342f98f1a25c162f6137b56e36b7","schema_version":"1.0","event_id":"sha256:498271dc1947d89e0ace41ef032033a7ce7c342f98f1a25c162f6137b56e36b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJLMSZFB4SSLE2MRV5LQ4FPHOJ/bundle.json","state_url":"https://pith.science/pith/KJLMSZFB4SSLE2MRV5LQ4FPHOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJLMSZFB4SSLE2MRV5LQ4FPHOJ/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":"2026-06-03T22:52:28Z","links":{"resolver":"https://pith.science/pith/KJLMSZFB4SSLE2MRV5LQ4FPHOJ","bundle":"https://pith.science/pith/KJLMSZFB4SSLE2MRV5LQ4FPHOJ/bundle.json","state":"https://pith.science/pith/KJLMSZFB4SSLE2MRV5LQ4FPHOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJLMSZFB4SSLE2MRV5LQ4FPHOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KJLMSZFB4SSLE2MRV5LQ4FPHOJ","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":"3672644e7dae9f683674683072a37ff1b18cb9eee0255a6ec216d274309abc63","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-19T02:31:24Z","title_canon_sha256":"d4e8025d019ce3f0f6d586879203a7b400477601fb9a19dca0e1fd5b13217846"},"schema_version":"1.0","source":{"id":"1802.06502","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06502","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06502v3","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06502","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"KJLMSZFB4SSL","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KJLMSZFB4SSLE2MR","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KJLMSZFB","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:498271dc1947d89e0ace41ef032033a7ce7c342f98f1a25c162f6137b56e36b7","target":"graph","created_at":"2026-05-17T23:58:59Z","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":"For training fully-connected neural networks (FCNNs), we propose a practical approximate second-order method including: 1) an approximation of the Hessian matrix and 2) a conjugate gradient (CG) based method. Our proposed approximate Hessian matrix is memory-efficient and can be applied to any FCNNs where the activation and criterion functions are twice differentiable. We devise a CG-based method incorporating one-rank approximation to derive Newton directions for training FCNNs, which significantly reduces both space and time complexity. This CG-based method can be employed to solve any linea","authors_text":"Chun-Nan Chou, Edward Y. Chang, Sheng-Wei Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-19T02:31:24Z","title":"EA-CG: An Approximate Second-Order Method for Training Fully-Connected Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06502","kind":"arxiv","version":3},"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":"sha256:37d99d6eb35f590af2599aa20c0cf19d35edc062c6dd71c16646a7497c7b5376","target":"record","created_at":"2026-05-17T23:58:59Z","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":"3672644e7dae9f683674683072a37ff1b18cb9eee0255a6ec216d274309abc63","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-19T02:31:24Z","title_canon_sha256":"d4e8025d019ce3f0f6d586879203a7b400477601fb9a19dca0e1fd5b13217846"},"schema_version":"1.0","source":{"id":"1802.06502","kind":"arxiv","version":3}},"canonical_sha256":"5256c964a1e4a4b26991af570e15e7724a62657797f5064b7e22e71e1cc4ca93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5256c964a1e4a4b26991af570e15e7724a62657797f5064b7e22e71e1cc4ca93","first_computed_at":"2026-05-17T23:58:59.264133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:59.264133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nFI20t+/8kajtjYchXbRQJ/EwTh36XBLTIwaaPQ6QptXN/j9FiOwgd2GYx81YCwCxdpByy2RXIrCVAHpej2SCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:59.264701Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06502","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37d99d6eb35f590af2599aa20c0cf19d35edc062c6dd71c16646a7497c7b5376","sha256:498271dc1947d89e0ace41ef032033a7ce7c342f98f1a25c162f6137b56e36b7"],"state_sha256":"8e79e7fb1d47fece4b69f067d0ad5d76c1ec0bbee202e6e6586f3da8cb06522b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"snuCcK5iPjC9QYe6c8RZ/+yt6yI286yD3m9vxwhDduZOjg76dpJwQveekkZ3md42efG15RJqzcevoam3XTY9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T22:52:28.552951Z","bundle_sha256":"6637bf0b5eccb3049362255ed1a22a63e0fa4a7a1dc2c676e1ad9e0889fccb76"}}