{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WBUJJT75UN5XBTVBWWFIBSQ6K5","short_pith_number":"pith:WBUJJT75","canonical_record":{"source":{"id":"1712.07296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-20T02:52:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d2c1f6d836aea76c78e77946ce8baa657e264cb9063ac1b66e82f3b5d1380d9f","abstract_canon_sha256":"210434054c17101dbf1e4b4e187f39a6cc2bc12633eca5c62897d623cf05094e"},"schema_version":"1.0"},"canonical_sha256":"b06894cffda37b70cea1b58a80ca1e575882c7ed015f68f5d29dc1e4e27fe3b9","source":{"kind":"arxiv","id":"1712.07296","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.07296","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"arxiv_version","alias_value":"1712.07296v1","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07296","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"pith_short_12","alias_value":"WBUJJT75UN5X","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WBUJJT75UN5XBTVB","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WBUJJT75","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WBUJJT75UN5XBTVBWWFIBSQ6K5","target":"record","payload":{"canonical_record":{"source":{"id":"1712.07296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-20T02:52:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d2c1f6d836aea76c78e77946ce8baa657e264cb9063ac1b66e82f3b5d1380d9f","abstract_canon_sha256":"210434054c17101dbf1e4b4e187f39a6cc2bc12633eca5c62897d623cf05094e"},"schema_version":"1.0"},"canonical_sha256":"b06894cffda37b70cea1b58a80ca1e575882c7ed015f68f5d29dc1e4e27fe3b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:34.939632Z","signature_b64":"iqsY3Zwew4jJIjrPg4klOkpqiVPYSRG9V/Qor5CO6q5MfpjRaElu5fAOKwuFJpCY+CM+4sNlnzzmjQakVd95Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b06894cffda37b70cea1b58a80ca1e575882c7ed015f68f5d29dc1e4e27fe3b9","last_reissued_at":"2026-05-18T00:27:34.939004Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:34.939004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.07296","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":"2026-05-18T00:27:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xSXQVB6V3b4TV+hnUTrYnGpNQ6bxsnjp7SKEI19EXfEBuJFbbuBdxaRSXXOVh8AND5iNiFX7Q4sLL8J7v7+eBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T02:44:42.782263Z"},"content_sha256":"d4187579942b6db478e4aa7107cb2839fb11c5afdf6f778188c1cbcbd1994942","schema_version":"1.0","event_id":"sha256:d4187579942b6db478e4aa7107cb2839fb11c5afdf6f778188c1cbcbd1994942"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WBUJJT75UN5XBTVBWWFIBSQ6K5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Block-diagonal Hessian-free Optimization for Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Caiming Xiong, Huishuai Zhang, James Bradbury, Richard Socher","submitted_at":"2017-12-20T02:52:35Z","abstract_excerpt":"Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are rarely applied to deep learning in practice because of high computational cost and the need for model-dependent algorithmic variations. We introduce a variant of the Hessian-free method that leverages a block-diagonal approximation of the generalized Gauss-Newton matrix. Our method computes the curvature approximation matrix only for pairs of parameters from the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07296","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":""},"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":"2026-05-18T00:27:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZzaPrMKNbutD4yaIFhIgjHqG8CpF8oqGzVOeW41ImiW4stKZUEUg2q0Mp4ibGHNPb+Py0QXW6uCe42g2N5iYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T02:44:42.782638Z"},"content_sha256":"992fd8e0716342c8d7868795e15cb162f5de6bdb6439655d3a7e033b87cc116c","schema_version":"1.0","event_id":"sha256:992fd8e0716342c8d7868795e15cb162f5de6bdb6439655d3a7e033b87cc116c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBUJJT75UN5XBTVBWWFIBSQ6K5/bundle.json","state_url":"https://pith.science/pith/WBUJJT75UN5XBTVBWWFIBSQ6K5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBUJJT75UN5XBTVBWWFIBSQ6K5/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":"2026-06-07T02:44:42Z","links":{"resolver":"https://pith.science/pith/WBUJJT75UN5XBTVBWWFIBSQ6K5","bundle":"https://pith.science/pith/WBUJJT75UN5XBTVBWWFIBSQ6K5/bundle.json","state":"https://pith.science/pith/WBUJJT75UN5XBTVBWWFIBSQ6K5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBUJJT75UN5XBTVBWWFIBSQ6K5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WBUJJT75UN5XBTVBWWFIBSQ6K5","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":"210434054c17101dbf1e4b4e187f39a6cc2bc12633eca5c62897d623cf05094e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-20T02:52:35Z","title_canon_sha256":"d2c1f6d836aea76c78e77946ce8baa657e264cb9063ac1b66e82f3b5d1380d9f"},"schema_version":"1.0","source":{"id":"1712.07296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.07296","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"arxiv_version","alias_value":"1712.07296v1","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07296","created_at":"2026-05-18T00:27:34Z"},{"alias_kind":"pith_short_12","alias_value":"WBUJJT75UN5X","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WBUJJT75UN5XBTVB","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WBUJJT75","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:992fd8e0716342c8d7868795e15cb162f5de6bdb6439655d3a7e033b87cc116c","target":"graph","created_at":"2026-05-18T00:27:34Z","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":"Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are rarely applied to deep learning in practice because of high computational cost and the need for model-dependent algorithmic variations. We introduce a variant of the Hessian-free method that leverages a block-diagonal approximation of the generalized Gauss-Newton matrix. Our method computes the curvature approximation matrix only for pairs of parameters from the ","authors_text":"Caiming Xiong, Huishuai Zhang, James Bradbury, Richard Socher","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-20T02:52:35Z","title":"Block-diagonal Hessian-free Optimization for Training Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07296","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:d4187579942b6db478e4aa7107cb2839fb11c5afdf6f778188c1cbcbd1994942","target":"record","created_at":"2026-05-18T00:27:34Z","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":"210434054c17101dbf1e4b4e187f39a6cc2bc12633eca5c62897d623cf05094e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-20T02:52:35Z","title_canon_sha256":"d2c1f6d836aea76c78e77946ce8baa657e264cb9063ac1b66e82f3b5d1380d9f"},"schema_version":"1.0","source":{"id":"1712.07296","kind":"arxiv","version":1}},"canonical_sha256":"b06894cffda37b70cea1b58a80ca1e575882c7ed015f68f5d29dc1e4e27fe3b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b06894cffda37b70cea1b58a80ca1e575882c7ed015f68f5d29dc1e4e27fe3b9","first_computed_at":"2026-05-18T00:27:34.939004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:34.939004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iqsY3Zwew4jJIjrPg4klOkpqiVPYSRG9V/Qor5CO6q5MfpjRaElu5fAOKwuFJpCY+CM+4sNlnzzmjQakVd95Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:34.939632Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.07296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4187579942b6db478e4aa7107cb2839fb11c5afdf6f778188c1cbcbd1994942","sha256:992fd8e0716342c8d7868795e15cb162f5de6bdb6439655d3a7e033b87cc116c"],"state_sha256":"8c3ea3058814bcb6f2981a68c10929cc9f3294036431b08593dfb85ca6ad65fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m934/huhLkijSy6sRjnwIrgOidQnDw7h1SlRXaktE/GyINsBNzK51T5sUqj/bWFZr89Fu4v9mg5QHUjlzJKyAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T02:44:42.784573Z","bundle_sha256":"a15a384b0ba9f3a06ae8248f98aa53b92321bae9647c4fec747d63189b9c2907"}}