{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OBMJYVVX3Q67I2JJMTD64FKTYB","short_pith_number":"pith:OBMJYVVX","canonical_record":{"source":{"id":"1605.09593","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T12:11:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ff50778514bf5b25909d479b127260b39ff7b3a3c2c6f69c21823bebe7b201c2","abstract_canon_sha256":"af987786de35740f684e5361d9a6364a55df0a160a518c00eb0cd80ac8174555"},"schema_version":"1.0"},"canonical_sha256":"70589c56b7dc3df4692964c7ee1553c0414d59bc9975053a282252c2560528c2","source":{"kind":"arxiv","id":"1605.09593","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.09593","created_at":"2026-05-18T00:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"1605.09593v2","created_at":"2026-05-18T00:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09593","created_at":"2026-05-18T00:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"OBMJYVVX3Q67","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OBMJYVVX3Q67I2JJ","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OBMJYVVX","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OBMJYVVX3Q67I2JJMTD64FKTYB","target":"record","payload":{"canonical_record":{"source":{"id":"1605.09593","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T12:11:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ff50778514bf5b25909d479b127260b39ff7b3a3c2c6f69c21823bebe7b201c2","abstract_canon_sha256":"af987786de35740f684e5361d9a6364a55df0a160a518c00eb0cd80ac8174555"},"schema_version":"1.0"},"canonical_sha256":"70589c56b7dc3df4692964c7ee1553c0414d59bc9975053a282252c2560528c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:10.419530Z","signature_b64":"i0WnFEryIcnZ4Jl8pkRnIuIs5b2o7OSbG5idZvjPh92ZDzyB3btYfAAqR6jTeusFDeYhOAIsm4gWpquZUZajCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70589c56b7dc3df4692964c7ee1553c0414d59bc9975053a282252c2560528c2","last_reissued_at":"2026-05-18T00:34:10.418775Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:10.418775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.09593","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":"2026-05-18T00:34:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ssPW4eQwQcb0Q/FfDcwRGxDMJS0oUBPTHFDu8vUzoUq2H3aJyRKcSqPU/rQ1KpoV6//1/NybZTgUga86f7OACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T10:18:45.446510Z"},"content_sha256":"f3aaf2dbfc4cb3092ece9d720b749b7ff3ba64aad7e98fed11927cf7640137ed","schema_version":"1.0","event_id":"sha256:f3aaf2dbfc4cb3092ece9d720b749b7ff3ba64aad7e98fed11927cf7640137ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OBMJYVVX3Q67I2JJMTD64FKTYB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Sotetsu Iwamura, Yasuhiro Fujiwara, Yasutoshi Ida","submitted_at":"2016-05-31T12:11:51Z","abstract_excerpt":"Adaptive learning rate algorithms such as RMSProp are widely used for training deep neural networks. RMSProp offers efficient training since it uses first order gradients to approximate Hessian-based preconditioning. However, since the first order gradients include noise caused by stochastic optimization, the approximation may be inaccurate. In this paper, we propose a novel adaptive learning rate algorithm called SDProp. Its key idea is effective handling of the noise by preconditioning based on covariance matrix. For various neural networks, our approach is more efficient and effective than "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09593","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":"2026-05-18T00:34:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rY4j0M66rrOmkvR0O5zPlO0YhGK0ukRQrE7eutNIJFn396NW5A2aIQ3k4lOzmVF9v204UqMQETWbMgBoP0KMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T10:18:45.446846Z"},"content_sha256":"4c7569f5318f77dc55897e6d71a5324c66ff4886cd047dbeef5a2365750f4182","schema_version":"1.0","event_id":"sha256:4c7569f5318f77dc55897e6d71a5324c66ff4886cd047dbeef5a2365750f4182"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OBMJYVVX3Q67I2JJMTD64FKTYB/bundle.json","state_url":"https://pith.science/pith/OBMJYVVX3Q67I2JJMTD64FKTYB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OBMJYVVX3Q67I2JJMTD64FKTYB/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":"2026-06-08T10:18:45Z","links":{"resolver":"https://pith.science/pith/OBMJYVVX3Q67I2JJMTD64FKTYB","bundle":"https://pith.science/pith/OBMJYVVX3Q67I2JJMTD64FKTYB/bundle.json","state":"https://pith.science/pith/OBMJYVVX3Q67I2JJMTD64FKTYB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OBMJYVVX3Q67I2JJMTD64FKTYB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OBMJYVVX3Q67I2JJMTD64FKTYB","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":"af987786de35740f684e5361d9a6364a55df0a160a518c00eb0cd80ac8174555","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T12:11:51Z","title_canon_sha256":"ff50778514bf5b25909d479b127260b39ff7b3a3c2c6f69c21823bebe7b201c2"},"schema_version":"1.0","source":{"id":"1605.09593","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.09593","created_at":"2026-05-18T00:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"1605.09593v2","created_at":"2026-05-18T00:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09593","created_at":"2026-05-18T00:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"OBMJYVVX3Q67","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OBMJYVVX3Q67I2JJ","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OBMJYVVX","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:4c7569f5318f77dc55897e6d71a5324c66ff4886cd047dbeef5a2365750f4182","target":"graph","created_at":"2026-05-18T00:34:10Z","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":"Adaptive learning rate algorithms such as RMSProp are widely used for training deep neural networks. RMSProp offers efficient training since it uses first order gradients to approximate Hessian-based preconditioning. However, since the first order gradients include noise caused by stochastic optimization, the approximation may be inaccurate. In this paper, we propose a novel adaptive learning rate algorithm called SDProp. Its key idea is effective handling of the noise by preconditioning based on covariance matrix. For various neural networks, our approach is more efficient and effective than ","authors_text":"Sotetsu Iwamura, Yasuhiro Fujiwara, Yasutoshi Ida","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T12:11:51Z","title":"Adaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09593","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:f3aaf2dbfc4cb3092ece9d720b749b7ff3ba64aad7e98fed11927cf7640137ed","target":"record","created_at":"2026-05-18T00:34:10Z","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":"af987786de35740f684e5361d9a6364a55df0a160a518c00eb0cd80ac8174555","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T12:11:51Z","title_canon_sha256":"ff50778514bf5b25909d479b127260b39ff7b3a3c2c6f69c21823bebe7b201c2"},"schema_version":"1.0","source":{"id":"1605.09593","kind":"arxiv","version":2}},"canonical_sha256":"70589c56b7dc3df4692964c7ee1553c0414d59bc9975053a282252c2560528c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70589c56b7dc3df4692964c7ee1553c0414d59bc9975053a282252c2560528c2","first_computed_at":"2026-05-18T00:34:10.418775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:10.418775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i0WnFEryIcnZ4Jl8pkRnIuIs5b2o7OSbG5idZvjPh92ZDzyB3btYfAAqR6jTeusFDeYhOAIsm4gWpquZUZajCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:10.419530Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.09593","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3aaf2dbfc4cb3092ece9d720b749b7ff3ba64aad7e98fed11927cf7640137ed","sha256:4c7569f5318f77dc55897e6d71a5324c66ff4886cd047dbeef5a2365750f4182"],"state_sha256":"0eb8c7021beffeb1ab90e7519d4372829154b0f51d650b7da9d773ce59947737"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIe2wpbvlDBgRVLGZ1yEGWf8KNbFrShx/kcTdgfr9x/o0dssEmBy/oRwFLb87of+xpzpnOGTbI+uCQZFpHJ6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T10:18:45.448786Z","bundle_sha256":"0ab7d64cd12f432d8996954487f2b531ca9a4a9512590f0817bd32f19a4e2932"}}