{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FPF2CDRSZJAY64TPHSC7XJU6IQ","short_pith_number":"pith:FPF2CDRS","canonical_record":{"source":{"id":"1908.01878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T21:56:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1b6dfff18c34737b8fdbb6de1796a93b201cd1ed520930b0aac55819ae03ff9f","abstract_canon_sha256":"9cd16416e30938bf8cd9ba3c90f65429bea29737199c4fa033e21a61c3b0e52a"},"schema_version":"1.0"},"canonical_sha256":"2bcba10e32ca418f726f3c85fba69e441fdcdbafc9d0e901de3aeb05d96663b1","source":{"kind":"arxiv","id":"1908.01878","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01878","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01878v2","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01878","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"FPF2CDRSZJAY","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"FPF2CDRSZJAY64TP","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"FPF2CDRS","created_at":"2026-07-05T00:07:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FPF2CDRSZJAY64TPHSC7XJU6IQ","target":"record","payload":{"canonical_record":{"source":{"id":"1908.01878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T21:56:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1b6dfff18c34737b8fdbb6de1796a93b201cd1ed520930b0aac55819ae03ff9f","abstract_canon_sha256":"9cd16416e30938bf8cd9ba3c90f65429bea29737199c4fa033e21a61c3b0e52a"},"schema_version":"1.0"},"canonical_sha256":"2bcba10e32ca418f726f3c85fba69e441fdcdbafc9d0e901de3aeb05d96663b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:24.394384Z","signature_b64":"RF8kzA+5a7iVPufReeJrGa4TSanA745/nuXa0v88cxcuK5KJYw+XJUBAmz39QZgXlNy5OoT7MVK9s3aHYgfhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bcba10e32ca418f726f3c85fba69e441fdcdbafc9d0e901de3aeb05d96663b1","last_reissued_at":"2026-07-05T00:07:24.393855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:24.393855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.01878","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":"2026-07-05T00:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uPTcDb0JzZJ51rcz++ro/OTL/E57MBJi+m31NHEYyQs7ZVPPs1ARrrrq/zL5TI/DzYnIHq/l/pF9OAyUg9RECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:16:53.810481Z"},"content_sha256":"ce1df78e2233e975588c3b47824ccd5b0bdd048f87cc3a870743b242e2343165","schema_version":"1.0","event_id":"sha256:ce1df78e2233e975588c3b47824ccd5b0bdd048f87cc3a870743b242e2343165"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FPF2CDRSZJAY64TPHSC7XJU6IQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Does Learning Rate Decay Help Modern Neural Networks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Kaichao You, Michael I. Jordan, Mingsheng Long","submitted_at":"2019-08-05T21:56:41Z","abstract_excerpt":"Learning rate decay (lrDecay) is a \\emph{de facto} technique for training modern neural networks. It starts with a large learning rate and then decays it multiple times. It is empirically observed to help both optimization and generalization. Common beliefs in how lrDecay works come from the optimization analysis of (Stochastic) Gradient Descent: 1) an initially large learning rate accelerates training or helps the network escape spurious local minima; 2) decaying the learning rate helps the network converge to a local minimum and avoid oscillation. Despite the popularity of these common belie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01878","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.01878/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sRFoDvfOLazEQKIDXVhNA8pvwe/yyyb085+VJKNDVWZBlC4CuYJYSZijb3/OfjGF/JmimS2YZKusAnv4eZsbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:16:53.811458Z"},"content_sha256":"16a7cef5e2a4b1c8c559fba96ad15fe5f980a9a32f33025902a9f49968d67e7b","schema_version":"1.0","event_id":"sha256:16a7cef5e2a4b1c8c559fba96ad15fe5f980a9a32f33025902a9f49968d67e7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPF2CDRSZJAY64TPHSC7XJU6IQ/bundle.json","state_url":"https://pith.science/pith/FPF2CDRSZJAY64TPHSC7XJU6IQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPF2CDRSZJAY64TPHSC7XJU6IQ/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":"2026-08-04T20:16:53Z","links":{"resolver":"https://pith.science/pith/FPF2CDRSZJAY64TPHSC7XJU6IQ","bundle":"https://pith.science/pith/FPF2CDRSZJAY64TPHSC7XJU6IQ/bundle.json","state":"https://pith.science/pith/FPF2CDRSZJAY64TPHSC7XJU6IQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPF2CDRSZJAY64TPHSC7XJU6IQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FPF2CDRSZJAY64TPHSC7XJU6IQ","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":"9cd16416e30938bf8cd9ba3c90f65429bea29737199c4fa033e21a61c3b0e52a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T21:56:41Z","title_canon_sha256":"1b6dfff18c34737b8fdbb6de1796a93b201cd1ed520930b0aac55819ae03ff9f"},"schema_version":"1.0","source":{"id":"1908.01878","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01878","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01878v2","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01878","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"FPF2CDRSZJAY","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"FPF2CDRSZJAY64TP","created_at":"2026-07-05T00:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"FPF2CDRS","created_at":"2026-07-05T00:07:24Z"}],"graph_snapshots":[{"event_id":"sha256:16a7cef5e2a4b1c8c559fba96ad15fe5f980a9a32f33025902a9f49968d67e7b","target":"graph","created_at":"2026-07-05T00:07:24Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.01878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning rate decay (lrDecay) is a \\emph{de facto} technique for training modern neural networks. It starts with a large learning rate and then decays it multiple times. It is empirically observed to help both optimization and generalization. Common beliefs in how lrDecay works come from the optimization analysis of (Stochastic) Gradient Descent: 1) an initially large learning rate accelerates training or helps the network escape spurious local minima; 2) decaying the learning rate helps the network converge to a local minimum and avoid oscillation. Despite the popularity of these common belie","authors_text":"Jianmin Wang, Kaichao You, Michael I. Jordan, Mingsheng Long","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T21:56:41Z","title":"How Does Learning Rate Decay Help Modern Neural Networks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01878","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:ce1df78e2233e975588c3b47824ccd5b0bdd048f87cc3a870743b242e2343165","target":"record","created_at":"2026-07-05T00:07:24Z","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":"9cd16416e30938bf8cd9ba3c90f65429bea29737199c4fa033e21a61c3b0e52a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T21:56:41Z","title_canon_sha256":"1b6dfff18c34737b8fdbb6de1796a93b201cd1ed520930b0aac55819ae03ff9f"},"schema_version":"1.0","source":{"id":"1908.01878","kind":"arxiv","version":2}},"canonical_sha256":"2bcba10e32ca418f726f3c85fba69e441fdcdbafc9d0e901de3aeb05d96663b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bcba10e32ca418f726f3c85fba69e441fdcdbafc9d0e901de3aeb05d96663b1","first_computed_at":"2026-07-05T00:07:24.393855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:24.393855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RF8kzA+5a7iVPufReeJrGa4TSanA745/nuXa0v88cxcuK5KJYw+XJUBAmz39QZgXlNy5OoT7MVK9s3aHYgfhBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:24.394384Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01878","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce1df78e2233e975588c3b47824ccd5b0bdd048f87cc3a870743b242e2343165","sha256:16a7cef5e2a4b1c8c559fba96ad15fe5f980a9a32f33025902a9f49968d67e7b"],"state_sha256":"48f1adeed376aaa505d78a3ba8c90dd7698ceaeb7ec69dea570a6a1c5e03fb3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VX6uQsRvLuKP8IsJrquhk7VYZ34OYBjxeU1Ukv+S4onz0/BCSPCn0QFmo9N1wJbAxuLsXYMW2CGjK8Kj2w5VAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:16:53.855106Z","bundle_sha256":"a17aae5ae3e3d76ebcf2e4b1954569ac229c6a97d2c3980a14d503c992d4ddf4"}}