{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JILYEZXIPICUBHNOJIVB6FWO2R","short_pith_number":"pith:JILYEZXI","canonical_record":{"source":{"id":"1908.06395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-18T08:12:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d221069dfc0de2d3cce2a47f80ff3ec5695f8105e343d0a32ab1bdcde52dc268","abstract_canon_sha256":"cc2711bef9b3902d74f23bfe38189690e185f35f456b861bca39eec44d7a4f3a"},"schema_version":"1.0"},"canonical_sha256":"4a178266e87a05409dae4a2a1f16ced44bfb42f79a368701b64131308ee07861","source":{"kind":"arxiv","id":"1908.06395","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.06395","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"arxiv_version","alias_value":"1908.06395v1","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06395","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"pith_short_12","alias_value":"JILYEZXIPICU","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"pith_short_16","alias_value":"JILYEZXIPICUBHNO","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"pith_short_8","alias_value":"JILYEZXI","created_at":"2026-07-04T23:58:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JILYEZXIPICUBHNOJIVB6FWO2R","target":"record","payload":{"canonical_record":{"source":{"id":"1908.06395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-18T08:12:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d221069dfc0de2d3cce2a47f80ff3ec5695f8105e343d0a32ab1bdcde52dc268","abstract_canon_sha256":"cc2711bef9b3902d74f23bfe38189690e185f35f456b861bca39eec44d7a4f3a"},"schema_version":"1.0"},"canonical_sha256":"4a178266e87a05409dae4a2a1f16ced44bfb42f79a368701b64131308ee07861","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:15.312297Z","signature_b64":"36UZWaAM+jK3GyP2PS8Suc8ig22ajnhKWpmjDDJUuj5IFC8Q7uuBUrNNqgZ27KRQn3FyRnIlMfSLjM/xZPaHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a178266e87a05409dae4a2a1f16ced44bfb42f79a368701b64131308ee07861","last_reissued_at":"2026-07-04T23:58:15.311959Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:15.311959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.06395","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":"2026-07-04T23:58:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6uTpO0znSnQdn4uXEcs08WxAvXpKbIcCRk+p82wymupbM4QTW6n4hMTysk4sKzC/dSwVbSqP1Gh/u/bgbaWeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:42:42.113709Z"},"content_sha256":"da1a152990e1667937028da3b3ec833a9b55032e90e637d5b18e43dce0e8c9d6","schema_version":"1.0","event_id":"sha256:da1a152990e1667937028da3b3ec833a9b55032e90e637d5b18e43dce0e8c9d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JILYEZXIPICUBHNOJIVB6FWO2R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Better Generalization: BP-SVRG in Training Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dachao Lin, Hao Jin, Zhihua Zhang","submitted_at":"2019-08-18T08:12:03Z","abstract_excerpt":"Stochastic variance-reduced gradient (SVRG) is a classical optimization method. Although it is theoretically proved to have better convergence performance than stochastic gradient descent (SGD), the generalization performance of SVRG remains open. In this paper we investigate the effects of some training techniques, mini-batching and learning rate decay, on the generalization performance of SVRG, and verify the generalization performance of Batch-SVRG (B-SVRG). In terms of the relationship between optimization and generalization, we believe that the average norm of gradients on each training s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06395","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.06395/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":"2026-07-04T23:58:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eM5P+SpG0vRexvjMcbBmf5/H1W62wyrGNDgN6uyIx/HAIcHyE0HeYlng9Ni1EkWFhjriQxc5K4w3aLfBWMSGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:42:42.115692Z"},"content_sha256":"0dda8536f4d71341fd125bc9f772f6b6487b4ebf258cad858e1e7285661a0c5e","schema_version":"1.0","event_id":"sha256:0dda8536f4d71341fd125bc9f772f6b6487b4ebf258cad858e1e7285661a0c5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JILYEZXIPICUBHNOJIVB6FWO2R/bundle.json","state_url":"https://pith.science/pith/JILYEZXIPICUBHNOJIVB6FWO2R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JILYEZXIPICUBHNOJIVB6FWO2R/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":"2026-08-16T07:42:42Z","links":{"resolver":"https://pith.science/pith/JILYEZXIPICUBHNOJIVB6FWO2R","bundle":"https://pith.science/pith/JILYEZXIPICUBHNOJIVB6FWO2R/bundle.json","state":"https://pith.science/pith/JILYEZXIPICUBHNOJIVB6FWO2R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JILYEZXIPICUBHNOJIVB6FWO2R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JILYEZXIPICUBHNOJIVB6FWO2R","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":"cc2711bef9b3902d74f23bfe38189690e185f35f456b861bca39eec44d7a4f3a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-18T08:12:03Z","title_canon_sha256":"d221069dfc0de2d3cce2a47f80ff3ec5695f8105e343d0a32ab1bdcde52dc268"},"schema_version":"1.0","source":{"id":"1908.06395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.06395","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"arxiv_version","alias_value":"1908.06395v1","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06395","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"pith_short_12","alias_value":"JILYEZXIPICU","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"pith_short_16","alias_value":"JILYEZXIPICUBHNO","created_at":"2026-07-04T23:58:15Z"},{"alias_kind":"pith_short_8","alias_value":"JILYEZXI","created_at":"2026-07-04T23:58:15Z"}],"graph_snapshots":[{"event_id":"sha256:0dda8536f4d71341fd125bc9f772f6b6487b4ebf258cad858e1e7285661a0c5e","target":"graph","created_at":"2026-07-04T23:58:15Z","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/1908.06395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic variance-reduced gradient (SVRG) is a classical optimization method. Although it is theoretically proved to have better convergence performance than stochastic gradient descent (SGD), the generalization performance of SVRG remains open. In this paper we investigate the effects of some training techniques, mini-batching and learning rate decay, on the generalization performance of SVRG, and verify the generalization performance of Batch-SVRG (B-SVRG). In terms of the relationship between optimization and generalization, we believe that the average norm of gradients on each training s","authors_text":"Dachao Lin, Hao Jin, Zhihua Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-18T08:12:03Z","title":"Towards Better Generalization: BP-SVRG in Training Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06395","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:da1a152990e1667937028da3b3ec833a9b55032e90e637d5b18e43dce0e8c9d6","target":"record","created_at":"2026-07-04T23:58:15Z","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":"cc2711bef9b3902d74f23bfe38189690e185f35f456b861bca39eec44d7a4f3a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-18T08:12:03Z","title_canon_sha256":"d221069dfc0de2d3cce2a47f80ff3ec5695f8105e343d0a32ab1bdcde52dc268"},"schema_version":"1.0","source":{"id":"1908.06395","kind":"arxiv","version":1}},"canonical_sha256":"4a178266e87a05409dae4a2a1f16ced44bfb42f79a368701b64131308ee07861","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a178266e87a05409dae4a2a1f16ced44bfb42f79a368701b64131308ee07861","first_computed_at":"2026-07-04T23:58:15.311959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:58:15.311959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"36UZWaAM+jK3GyP2PS8Suc8ig22ajnhKWpmjDDJUuj5IFC8Q7uuBUrNNqgZ27KRQn3FyRnIlMfSLjM/xZPaHBA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:58:15.312297Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.06395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da1a152990e1667937028da3b3ec833a9b55032e90e637d5b18e43dce0e8c9d6","sha256:0dda8536f4d71341fd125bc9f772f6b6487b4ebf258cad858e1e7285661a0c5e"],"state_sha256":"feb3eabe95e389efcc15b244a163f98c630d79a821fe43df92a231b132df56c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m4c8gCkaFdOt3r8G3d6GG206YXyTmux0QtESgI0q/gXgjBCu+f1FcZHZJef3Zicra2Gt414QojGD3/5A7VFrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:42:42.125568Z","bundle_sha256":"1b23f0de3080743ec770db14c83610b9dae1f474eb7559c2b69315ddf42df061"}}