{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:BTYRUS7BUF4OXJFVR45RYUSNXQ","short_pith_number":"pith:BTYRUS7B","canonical_record":{"source":{"id":"1506.02690","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T20:42:12Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"82c082b730564f77392e525c0b8165708fefc5af314d0a5109197c72ae7b0f01","abstract_canon_sha256":"730db6efececb469c505a701867f592f72c5c4545a8da7b13eb1b3c0a817c144"},"schema_version":"1.0"},"canonical_sha256":"0cf11a4be1a178eba4b58f3b1c524dbc0af5936183d61b060a5ae6610dbcea69","source":{"kind":"arxiv","id":"1506.02690","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02690","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02690v3","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02690","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"pith_short_12","alias_value":"BTYRUS7BUF4O","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BTYRUS7BUF4OXJFV","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BTYRUS7B","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:BTYRUS7BUF4OXJFVR45RYUSNXQ","target":"record","payload":{"canonical_record":{"source":{"id":"1506.02690","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T20:42:12Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"82c082b730564f77392e525c0b8165708fefc5af314d0a5109197c72ae7b0f01","abstract_canon_sha256":"730db6efececb469c505a701867f592f72c5c4545a8da7b13eb1b3c0a817c144"},"schema_version":"1.0"},"canonical_sha256":"0cf11a4be1a178eba4b58f3b1c524dbc0af5936183d61b060a5ae6610dbcea69","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:40.575578Z","signature_b64":"DV8GIIFF2xgUtdUEdZUdz5rK8bB8g2GMB3PA+FwY2rkQkTmvyv9RBXNTWczzjNdK+XgNBWGMxB3uYEx6iBkmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cf11a4be1a178eba4b58f3b1c524dbc0af5936183d61b060a5ae6610dbcea69","last_reissued_at":"2026-05-18T01:12:40.575173Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:40.575173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.02690","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":"2026-05-18T01:12:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmloWbHykQanNv4BQXiiSSQGLmgmOng5hs/LCYP3kL+l2n2qQvt2Ipe7thUIkMuqIplKFVsWSLVxFLMgFQyrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:20:16.311028Z"},"content_sha256":"f358c1851f3eae6357a4ff8dfea8430d700bd4645b6ad977ad70c4765f2c39ec","schema_version":"1.0","event_id":"sha256:f358c1851f3eae6357a4ff8dfea8430d700bd4645b6ad977ad70c4765f2c39ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:BTYRUS7BUF4OXJFVR45RYUSNXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Normalized Risk-Averting Training For Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"James Lo, Tim Oates, Zhiguang Wang","submitted_at":"2015-06-08T20:42:12Z","abstract_excerpt":"This paper proposes a set of new error criteria and learning approaches, Adaptive Normalized Risk-Averting Training (ANRAT), to attack the non-convex optimization problem in training deep neural networks (DNNs). Theoretically, we demonstrate its effectiveness on global and local convexity lower-bounded by the standard $L_p$-norm error. By analyzing the gradient on the convexity index $\\lambda$, we explain the reason why to learn $\\lambda$ adaptively using gradient descent works. In practice, we show how this method improves training of deep neural networks to solve visual recognition tasks on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02690","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":"2026-05-18T01:12:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tDaNdPL6nIKEc2dixJIyQqIedBneQTweWTGzyKwHPS0RXgILS/l0/DjWkqemd5erCINr5m9oDoruO20MJ9a5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:20:16.311750Z"},"content_sha256":"fa9b2dd1dc2667afff333153d051279f7452332e3085117099c0749fa16418f7","schema_version":"1.0","event_id":"sha256:fa9b2dd1dc2667afff333153d051279f7452332e3085117099c0749fa16418f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BTYRUS7BUF4OXJFVR45RYUSNXQ/bundle.json","state_url":"https://pith.science/pith/BTYRUS7BUF4OXJFVR45RYUSNXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BTYRUS7BUF4OXJFVR45RYUSNXQ/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":"2026-06-11T22:20:16Z","links":{"resolver":"https://pith.science/pith/BTYRUS7BUF4OXJFVR45RYUSNXQ","bundle":"https://pith.science/pith/BTYRUS7BUF4OXJFVR45RYUSNXQ/bundle.json","state":"https://pith.science/pith/BTYRUS7BUF4OXJFVR45RYUSNXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BTYRUS7BUF4OXJFVR45RYUSNXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:BTYRUS7BUF4OXJFVR45RYUSNXQ","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":"730db6efececb469c505a701867f592f72c5c4545a8da7b13eb1b3c0a817c144","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T20:42:12Z","title_canon_sha256":"82c082b730564f77392e525c0b8165708fefc5af314d0a5109197c72ae7b0f01"},"schema_version":"1.0","source":{"id":"1506.02690","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02690","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02690v3","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02690","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"pith_short_12","alias_value":"BTYRUS7BUF4O","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BTYRUS7BUF4OXJFV","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BTYRUS7B","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:fa9b2dd1dc2667afff333153d051279f7452332e3085117099c0749fa16418f7","target":"graph","created_at":"2026-05-18T01:12:40Z","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":"This paper proposes a set of new error criteria and learning approaches, Adaptive Normalized Risk-Averting Training (ANRAT), to attack the non-convex optimization problem in training deep neural networks (DNNs). Theoretically, we demonstrate its effectiveness on global and local convexity lower-bounded by the standard $L_p$-norm error. By analyzing the gradient on the convexity index $\\lambda$, we explain the reason why to learn $\\lambda$ adaptively using gradient descent works. In practice, we show how this method improves training of deep neural networks to solve visual recognition tasks on ","authors_text":"James Lo, Tim Oates, Zhiguang Wang","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T20:42:12Z","title":"Adaptive Normalized Risk-Averting Training For Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02690","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:f358c1851f3eae6357a4ff8dfea8430d700bd4645b6ad977ad70c4765f2c39ec","target":"record","created_at":"2026-05-18T01:12:40Z","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":"730db6efececb469c505a701867f592f72c5c4545a8da7b13eb1b3c0a817c144","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T20:42:12Z","title_canon_sha256":"82c082b730564f77392e525c0b8165708fefc5af314d0a5109197c72ae7b0f01"},"schema_version":"1.0","source":{"id":"1506.02690","kind":"arxiv","version":3}},"canonical_sha256":"0cf11a4be1a178eba4b58f3b1c524dbc0af5936183d61b060a5ae6610dbcea69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cf11a4be1a178eba4b58f3b1c524dbc0af5936183d61b060a5ae6610dbcea69","first_computed_at":"2026-05-18T01:12:40.575173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:40.575173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DV8GIIFF2xgUtdUEdZUdz5rK8bB8g2GMB3PA+FwY2rkQkTmvyv9RBXNTWczzjNdK+XgNBWGMxB3uYEx6iBkmAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:40.575578Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.02690","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f358c1851f3eae6357a4ff8dfea8430d700bd4645b6ad977ad70c4765f2c39ec","sha256:fa9b2dd1dc2667afff333153d051279f7452332e3085117099c0749fa16418f7"],"state_sha256":"896ca08cabe2a4c5945bc4559f38e12bd6157443f4a86abb4f9d988148767742"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/VYFreQHM7Sd/izol193iqPnvy8gdWtMWzsIhBmy1dtvRQnU9LZKkklztstVwkxieQfItlLDoACA4JZv02mSCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T22:20:16.315712Z","bundle_sha256":"285c3a83c387077d7e1331e653e2d4c6eb6761a3674f5e14f0f99ccb86d67816"}}