{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6WVR2CNP4X6LZGCDGHGNPTIB2P","short_pith_number":"pith:6WVR2CNP","canonical_record":{"source":{"id":"2011.11152","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-23T00:39:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e38541b108503d67b98b4fc295fa982ab20ffe363f4abbf5bf8ebeab341dcf28","abstract_canon_sha256":"5ace4735c9ab3b304e6cb0df32ea9eae8d1772f55cf65cd411c9395b15d8c16f"},"schema_version":"1.0"},"canonical_sha256":"f5ab1d09afe5fcbc984331ccd7cd01d3e329c517d43d08d04df80b1aecd5a2bb","source":{"kind":"arxiv","id":"2011.11152","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.11152","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"arxiv_version","alias_value":"2011.11152v6","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11152","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"pith_short_12","alias_value":"6WVR2CNP4X6L","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"pith_short_16","alias_value":"6WVR2CNP4X6LZGCD","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"pith_short_8","alias_value":"6WVR2CNP","created_at":"2026-07-05T08:56:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6WVR2CNP4X6LZGCDGHGNPTIB2P","target":"record","payload":{"canonical_record":{"source":{"id":"2011.11152","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-23T00:39:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e38541b108503d67b98b4fc295fa982ab20ffe363f4abbf5bf8ebeab341dcf28","abstract_canon_sha256":"5ace4735c9ab3b304e6cb0df32ea9eae8d1772f55cf65cd411c9395b15d8c16f"},"schema_version":"1.0"},"canonical_sha256":"f5ab1d09afe5fcbc984331ccd7cd01d3e329c517d43d08d04df80b1aecd5a2bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:01.203114Z","signature_b64":"tvqpJn1e5YfDgLvIf+Uznq8rWGJsjLW+fNwo6XWa9fpOmtsVOex/G63H/VnpxEBxukiii4NNP4nOCviEyHfQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5ab1d09afe5fcbc984331ccd7cd01d3e329c517d43d08d04df80b1aecd5a2bb","last_reissued_at":"2026-07-05T08:56:01.202686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:01.202686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.11152","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yRZ7sz6ZNakzPzAA59XM7RF9JXpXybveQTpfrvReE9/XqoTn014YCEkfajnX4CPfJxilfMKXp51dRobj883PAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:07:30.246402Z"},"content_sha256":"4a0cd52aed47414793ffa49050ad54e33d2a954dc8d21e526b0b8add5f6e3322","schema_version":"1.0","event_id":"sha256:4a0cd52aed47414793ffa49050ad54e33d2a954dc8d21e526b0b8add5f6e3322"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6WVR2CNP4X6LZGCDGHGNPTIB2P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Issei Sato, Jingzhao Zhang, Masashi Sugiyama, Zeke Xie, Zhiqiang Xu","submitted_at":"2020-11-23T00:39:49Z","abstract_excerpt":"Weight decay is a simple yet powerful regularization technique that has been very widely used in training of deep neural networks (DNNs). While weight decay has attracted much attention, previous studies fail to discover some overlooked pitfalls on large gradient norms resulted by weight decay. In this paper, we discover that, weight decay can unfortunately lead to large gradient norms at the final phase (or the terminated solution) of training, which often indicates bad convergence and poor generalization. To mitigate the gradient-norm-centered pitfalls, we present the first practical schedul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11152","kind":"arxiv","version":6},"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/2011.11152/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":"2026-07-05T08:56:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pptIwXGi/9jrE8zQHVpJ0D1TJkgjvEREEbrtIn1QBNHP106fPYVGY++CrtkahXeFVm8M9ow3vnDG4DvgkjExDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:07:30.246788Z"},"content_sha256":"0ca07eb34a3f1c1d3372ce57b24a8fb3cd2a2daf50c9a072b8c3f8edc369acc6","schema_version":"1.0","event_id":"sha256:0ca07eb34a3f1c1d3372ce57b24a8fb3cd2a2daf50c9a072b8c3f8edc369acc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WVR2CNP4X6LZGCDGHGNPTIB2P/bundle.json","state_url":"https://pith.science/pith/6WVR2CNP4X6LZGCDGHGNPTIB2P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WVR2CNP4X6LZGCDGHGNPTIB2P/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":"2026-07-07T07:07:30Z","links":{"resolver":"https://pith.science/pith/6WVR2CNP4X6LZGCDGHGNPTIB2P","bundle":"https://pith.science/pith/6WVR2CNP4X6LZGCDGHGNPTIB2P/bundle.json","state":"https://pith.science/pith/6WVR2CNP4X6LZGCDGHGNPTIB2P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WVR2CNP4X6LZGCDGHGNPTIB2P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6WVR2CNP4X6LZGCDGHGNPTIB2P","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":"5ace4735c9ab3b304e6cb0df32ea9eae8d1772f55cf65cd411c9395b15d8c16f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-23T00:39:49Z","title_canon_sha256":"e38541b108503d67b98b4fc295fa982ab20ffe363f4abbf5bf8ebeab341dcf28"},"schema_version":"1.0","source":{"id":"2011.11152","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.11152","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"arxiv_version","alias_value":"2011.11152v6","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11152","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"pith_short_12","alias_value":"6WVR2CNP4X6L","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"pith_short_16","alias_value":"6WVR2CNP4X6LZGCD","created_at":"2026-07-05T08:56:01Z"},{"alias_kind":"pith_short_8","alias_value":"6WVR2CNP","created_at":"2026-07-05T08:56:01Z"}],"graph_snapshots":[{"event_id":"sha256:0ca07eb34a3f1c1d3372ce57b24a8fb3cd2a2daf50c9a072b8c3f8edc369acc6","target":"graph","created_at":"2026-07-05T08:56:01Z","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/2011.11152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Weight decay is a simple yet powerful regularization technique that has been very widely used in training of deep neural networks (DNNs). While weight decay has attracted much attention, previous studies fail to discover some overlooked pitfalls on large gradient norms resulted by weight decay. In this paper, we discover that, weight decay can unfortunately lead to large gradient norms at the final phase (or the terminated solution) of training, which often indicates bad convergence and poor generalization. To mitigate the gradient-norm-centered pitfalls, we present the first practical schedul","authors_text":"Issei Sato, Jingzhao Zhang, Masashi Sugiyama, Zeke Xie, Zhiqiang Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-23T00:39:49Z","title":"On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11152","kind":"arxiv","version":6},"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":"sha256:4a0cd52aed47414793ffa49050ad54e33d2a954dc8d21e526b0b8add5f6e3322","target":"record","created_at":"2026-07-05T08:56:01Z","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":"5ace4735c9ab3b304e6cb0df32ea9eae8d1772f55cf65cd411c9395b15d8c16f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-23T00:39:49Z","title_canon_sha256":"e38541b108503d67b98b4fc295fa982ab20ffe363f4abbf5bf8ebeab341dcf28"},"schema_version":"1.0","source":{"id":"2011.11152","kind":"arxiv","version":6}},"canonical_sha256":"f5ab1d09afe5fcbc984331ccd7cd01d3e329c517d43d08d04df80b1aecd5a2bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5ab1d09afe5fcbc984331ccd7cd01d3e329c517d43d08d04df80b1aecd5a2bb","first_computed_at":"2026-07-05T08:56:01.202686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:01.202686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvqpJn1e5YfDgLvIf+Uznq8rWGJsjLW+fNwo6XWa9fpOmtsVOex/G63H/VnpxEBxukiii4NNP4nOCviEyHfQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:01.203114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.11152","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a0cd52aed47414793ffa49050ad54e33d2a954dc8d21e526b0b8add5f6e3322","sha256:0ca07eb34a3f1c1d3372ce57b24a8fb3cd2a2daf50c9a072b8c3f8edc369acc6"],"state_sha256":"6ccb7b127f2326bad9f80b77f120ef20f3361ee8242c3529e4450093c3501924"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"36ZJxIz30JDc7bywsM0eL6tfuhVlzJgKSYmdVcDTDzQlh59+7+I4OERhBTwtaTN0xVXJVCLk4k9Qhpr7nW5XDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:07:30.248833Z","bundle_sha256":"d1dbfdddf6466408fd13b4f5bc3d373a1c7de9e802de52656db9ad26f13c8e9a"}}