{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QNM3QZ7UR4YXN4RGQRJPQVMFZZ","short_pith_number":"pith:QNM3QZ7U","canonical_record":{"source":{"id":"2404.04454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T23:56:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"1b0039d8401c1c97c05881bc736c261a1ce3043120bc841bb3a64ce7e1ce1733","abstract_canon_sha256":"223ed2b813e89a340f8367c7f438be7a865c74e0b6f7573b3fd3cd2c3a4ae7c0"},"schema_version":"1.0"},"canonical_sha256":"8359b867f48f3176f2268452f85585ce5161b06d7e82f49a960a20a6b939ad56","source":{"kind":"arxiv","id":"2404.04454","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04454","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04454v1","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04454","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"QNM3QZ7UR4YX","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"QNM3QZ7UR4YXN4RG","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"QNM3QZ7U","created_at":"2026-07-05T08:05:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QNM3QZ7UR4YXN4RGQRJPQVMFZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T23:56:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"1b0039d8401c1c97c05881bc736c261a1ce3043120bc841bb3a64ce7e1ce1733","abstract_canon_sha256":"223ed2b813e89a340f8367c7f438be7a865c74e0b6f7573b3fd3cd2c3a4ae7c0"},"schema_version":"1.0"},"canonical_sha256":"8359b867f48f3176f2268452f85585ce5161b06d7e82f49a960a20a6b939ad56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:16.924673Z","signature_b64":"0045xsCCGDY44YGb42gMaWWcdiMbjvGO4y4YSyR+UHAsx4S89qW5pW7q9bfIlKNfiTUkMRbzdAJX8l9w4afyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8359b867f48f3176f2268452f85585ce5161b06d7e82f49a960a20a6b939ad56","last_reissued_at":"2026-07-05T08:05:16.924225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:16.924225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04454","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":"2026-07-05T08:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8XbLXFdBFpO5522Dk1quB5xVnya4utLVNyMSVO8cSPIxVd9RxMy8sJO99CUND5UM/DTaoFDtyFSy4FawqOZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:42:02.713172Z"},"content_sha256":"029846cdbd6cb597739fa07b0e71200f6b4727d24f7a36170e2031397e213098","schema_version":"1.0","event_id":"sha256:029846cdbd6cb597739fa07b0e71200f6b4727d24f7a36170e2031397e213098"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QNM3QZ7UR4YXN4RGQRJPQVMFZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Shuo Xie, Zhiyuan Li","submitted_at":"2024-04-05T23:56:50Z","abstract_excerpt":"Adam with decoupled weight decay, also known as AdamW, is widely acclaimed for its superior performance in language modeling tasks, surpassing Adam with $\\ell_2$ regularization in terms of generalization and optimization. However, this advantage is not theoretically well-understood. One challenge here is that though intuitively Adam with $\\ell_2$ regularization optimizes the $\\ell_2$ regularized loss, it is not clear if AdamW optimizes a specific objective. In this work, we make progress toward understanding the benefit of AdamW by showing that it implicitly performs constrained optimization. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04454","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/2404.04454/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":"2026-07-05T08:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gZ1zd1YCWOGGo6blfSi1+X46A7GVk6vjrqNlbktgoKSrftYbo0mLORkFx/tcQ/Tdp8EHa3u5MsuDptNVaZ96CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:42:02.713941Z"},"content_sha256":"dc4210806a617c40e176f275cdc959151c082ad635a1b62e32a5e066a859d785","schema_version":"1.0","event_id":"sha256:dc4210806a617c40e176f275cdc959151c082ad635a1b62e32a5e066a859d785"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNM3QZ7UR4YXN4RGQRJPQVMFZZ/bundle.json","state_url":"https://pith.science/pith/QNM3QZ7UR4YXN4RGQRJPQVMFZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNM3QZ7UR4YXN4RGQRJPQVMFZZ/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":"2026-08-18T13:42:02Z","links":{"resolver":"https://pith.science/pith/QNM3QZ7UR4YXN4RGQRJPQVMFZZ","bundle":"https://pith.science/pith/QNM3QZ7UR4YXN4RGQRJPQVMFZZ/bundle.json","state":"https://pith.science/pith/QNM3QZ7UR4YXN4RGQRJPQVMFZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNM3QZ7UR4YXN4RGQRJPQVMFZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QNM3QZ7UR4YXN4RGQRJPQVMFZZ","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":"223ed2b813e89a340f8367c7f438be7a865c74e0b6f7573b3fd3cd2c3a4ae7c0","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T23:56:50Z","title_canon_sha256":"1b0039d8401c1c97c05881bc736c261a1ce3043120bc841bb3a64ce7e1ce1733"},"schema_version":"1.0","source":{"id":"2404.04454","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04454","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04454v1","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04454","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"QNM3QZ7UR4YX","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"QNM3QZ7UR4YXN4RG","created_at":"2026-07-05T08:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"QNM3QZ7U","created_at":"2026-07-05T08:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:dc4210806a617c40e176f275cdc959151c082ad635a1b62e32a5e066a859d785","target":"graph","created_at":"2026-07-05T08:05:16Z","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/2404.04454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adam with decoupled weight decay, also known as AdamW, is widely acclaimed for its superior performance in language modeling tasks, surpassing Adam with $\\ell_2$ regularization in terms of generalization and optimization. However, this advantage is not theoretically well-understood. One challenge here is that though intuitively Adam with $\\ell_2$ regularization optimizes the $\\ell_2$ regularized loss, it is not clear if AdamW optimizes a specific objective. In this work, we make progress toward understanding the benefit of AdamW by showing that it implicitly performs constrained optimization. ","authors_text":"Shuo Xie, Zhiyuan Li","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T23:56:50Z","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04454","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":"sha256:029846cdbd6cb597739fa07b0e71200f6b4727d24f7a36170e2031397e213098","target":"record","created_at":"2026-07-05T08:05:16Z","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":"223ed2b813e89a340f8367c7f438be7a865c74e0b6f7573b3fd3cd2c3a4ae7c0","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T23:56:50Z","title_canon_sha256":"1b0039d8401c1c97c05881bc736c261a1ce3043120bc841bb3a64ce7e1ce1733"},"schema_version":"1.0","source":{"id":"2404.04454","kind":"arxiv","version":1}},"canonical_sha256":"8359b867f48f3176f2268452f85585ce5161b06d7e82f49a960a20a6b939ad56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8359b867f48f3176f2268452f85585ce5161b06d7e82f49a960a20a6b939ad56","first_computed_at":"2026-07-05T08:05:16.924225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:16.924225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0045xsCCGDY44YGb42gMaWWcdiMbjvGO4y4YSyR+UHAsx4S89qW5pW7q9bfIlKNfiTUkMRbzdAJX8l9w4afyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:16.924673Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04454","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:029846cdbd6cb597739fa07b0e71200f6b4727d24f7a36170e2031397e213098","sha256:dc4210806a617c40e176f275cdc959151c082ad635a1b62e32a5e066a859d785"],"state_sha256":"403b9775cffaf653e81eafb447327cda6309ff2913d6871b948d70a169a08751"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOLG9pC8XEx2AneeZyqDwiWEi0hU2bzzO1d3+NxyGspF7pUWen58mhzG5/7R2hJYckLQG1WNBYnxOMOFe9JaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T13:42:02.723429Z","bundle_sha256":"cd339e030406ca19bec2b8ec4488062c2c17d1f86abf8890b73e4075734b6950"}}