{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CMFQ6UBXLS4KCZYCZOC4ALQU46","short_pith_number":"pith:CMFQ6UBX","canonical_record":{"source":{"id":"2208.06677","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-13T16:04:39Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"bacf8eefa35b6d80fc84b172cf3cfdceeb6d3e4f1da15bad82f29427151bf795","abstract_canon_sha256":"fa1eec7a19a75346b3a671caeed12b838e6c8bbc78d072488c82fb52726441f8"},"schema_version":"1.0"},"canonical_sha256":"130b0f50375cb8a16702cb85c02e14e78655ac29270c367064f3781007392fcd","source":{"kind":"arxiv","id":"2208.06677","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06677","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06677v5","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06677","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"pith_short_12","alias_value":"CMFQ6UBXLS4K","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"pith_short_16","alias_value":"CMFQ6UBXLS4KCZYC","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"pith_short_8","alias_value":"CMFQ6UBX","created_at":"2026-07-05T09:41:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CMFQ6UBXLS4KCZYCZOC4ALQU46","target":"record","payload":{"canonical_record":{"source":{"id":"2208.06677","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-13T16:04:39Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"bacf8eefa35b6d80fc84b172cf3cfdceeb6d3e4f1da15bad82f29427151bf795","abstract_canon_sha256":"fa1eec7a19a75346b3a671caeed12b838e6c8bbc78d072488c82fb52726441f8"},"schema_version":"1.0"},"canonical_sha256":"130b0f50375cb8a16702cb85c02e14e78655ac29270c367064f3781007392fcd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:26.246369Z","signature_b64":"LRwCYO/HVuorUZ4KlIFP0vJcY01J3pEE5v52gMKwqJmWdiewUFuFsszGWU4ABWyW1LdUG6NJwRW91ghemeqfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"130b0f50375cb8a16702cb85c02e14e78655ac29270c367064f3781007392fcd","last_reissued_at":"2026-07-05T09:41:26.245810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:26.245810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.06677","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:41:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KP6MPjnx0fe9C1dq+S52Rjrfin2L83YxmsH63IOfZsK2tv0TNKJ9jliMss1Z40ByL6DNiq4Vk+D4KvprAMvVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:12:04.284370Z"},"content_sha256":"5e443ef649d15f9c37c781ef2f6ac2118fa0dc1b0beea3546e8fd4f4c1b6f579","schema_version":"1.0","event_id":"sha256:5e443ef649d15f9c37c781ef2f6ac2118fa0dc1b0beea3546e8fd4f4c1b6f579"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CMFQ6UBXLS4KCZYCZOC4ALQU46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Huan Li, Pan Zhou, Shuicheng Yan, Xingyu Xie, Zhouchen Lin","submitted_at":"2022-08-13T16:04:39Z","abstract_excerpt":"In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To relieve this issue and consistently improve the model training speed across deep networks, we propose the ADAptive Nesterov momentum algorithm, Adan for short. Adan first reformulates the vanilla Nesterov acceleration to develop a new Nesterov momentum estimation (NME) method, which avoids the extra overhead of computing gradient at the extrapolation point. Then, Adan adopts NME to estimate the gradient's first- and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06677","kind":"arxiv","version":5},"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/2208.06677/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":"2026-07-05T09:41:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A8c7U0sJtWJE6xw0xk/nEWpGwpWOB2iH72wKAgv37Tgf3mcwZrk3dLFdWOV6JjhT1czIEkIDpgu5AUHshEEuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:12:04.284898Z"},"content_sha256":"78f2b8763a030c8a77cb0016dfd0c724f5dc23b72f64633334861917bcb7e654","schema_version":"1.0","event_id":"sha256:78f2b8763a030c8a77cb0016dfd0c724f5dc23b72f64633334861917bcb7e654"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMFQ6UBXLS4KCZYCZOC4ALQU46/bundle.json","state_url":"https://pith.science/pith/CMFQ6UBXLS4KCZYCZOC4ALQU46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMFQ6UBXLS4KCZYCZOC4ALQU46/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":"2026-08-08T12:12:04Z","links":{"resolver":"https://pith.science/pith/CMFQ6UBXLS4KCZYCZOC4ALQU46","bundle":"https://pith.science/pith/CMFQ6UBXLS4KCZYCZOC4ALQU46/bundle.json","state":"https://pith.science/pith/CMFQ6UBXLS4KCZYCZOC4ALQU46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMFQ6UBXLS4KCZYCZOC4ALQU46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CMFQ6UBXLS4KCZYCZOC4ALQU46","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":"fa1eec7a19a75346b3a671caeed12b838e6c8bbc78d072488c82fb52726441f8","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-13T16:04:39Z","title_canon_sha256":"bacf8eefa35b6d80fc84b172cf3cfdceeb6d3e4f1da15bad82f29427151bf795"},"schema_version":"1.0","source":{"id":"2208.06677","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06677","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06677v5","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06677","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"pith_short_12","alias_value":"CMFQ6UBXLS4K","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"pith_short_16","alias_value":"CMFQ6UBXLS4KCZYC","created_at":"2026-07-05T09:41:26Z"},{"alias_kind":"pith_short_8","alias_value":"CMFQ6UBX","created_at":"2026-07-05T09:41:26Z"}],"graph_snapshots":[{"event_id":"sha256:78f2b8763a030c8a77cb0016dfd0c724f5dc23b72f64633334861917bcb7e654","target":"graph","created_at":"2026-07-05T09:41:26Z","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/2208.06677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To relieve this issue and consistently improve the model training speed across deep networks, we propose the ADAptive Nesterov momentum algorithm, Adan for short. Adan first reformulates the vanilla Nesterov acceleration to develop a new Nesterov momentum estimation (NME) method, which avoids the extra overhead of computing gradient at the extrapolation point. Then, Adan adopts NME to estimate the gradient's first- and s","authors_text":"Huan Li, Pan Zhou, Shuicheng Yan, Xingyu Xie, Zhouchen Lin","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-13T16:04:39Z","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06677","kind":"arxiv","version":5},"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":"sha256:5e443ef649d15f9c37c781ef2f6ac2118fa0dc1b0beea3546e8fd4f4c1b6f579","target":"record","created_at":"2026-07-05T09:41:26Z","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":"fa1eec7a19a75346b3a671caeed12b838e6c8bbc78d072488c82fb52726441f8","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-13T16:04:39Z","title_canon_sha256":"bacf8eefa35b6d80fc84b172cf3cfdceeb6d3e4f1da15bad82f29427151bf795"},"schema_version":"1.0","source":{"id":"2208.06677","kind":"arxiv","version":5}},"canonical_sha256":"130b0f50375cb8a16702cb85c02e14e78655ac29270c367064f3781007392fcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"130b0f50375cb8a16702cb85c02e14e78655ac29270c367064f3781007392fcd","first_computed_at":"2026-07-05T09:41:26.245810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:26.245810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LRwCYO/HVuorUZ4KlIFP0vJcY01J3pEE5v52gMKwqJmWdiewUFuFsszGWU4ABWyW1LdUG6NJwRW91ghemeqfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:26.246369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.06677","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e443ef649d15f9c37c781ef2f6ac2118fa0dc1b0beea3546e8fd4f4c1b6f579","sha256:78f2b8763a030c8a77cb0016dfd0c724f5dc23b72f64633334861917bcb7e654"],"state_sha256":"0460ad92b1bf0b95593363ab35d1d1970239524b7c58240d121308c356e5d7d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXf4U7eInslWFf+njWeoj/ocxrkqh06Q8X5/8kvScMDwHzeeDxeOD6ZSi8Uucm5jY/r0EG+y6jup9ExlYQUDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:12:04.288902Z","bundle_sha256":"b7e9445dab50b2f8118d381323321d9c658aa07ec18bd9333fd51f0f6132a9c3"}}