{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EI5WFVAH5DDNMDAQAYXZ46B27S","short_pith_number":"pith:EI5WFVAH","canonical_record":{"source":{"id":"2405.18199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:08:04Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"f4e5b61884999d59929078264d04b981ddb6449a8c40ecde2a7e6f1ebf634880","abstract_canon_sha256":"15f9f6f846e0ac9f64ae263c2cefb6b593e5944445b3afd9ce2c94376b2625e9"},"schema_version":"1.0"},"canonical_sha256":"223b62d407e8c6d60c10062f9e783afc9546f4405b71fac02297ceb4b26a1c95","source":{"kind":"arxiv","id":"2405.18199","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18199","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18199v2","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18199","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"EI5WFVAH5DDN","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"EI5WFVAH5DDNMDAQ","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"EI5WFVAH","created_at":"2026-07-05T09:28:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EI5WFVAH5DDNMDAQAYXZ46B27S","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:08:04Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"f4e5b61884999d59929078264d04b981ddb6449a8c40ecde2a7e6f1ebf634880","abstract_canon_sha256":"15f9f6f846e0ac9f64ae263c2cefb6b593e5944445b3afd9ce2c94376b2625e9"},"schema_version":"1.0"},"canonical_sha256":"223b62d407e8c6d60c10062f9e783afc9546f4405b71fac02297ceb4b26a1c95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:31.403978Z","signature_b64":"NrtW328HsJ1eEMz7l+KYuOXKL67+8HNtjsmx0Ql3RU9qLRf4d7mVx8eN9cmo0+0FvRJEJ4Yo/SCaH4CKtwnXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"223b62d407e8c6d60c10062f9e783afc9546f4405b71fac02297ceb4b26a1c95","last_reissued_at":"2026-07-05T09:28:31.403570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:31.403570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18199","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X5GfAiYyhvg+mjYq+yaaFJTH58BS7FwGArXCzJTp7BW+qPn+lEpYy7Sqff9YXIz/0728JEohl2h8M/U4nASFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:32:18.565072Z"},"content_sha256":"1e8c14f627bb58ede9d73e15be3f8a27ead35f3d012526ae85a75e0225febe28","schema_version":"1.0","event_id":"sha256:1e8c14f627bb58ede9d73e15be3f8a27ead35f3d012526ae85a75e0225febe28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EI5WFVAH5DDNMDAQAYXZ46B27S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adam with model exponential moving average is effective for nonconvex optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ashok Cutkosky, Kwangjun Ahn","submitted_at":"2024-05-28T14:08:04Z","abstract_excerpt":"In this work, we offer a theoretical analysis of two modern optimization techniques for training large and complex models: (i) adaptive optimization algorithms, such as Adam, and (ii) the model exponential moving average (EMA). Specifically, we demonstrate that a clipped version of Adam with model EMA achieves the optimal convergence rates in various nonconvex optimization settings, both smooth and nonsmooth. Moreover, when the scale varies significantly across different coordinates, we demonstrate that the coordinate-wise adaptivity of Adam is provably advantageous. Notably, unlike previous a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18199","kind":"arxiv","version":2},"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/2405.18199/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":"2026-07-05T09:28:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/bHMugqWezo9OBZPvJE73S4bRMzs4vQWfTfjfiewISV3VIdF14+TQwgFEZebbVHcpOp//apSoNcne4uW+73DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:32:18.565992Z"},"content_sha256":"b496926001720b6263701d6a4721179e4f76c172a30b035fe638283a36048a25","schema_version":"1.0","event_id":"sha256:b496926001720b6263701d6a4721179e4f76c172a30b035fe638283a36048a25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EI5WFVAH5DDNMDAQAYXZ46B27S/bundle.json","state_url":"https://pith.science/pith/EI5WFVAH5DDNMDAQAYXZ46B27S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EI5WFVAH5DDNMDAQAYXZ46B27S/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":"2026-08-05T02:32:18Z","links":{"resolver":"https://pith.science/pith/EI5WFVAH5DDNMDAQAYXZ46B27S","bundle":"https://pith.science/pith/EI5WFVAH5DDNMDAQAYXZ46B27S/bundle.json","state":"https://pith.science/pith/EI5WFVAH5DDNMDAQAYXZ46B27S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EI5WFVAH5DDNMDAQAYXZ46B27S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EI5WFVAH5DDNMDAQAYXZ46B27S","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":"15f9f6f846e0ac9f64ae263c2cefb6b593e5944445b3afd9ce2c94376b2625e9","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:08:04Z","title_canon_sha256":"f4e5b61884999d59929078264d04b981ddb6449a8c40ecde2a7e6f1ebf634880"},"schema_version":"1.0","source":{"id":"2405.18199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18199","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18199v2","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18199","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"EI5WFVAH5DDN","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"EI5WFVAH5DDNMDAQ","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"EI5WFVAH","created_at":"2026-07-05T09:28:31Z"}],"graph_snapshots":[{"event_id":"sha256:b496926001720b6263701d6a4721179e4f76c172a30b035fe638283a36048a25","target":"graph","created_at":"2026-07-05T09:28:31Z","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/2405.18199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we offer a theoretical analysis of two modern optimization techniques for training large and complex models: (i) adaptive optimization algorithms, such as Adam, and (ii) the model exponential moving average (EMA). Specifically, we demonstrate that a clipped version of Adam with model EMA achieves the optimal convergence rates in various nonconvex optimization settings, both smooth and nonsmooth. Moreover, when the scale varies significantly across different coordinates, we demonstrate that the coordinate-wise adaptivity of Adam is provably advantageous. Notably, unlike previous a","authors_text":"Ashok Cutkosky, Kwangjun Ahn","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:08:04Z","title":"Adam with model exponential moving average is effective for nonconvex optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18199","kind":"arxiv","version":2},"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":"sha256:1e8c14f627bb58ede9d73e15be3f8a27ead35f3d012526ae85a75e0225febe28","target":"record","created_at":"2026-07-05T09:28:31Z","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":"15f9f6f846e0ac9f64ae263c2cefb6b593e5944445b3afd9ce2c94376b2625e9","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:08:04Z","title_canon_sha256":"f4e5b61884999d59929078264d04b981ddb6449a8c40ecde2a7e6f1ebf634880"},"schema_version":"1.0","source":{"id":"2405.18199","kind":"arxiv","version":2}},"canonical_sha256":"223b62d407e8c6d60c10062f9e783afc9546f4405b71fac02297ceb4b26a1c95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"223b62d407e8c6d60c10062f9e783afc9546f4405b71fac02297ceb4b26a1c95","first_computed_at":"2026-07-05T09:28:31.403570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:31.403570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NrtW328HsJ1eEMz7l+KYuOXKL67+8HNtjsmx0Ql3RU9qLRf4d7mVx8eN9cmo0+0FvRJEJ4Yo/SCaH4CKtwnXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:31.403978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e8c14f627bb58ede9d73e15be3f8a27ead35f3d012526ae85a75e0225febe28","sha256:b496926001720b6263701d6a4721179e4f76c172a30b035fe638283a36048a25"],"state_sha256":"b142aacb5c9d18e6b33c10fa0b2b2e701386efff657fe2e58c15072a81e86906"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBn22YjGhLj057XASi9o13kMzHThJlQD1ZGDja+AljKDQD7zgo3cOuX94O07aEa2fo317gGXUCtIkZ/St9gwBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:32:18.572008Z","bundle_sha256":"7182047d6da2c8d71547d4f8faa0184f6b0f7ddda542f250ee6b44eb5cd3635a"}}