{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LCGDKACG2IOKE7FZHL7UAKXVNP","short_pith_number":"pith:LCGDKACG","canonical_record":{"source":{"id":"2605.20533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T22:11:04Z","cross_cats_sorted":[],"title_canon_sha256":"6a469f1e123b26bc33d153743c80b26a622bfe176be786e9f1ac6953e4042017","abstract_canon_sha256":"b2482ac5a54d461b9fd158583d6b445db35f06721440cf3e0508f7262d47c0d1"},"schema_version":"1.0"},"canonical_sha256":"588c350046d21ca27cb93aff402af56bf455b01df483023192a2f4a4e5981b8f","source":{"kind":"arxiv","id":"2605.20533","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20533","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20533v1","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20533","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"LCGDKACG2IOK","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"LCGDKACG2IOKE7FZ","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"LCGDKACG","created_at":"2026-05-21T01:04:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LCGDKACG2IOKE7FZHL7UAKXVNP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T22:11:04Z","cross_cats_sorted":[],"title_canon_sha256":"6a469f1e123b26bc33d153743c80b26a622bfe176be786e9f1ac6953e4042017","abstract_canon_sha256":"b2482ac5a54d461b9fd158583d6b445db35f06721440cf3e0508f7262d47c0d1"},"schema_version":"1.0"},"canonical_sha256":"588c350046d21ca27cb93aff402af56bf455b01df483023192a2f4a4e5981b8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:41.365774Z","signature_b64":"9H7oR4u7pRHaabNuygrK5/lhBz55yeZXmgrqBNn8unEWgyEyNZ5keOJQjFe8Mg8ILeKXeLp6ihxWXStuLkpRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"588c350046d21ca27cb93aff402af56bf455b01df483023192a2f4a4e5981b8f","last_reissued_at":"2026-05-21T01:04:41.365077Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:41.365077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20533","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":"2026-05-21T01:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UP28SXPmDALLi2jgm6TF+DhelKg5/WA9cBKUeRplpvhlZ1v+Urcl102xfkf+gUyODIxuQqn2Y0cJzidhdnviAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T23:18:48.656618Z"},"content_sha256":"df03dc7ac0026092056d7575575da203c590fb30b57e6ac1319f7c50983c41d0","schema_version":"1.0","event_id":"sha256:df03dc7ac0026092056d7575575da203c590fb30b57e6ac1319f7c50983c41d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LCGDKACG2IOKE7FZHL7UAKXVNP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Meng Zhu, Quan Xiao, Weidong Min","submitted_at":"2026-05-19T22:11:04Z","abstract_excerpt":"Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum SGD and AdamW represent two important optimization paradigms. AdamW produces stable updates and usually has strong robustness across training scenarios, but its generalization performance is sometimes weaker than that of momentum methods. Momentum SGD can often obtain better generalization after careful tuning, but it is more sensitive to gradient-scale variation and hyperparameter settings. To balance the strengths"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20533","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/2605.20533/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":"2026-05-21T01:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TKK74XoMKlOeTfFtz9Qjn57NbE21O5ZuoVRcgeF3OICh9//3jqiWVwT0vCENeOTyyP962lbpHT2bMGnNjhxzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T23:18:48.657369Z"},"content_sha256":"6867d88fd40af0a3c436b12e096c039693ac6cc2391301b11aa12834286cdabf","schema_version":"1.0","event_id":"sha256:6867d88fd40af0a3c436b12e096c039693ac6cc2391301b11aa12834286cdabf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LCGDKACG2IOKE7FZHL7UAKXVNP/bundle.json","state_url":"https://pith.science/pith/LCGDKACG2IOKE7FZHL7UAKXVNP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LCGDKACG2IOKE7FZHL7UAKXVNP/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":"2026-05-24T23:18:48Z","links":{"resolver":"https://pith.science/pith/LCGDKACG2IOKE7FZHL7UAKXVNP","bundle":"https://pith.science/pith/LCGDKACG2IOKE7FZHL7UAKXVNP/bundle.json","state":"https://pith.science/pith/LCGDKACG2IOKE7FZHL7UAKXVNP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LCGDKACG2IOKE7FZHL7UAKXVNP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LCGDKACG2IOKE7FZHL7UAKXVNP","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":"b2482ac5a54d461b9fd158583d6b445db35f06721440cf3e0508f7262d47c0d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T22:11:04Z","title_canon_sha256":"6a469f1e123b26bc33d153743c80b26a622bfe176be786e9f1ac6953e4042017"},"schema_version":"1.0","source":{"id":"2605.20533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20533","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20533v1","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20533","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"LCGDKACG2IOK","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"LCGDKACG2IOKE7FZ","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"LCGDKACG","created_at":"2026-05-21T01:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:6867d88fd40af0a3c436b12e096c039693ac6cc2391301b11aa12834286cdabf","target":"graph","created_at":"2026-05-21T01:04:41Z","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/2605.20533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum SGD and AdamW represent two important optimization paradigms. AdamW produces stable updates and usually has strong robustness across training scenarios, but its generalization performance is sometimes weaker than that of momentum methods. Momentum SGD can often obtain better generalization after careful tuning, but it is more sensitive to gradient-scale variation and hyperparameter settings. To balance the strengths","authors_text":"Meng Zhu, Quan Xiao, Weidong Min","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T22:11:04Z","title":"Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20533","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:df03dc7ac0026092056d7575575da203c590fb30b57e6ac1319f7c50983c41d0","target":"record","created_at":"2026-05-21T01:04:41Z","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":"b2482ac5a54d461b9fd158583d6b445db35f06721440cf3e0508f7262d47c0d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T22:11:04Z","title_canon_sha256":"6a469f1e123b26bc33d153743c80b26a622bfe176be786e9f1ac6953e4042017"},"schema_version":"1.0","source":{"id":"2605.20533","kind":"arxiv","version":1}},"canonical_sha256":"588c350046d21ca27cb93aff402af56bf455b01df483023192a2f4a4e5981b8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"588c350046d21ca27cb93aff402af56bf455b01df483023192a2f4a4e5981b8f","first_computed_at":"2026-05-21T01:04:41.365077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:41.365077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9H7oR4u7pRHaabNuygrK5/lhBz55yeZXmgrqBNn8unEWgyEyNZ5keOJQjFe8Mg8ILeKXeLp6ihxWXStuLkpRCg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:41.365774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df03dc7ac0026092056d7575575da203c590fb30b57e6ac1319f7c50983c41d0","sha256:6867d88fd40af0a3c436b12e096c039693ac6cc2391301b11aa12834286cdabf"],"state_sha256":"fa056432e5cbea9d23cc297ab977648f05bf65e3de8c8759eb537232ebf67bc4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J6chiZv5ZbTttkh/U188wL2VuoC/JJFqqnXoXetxtEZP7p5p2UlaPZCBNTfGvoUd4QXnPw/gcT67HHieHTObAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T23:18:48.661227Z","bundle_sha256":"9f065842b8e485361220fba3e1156365a8e1598758b2954c4e326fb400257815"}}