{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IXSVI7SWMIEZDWNWXR5VFT7CMW","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":"c59126d61cc254595b0052ef621408fd8b6c3ee4cb5a8cb4320c0ea7c6e5f5cc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T08:16:48Z","title_canon_sha256":"657d956ec3b4dd8500ff9122f813a7883918e77ade5c836febe2750fd3016c5e"},"schema_version":"1.0","source":{"id":"2505.16363","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16363","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16363v1","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16363","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"IXSVI7SWMIEZ","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"IXSVI7SWMIEZDWNW","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"IXSVI7SW","created_at":"2026-07-05T11:07:34Z"}],"graph_snapshots":[{"event_id":"sha256:b1d1897ce89d74db2500927f9c0fd66c7866edbef88e1d74e5a890165775ab4b","target":"graph","created_at":"2026-07-05T11:07:34Z","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/2505.16363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce AdamS, a simple yet effective alternative to Adam for large language model (LLM) pretraining and post-training. By leveraging a novel denominator, i.e., the root of weighted sum of squares of the momentum and the current gradient, AdamS eliminates the need for second-moment estimates. Hence, AdamS is efficient, matching the memory and compute footprint of SGD with momentum while delivering superior optimization performance. Moreover, AdamS is easy to adopt: it can directly inherit hyperparameters of AdamW, and is entirely model-agnostic, integrating seamlessly into existing pipeli","authors_text":"Bohan Wang, Huishuai Zhang, Luoxin Chen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T08:16:48Z","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16363","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":"sha256:47c0b61b6f4add18c50722babdc27ad452362bef13ca0069134c2bd87a3b5ff8","target":"record","created_at":"2026-07-05T11:07:34Z","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":"c59126d61cc254595b0052ef621408fd8b6c3ee4cb5a8cb4320c0ea7c6e5f5cc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T08:16:48Z","title_canon_sha256":"657d956ec3b4dd8500ff9122f813a7883918e77ade5c836febe2750fd3016c5e"},"schema_version":"1.0","source":{"id":"2505.16363","kind":"arxiv","version":1}},"canonical_sha256":"45e5547e56620991d9b6bc7b52cfe265949dcb2116018d6dd00eb146888b6367","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45e5547e56620991d9b6bc7b52cfe265949dcb2116018d6dd00eb146888b6367","first_computed_at":"2026-07-05T11:07:34.169383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:34.169383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7GLO+ICU5zNmTbDg41YMBrtfqkkcN+0lOXRqHHHqpFGm8Xp6ECxVNHv27YFzgJefTtOHraROeDOjF7a15u0UCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:34.169869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16363","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47c0b61b6f4add18c50722babdc27ad452362bef13ca0069134c2bd87a3b5ff8","sha256:b1d1897ce89d74db2500927f9c0fd66c7866edbef88e1d74e5a890165775ab4b"],"state_sha256":"f97eeccae0b3d495e061444f481132e99149f69c917e9376eaa262e6df861c52"}