{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T77WM7AD6GLNPABNY2V64A367Z","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":"bf4d48d0e69130255c9f9e26e1fe6c03089bb8010bfc06ff2d42c30c53e1fe22","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-05T06:05:36Z","title_canon_sha256":"da2175414131c2c83ae372690a3d95defc7a753b23fe529379f49066e26a9ecf"},"schema_version":"1.0","source":{"id":"2307.02047","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02047","created_at":"2026-07-05T06:38:01Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02047v2","created_at":"2026-07-05T06:38:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02047","created_at":"2026-07-05T06:38:01Z"},{"alias_kind":"pith_short_12","alias_value":"T77WM7AD6GLN","created_at":"2026-07-05T06:38:01Z"},{"alias_kind":"pith_short_16","alias_value":"T77WM7AD6GLNPABN","created_at":"2026-07-05T06:38:01Z"},{"alias_kind":"pith_short_8","alias_value":"T77WM7AD","created_at":"2026-07-05T06:38:01Z"}],"graph_snapshots":[{"event_id":"sha256:c753d8dee39f81417f472f407f5dab1283a548c9185166a27829ec4c830d598e","target":"graph","created_at":"2026-07-05T06:38:01Z","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/2307.02047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive gradient methods, such as Adam and LAMB, have demonstrated excellent performance in the training of large language models. Nevertheless, the need for adaptivity requires maintaining second-moment estimates of the per-parameter gradients, which entails a high cost of extra memory overheads. To solve this problem, several memory-efficient optimizers (e.g., Adafactor) have been proposed to obtain a drastic reduction in auxiliary memory usage, but with a performance penalty. In this paper, we first study a confidence-guided strategy to reduce the instability of existing memory efficient o","authors_text":"Xiaozhe Ren, Xin Jiang, Yang Luo, Yang You, Zangwei Zheng, Zhuo Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-05T06:05:36Z","title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02047","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":"sha256:5d551df96faa5e3c1be767041d67e46b7c69ad2cf3e79af892edf6dadfd1ed24","target":"record","created_at":"2026-07-05T06:38:01Z","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":"bf4d48d0e69130255c9f9e26e1fe6c03089bb8010bfc06ff2d42c30c53e1fe22","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-05T06:05:36Z","title_canon_sha256":"da2175414131c2c83ae372690a3d95defc7a753b23fe529379f49066e26a9ecf"},"schema_version":"1.0","source":{"id":"2307.02047","kind":"arxiv","version":2}},"canonical_sha256":"9fff667c03f196d7802dc6abee037efe491df742f16d209bc8988eaccf81becb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fff667c03f196d7802dc6abee037efe491df742f16d209bc8988eaccf81becb","first_computed_at":"2026-07-05T06:38:01.543770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:38:01.543770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lv9F++Tqyl4e1JloYKGSJDnCg469ujQFlbllzwqsWKEhv/bOkd8rVH9siD7UZnqNdUx0E3HgUYdvLW3tfgkFDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:38:01.544152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02047","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d551df96faa5e3c1be767041d67e46b7c69ad2cf3e79af892edf6dadfd1ed24","sha256:c753d8dee39f81417f472f407f5dab1283a548c9185166a27829ec4c830d598e"],"state_sha256":"d1688573f54c5034ab0476abdf52a6e8e43bd2414ca51fb477250c1699cfbbaf"}