{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T77WM7AD6GLNPABNY2V64A367Z","short_pith_number":"pith:T77WM7AD","schema_version":"1.0","canonical_sha256":"9fff667c03f196d7802dc6abee037efe491df742f16d209bc8988eaccf81becb","source":{"kind":"arxiv","id":"2307.02047","version":2},"attestation_state":"computed","paper":{"title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiaozhe Ren, Xin Jiang, Yang Luo, Yang You, Zangwei Zheng, Zhuo Jiang","submitted_at":"2023-07-05T06:05:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.02047","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-05T06:05:36Z","cross_cats_sorted":[],"title_canon_sha256":"da2175414131c2c83ae372690a3d95defc7a753b23fe529379f49066e26a9ecf","abstract_canon_sha256":"bf4d48d0e69130255c9f9e26e1fe6c03089bb8010bfc06ff2d42c30c53e1fe22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:01.544152Z","signature_b64":"Lv9F++Tqyl4e1JloYKGSJDnCg469ujQFlbllzwqsWKEhv/bOkd8rVH9siD7UZnqNdUx0E3HgUYdvLW3tfgkFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fff667c03f196d7802dc6abee037efe491df742f16d209bc8988eaccf81becb","last_reissued_at":"2026-07-05T06:38:01.543770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:01.543770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiaozhe Ren, Xin Jiang, Yang Luo, Yang You, Zangwei Zheng, Zhuo Jiang","submitted_at":"2023-07-05T06:05:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02047","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/2307.02047/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.02047","created_at":"2026-07-05T06:38:01.543825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02047v2","created_at":"2026-07-05T06:38:01.543825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02047","created_at":"2026-07-05T06:38:01.543825+00:00"},{"alias_kind":"pith_short_12","alias_value":"T77WM7AD6GLN","created_at":"2026-07-05T06:38:01.543825+00:00"},{"alias_kind":"pith_short_16","alias_value":"T77WM7AD6GLNPABN","created_at":"2026-07-05T06:38:01.543825+00:00"},{"alias_kind":"pith_short_8","alias_value":"T77WM7AD","created_at":"2026-07-05T06:38:01.543825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10855","citing_title":"Sparse Fine-Tuning of Transformers for Generative Tasks","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z","json":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z.json","graph_json":"https://pith.science/api/pith-number/T77WM7AD6GLNPABNY2V64A367Z/graph.json","events_json":"https://pith.science/api/pith-number/T77WM7AD6GLNPABNY2V64A367Z/events.json","paper":"https://pith.science/paper/T77WM7AD"},"agent_actions":{"view_html":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z","download_json":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z.json","view_paper":"https://pith.science/paper/T77WM7AD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02047&json=true","fetch_graph":"https://pith.science/api/pith-number/T77WM7AD6GLNPABNY2V64A367Z/graph.json","fetch_events":"https://pith.science/api/pith-number/T77WM7AD6GLNPABNY2V64A367Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z/action/storage_attestation","attest_author":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z/action/author_attestation","sign_citation":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z/action/citation_signature","submit_replication":"https://pith.science/pith/T77WM7AD6GLNPABNY2V64A367Z/action/replication_record"}},"created_at":"2026-07-05T06:38:01.543825+00:00","updated_at":"2026-07-05T06:38:01.543825+00:00"}