{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SZRSFPDR2E3YNID3VXBWZQGAAY","short_pith_number":"pith:SZRSFPDR","canonical_record":{"source":{"id":"2310.10195","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T09:04:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d4b657fa5226e71df47fc5a131383d4698515c10a2598c5f3a49700f260a815d","abstract_canon_sha256":"1986f1671a3049e8eb53ede487935b5bcb76f128cf7ce10cebaa3475ac99a8c4"},"schema_version":"1.0"},"canonical_sha256":"966322bc71d13786a07badc36cc0c0063943942d9405209942a974d2aa41cf6f","source":{"kind":"arxiv","id":"2310.10195","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10195","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10195v3","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10195","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"SZRSFPDR2E3Y","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"SZRSFPDR2E3YNID3","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"SZRSFPDR","created_at":"2026-07-05T08:28:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SZRSFPDR2E3YNID3VXBWZQGAAY","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10195","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T09:04:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d4b657fa5226e71df47fc5a131383d4698515c10a2598c5f3a49700f260a815d","abstract_canon_sha256":"1986f1671a3049e8eb53ede487935b5bcb76f128cf7ce10cebaa3475ac99a8c4"},"schema_version":"1.0"},"canonical_sha256":"966322bc71d13786a07badc36cc0c0063943942d9405209942a974d2aa41cf6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:03.180423Z","signature_b64":"qhJUwhCDZcml2Rn+LpH59QaPvzGLCujiWkDZlMR6o4Xr8ZcKTnXjqxnuf2u7qSLF2AjZrupuGzEhvgKaq6UuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"966322bc71d13786a07badc36cc0c0063943942d9405209942a974d2aa41cf6f","last_reissued_at":"2026-07-05T08:28:03.179937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:03.179937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10195","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fw8DL4eQTmXECCWSjhD0ZbHSHq8uLxpBRSE5tbABxGVoO3+7uZRlVt3XS0ZafH2PzoSvxyHLcDektwgCzqGODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:09:59.345402Z"},"content_sha256":"f192a3d0982e1dfc15669477d285b0507b170635e0acae580d00838f47ff262a","schema_version":"1.0","event_id":"sha256:f192a3d0982e1dfc15669477d285b0507b170635e0acae580d00838f47ff262a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SZRSFPDR2E3YNID3VXBWZQGAAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haijun Lv, Hang Yan, Kai Lv, Qipeng Guo, Xipeng Qiu","submitted_at":"2023-10-16T09:04:28Z","abstract_excerpt":"Large language models have achieved remarkable success, but their extensive parameter size necessitates substantial memory for training, thereby setting a high threshold. While the recently proposed low-memory optimization (LOMO) reduces memory footprint, its optimization technique, akin to stochastic gradient descent, is sensitive to hyper-parameters and exhibits suboptimal convergence, failing to match the performance of the prevailing optimizer for large language models, AdamW. Through empirical analysis of the Adam optimizer, we found that, compared to momentum, the adaptive learning rate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10195","kind":"arxiv","version":3},"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/2310.10195/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":"2026-07-05T08:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mCtSlRJ5l7hhkGroL1v6fy7lcU3xJ/d1SFaDKhyFF7FFsDzjkSoqPXMywIL7o8VhDEfIDiam7GxyEX7sNsrKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:09:59.345916Z"},"content_sha256":"1912484714b3acd8601bea1b7d07d31a618371269710d2d829187065ccd5beab","schema_version":"1.0","event_id":"sha256:1912484714b3acd8601bea1b7d07d31a618371269710d2d829187065ccd5beab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZRSFPDR2E3YNID3VXBWZQGAAY/bundle.json","state_url":"https://pith.science/pith/SZRSFPDR2E3YNID3VXBWZQGAAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZRSFPDR2E3YNID3VXBWZQGAAY/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":"2026-08-05T22:09:59Z","links":{"resolver":"https://pith.science/pith/SZRSFPDR2E3YNID3VXBWZQGAAY","bundle":"https://pith.science/pith/SZRSFPDR2E3YNID3VXBWZQGAAY/bundle.json","state":"https://pith.science/pith/SZRSFPDR2E3YNID3VXBWZQGAAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZRSFPDR2E3YNID3VXBWZQGAAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SZRSFPDR2E3YNID3VXBWZQGAAY","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":"1986f1671a3049e8eb53ede487935b5bcb76f128cf7ce10cebaa3475ac99a8c4","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T09:04:28Z","title_canon_sha256":"d4b657fa5226e71df47fc5a131383d4698515c10a2598c5f3a49700f260a815d"},"schema_version":"1.0","source":{"id":"2310.10195","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10195","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10195v3","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10195","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"SZRSFPDR2E3Y","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"SZRSFPDR2E3YNID3","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"SZRSFPDR","created_at":"2026-07-05T08:28:03Z"}],"graph_snapshots":[{"event_id":"sha256:1912484714b3acd8601bea1b7d07d31a618371269710d2d829187065ccd5beab","target":"graph","created_at":"2026-07-05T08:28:03Z","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/2310.10195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have achieved remarkable success, but their extensive parameter size necessitates substantial memory for training, thereby setting a high threshold. While the recently proposed low-memory optimization (LOMO) reduces memory footprint, its optimization technique, akin to stochastic gradient descent, is sensitive to hyper-parameters and exhibits suboptimal convergence, failing to match the performance of the prevailing optimizer for large language models, AdamW. Through empirical analysis of the Adam optimizer, we found that, compared to momentum, the adaptive learning rate ","authors_text":"Haijun Lv, Hang Yan, Kai Lv, Qipeng Guo, Xipeng Qiu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T09:04:28Z","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10195","kind":"arxiv","version":3},"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:f192a3d0982e1dfc15669477d285b0507b170635e0acae580d00838f47ff262a","target":"record","created_at":"2026-07-05T08:28:03Z","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":"1986f1671a3049e8eb53ede487935b5bcb76f128cf7ce10cebaa3475ac99a8c4","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T09:04:28Z","title_canon_sha256":"d4b657fa5226e71df47fc5a131383d4698515c10a2598c5f3a49700f260a815d"},"schema_version":"1.0","source":{"id":"2310.10195","kind":"arxiv","version":3}},"canonical_sha256":"966322bc71d13786a07badc36cc0c0063943942d9405209942a974d2aa41cf6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"966322bc71d13786a07badc36cc0c0063943942d9405209942a974d2aa41cf6f","first_computed_at":"2026-07-05T08:28:03.179937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:03.179937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qhJUwhCDZcml2Rn+LpH59QaPvzGLCujiWkDZlMR6o4Xr8ZcKTnXjqxnuf2u7qSLF2AjZrupuGzEhvgKaq6UuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:03.180423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10195","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f192a3d0982e1dfc15669477d285b0507b170635e0acae580d00838f47ff262a","sha256:1912484714b3acd8601bea1b7d07d31a618371269710d2d829187065ccd5beab"],"state_sha256":"4dc6bc34c4f454a69aca42d9da2cba48255bdd44fb972f0386f04ae673c729f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WLNueaxXSBDLaxTg+kUk5WGZCo1sxBHlcQ73WgvRQjLgeibAShXMk2fWIabwA3gdPGhxqBBv7qEa/cRAKMwBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:09:59.350001Z","bundle_sha256":"6372e11bf815b5f909242b1e5c78b739f9d60d5fe99a681d7843ea8158788b7d"}}