{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5GLYRQWISBMTTF3GN5S5FKBQ66","short_pith_number":"pith:5GLYRQWI","canonical_record":{"source":{"id":"2506.16659","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T00:10:35Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"e23700cd447f3fb289457403c1de9e4e4ccd2b6cd75f0238eda93186941fe2ea","abstract_canon_sha256":"fb145049edde77775fb72af8b6b40a4ae2381029475cb35bc5fca05534044295"},"schema_version":"1.0"},"canonical_sha256":"e99788c2c890593997666f65d2a830f79dc294613e3e1f0b9a257e5a4c8ad390","source":{"kind":"arxiv","id":"2506.16659","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16659","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16659v3","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16659","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"5GLYRQWISBMT","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"5GLYRQWISBMTTF3G","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"5GLYRQWI","created_at":"2026-05-22T01:03:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5GLYRQWISBMTTF3GN5S5FKBQ66","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16659","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T00:10:35Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"e23700cd447f3fb289457403c1de9e4e4ccd2b6cd75f0238eda93186941fe2ea","abstract_canon_sha256":"fb145049edde77775fb72af8b6b40a4ae2381029475cb35bc5fca05534044295"},"schema_version":"1.0"},"canonical_sha256":"e99788c2c890593997666f65d2a830f79dc294613e3e1f0b9a257e5a4c8ad390","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:43.627522Z","signature_b64":"TnpRBpAGahUvU9uiv00WD6hKQmwHKvxcH4WolPu/mcTPfCN0IkEqBYw2MY2+OKcHk1mB7EEZHOgIJHhW0ianAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e99788c2c890593997666f65d2a830f79dc294613e3e1f0b9a257e5a4c8ad390","last_reissued_at":"2026-05-22T01:03:43.626630Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:43.626630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16659","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":"2026-05-22T01:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dfFXG+In+qk3XoJf90u+eSx5Tp8Fv9t3779FnnaCslrGMGHMsW5pNgFPGOVVlh0R6kG9Uu6EhcXEQWYk/YegDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T13:55:00.557397Z"},"content_sha256":"677888e35a1adda19e7342a556c189715a23c09a6641b300d4275042fb84291c","schema_version":"1.0","event_id":"sha256:677888e35a1adda19e7342a556c189715a23c09a6641b300d4275042fb84291c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5GLYRQWISBMTTF3GN5S5FKBQ66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory-Efficient LLM Pretraining via Minimalist Optimizer Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Andi Han, Athanasios Glentis, Jiaxiang Li, Mingyi Hong","submitted_at":"2025-06-20T00:10:35Z","abstract_excerpt":"Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as GaLore, Fira and APOLLO have proposed state-compressed memory-efficient variants, a fundamental question remains: What are the minimum modifications to plain SGD needed to match state-of-the-art pretraining performance? We systematically investigate this question using a bottom-up approach, and identify two simple yet highly (memory- and compute-) efficient techni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16659","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/2506.16659/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":"2026-05-22T01:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KDz3DStdvxnPDg7+FN2IupNL8re0BVr6QCuk1RvglNc2etPLFlP1a9qGWCZObCLhxgM/jLOKmQ2ucb7gU6nbAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T13:55:00.558129Z"},"content_sha256":"c01f01d840fa980beb96215a775c4e234c768a15fa99fd81d7ba249a0e2217eb","schema_version":"1.0","event_id":"sha256:c01f01d840fa980beb96215a775c4e234c768a15fa99fd81d7ba249a0e2217eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5GLYRQWISBMTTF3GN5S5FKBQ66/bundle.json","state_url":"https://pith.science/pith/5GLYRQWISBMTTF3GN5S5FKBQ66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5GLYRQWISBMTTF3GN5S5FKBQ66/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":"2026-05-22T13:55:00Z","links":{"resolver":"https://pith.science/pith/5GLYRQWISBMTTF3GN5S5FKBQ66","bundle":"https://pith.science/pith/5GLYRQWISBMTTF3GN5S5FKBQ66/bundle.json","state":"https://pith.science/pith/5GLYRQWISBMTTF3GN5S5FKBQ66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5GLYRQWISBMTTF3GN5S5FKBQ66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5GLYRQWISBMTTF3GN5S5FKBQ66","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":"fb145049edde77775fb72af8b6b40a4ae2381029475cb35bc5fca05534044295","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T00:10:35Z","title_canon_sha256":"e23700cd447f3fb289457403c1de9e4e4ccd2b6cd75f0238eda93186941fe2ea"},"schema_version":"1.0","source":{"id":"2506.16659","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16659","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16659v3","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16659","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"5GLYRQWISBMT","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"5GLYRQWISBMTTF3G","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"5GLYRQWI","created_at":"2026-05-22T01:03:43Z"}],"graph_snapshots":[{"event_id":"sha256:c01f01d840fa980beb96215a775c4e234c768a15fa99fd81d7ba249a0e2217eb","target":"graph","created_at":"2026-05-22T01:03:43Z","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/2506.16659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as GaLore, Fira and APOLLO have proposed state-compressed memory-efficient variants, a fundamental question remains: What are the minimum modifications to plain SGD needed to match state-of-the-art pretraining performance? We systematically investigate this question using a bottom-up approach, and identify two simple yet highly (memory- and compute-) efficient techni","authors_text":"Andi Han, Athanasios Glentis, Jiaxiang Li, Mingyi Hong","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T00:10:35Z","title":"Memory-Efficient LLM Pretraining via Minimalist Optimizer Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16659","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":"sha256:677888e35a1adda19e7342a556c189715a23c09a6641b300d4275042fb84291c","target":"record","created_at":"2026-05-22T01:03:43Z","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":"fb145049edde77775fb72af8b6b40a4ae2381029475cb35bc5fca05534044295","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T00:10:35Z","title_canon_sha256":"e23700cd447f3fb289457403c1de9e4e4ccd2b6cd75f0238eda93186941fe2ea"},"schema_version":"1.0","source":{"id":"2506.16659","kind":"arxiv","version":3}},"canonical_sha256":"e99788c2c890593997666f65d2a830f79dc294613e3e1f0b9a257e5a4c8ad390","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e99788c2c890593997666f65d2a830f79dc294613e3e1f0b9a257e5a4c8ad390","first_computed_at":"2026-05-22T01:03:43.626630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:43.626630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TnpRBpAGahUvU9uiv00WD6hKQmwHKvxcH4WolPu/mcTPfCN0IkEqBYw2MY2+OKcHk1mB7EEZHOgIJHhW0ianAA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:43.627522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16659","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:677888e35a1adda19e7342a556c189715a23c09a6641b300d4275042fb84291c","sha256:c01f01d840fa980beb96215a775c4e234c768a15fa99fd81d7ba249a0e2217eb"],"state_sha256":"82ae710ee577f0d1d34204e4f458b3202f07ef9ebf7815fd884ce462773b8c7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"taRt6Mbn6pE3qKXXnZyDocAGDKn+GbR+G8iYPZSKVTxkt20YQUz2eDltjwWTnUOaQpLXM77jZzMyKuRwq1s1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T13:55:00.562503Z","bundle_sha256":"70a425bdebb60f690ff7036774b0cd4111649b96790a227d90d1cde6ee0b8cba"}}