{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FAO6OGKWHAQ4TQIIHRC76D44S5","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":"29a1007fc86d3c8973274c10f9415a43968bce5fed2f99cfebc86b55cfd8c10d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T15:43:20Z","title_canon_sha256":"764b4da5b14458928b23324402b38cb19bb62725a46dbae0978ade484c14a6a4"},"schema_version":"1.0","source":{"id":"2110.02861","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02861","created_at":"2026-07-05T04:32:51Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02861v2","created_at":"2026-07-05T04:32:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02861","created_at":"2026-07-05T04:32:51Z"},{"alias_kind":"pith_short_12","alias_value":"FAO6OGKWHAQ4","created_at":"2026-07-05T04:32:51Z"},{"alias_kind":"pith_short_16","alias_value":"FAO6OGKWHAQ4TQII","created_at":"2026-07-05T04:32:51Z"},{"alias_kind":"pith_short_8","alias_value":"FAO6OGKW","created_at":"2026-07-05T04:32:51Z"}],"graph_snapshots":[{"event_id":"sha256:1aeca3ef18b7ba55274939843cd656878bc9dd5a7979a36928622fc7a303dd7f","target":"graph","created_at":"2026-07-05T04:32:51Z","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/2110.02861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stateful optimizers maintain gradient statistics over time, e.g., the exponentially smoothed sum (SGD with momentum) or squared sum (Adam) of past gradient values. This state can be used to accelerate optimization compared to plain stochastic gradient descent but uses memory that might otherwise be allocated to model parameters, thereby limiting the maximum size of models trained in practice. In this paper, we develop the first optimizers that use 8-bit statistics while maintaining the performance levels of using 32-bit optimizer states. To overcome the resulting computational, quantization, a","authors_text":"Luke Zettlemoyer, Mike Lewis, Sam Shleifer, Tim Dettmers","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T15:43:20Z","title":"8-bit Optimizers via Block-wise Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02861","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:c444660dff216ffdd6aae30bbce2f2db6f34307d0638c8b1dab0780c727a6bb7","target":"record","created_at":"2026-07-05T04:32:51Z","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":"29a1007fc86d3c8973274c10f9415a43968bce5fed2f99cfebc86b55cfd8c10d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T15:43:20Z","title_canon_sha256":"764b4da5b14458928b23324402b38cb19bb62725a46dbae0978ade484c14a6a4"},"schema_version":"1.0","source":{"id":"2110.02861","kind":"arxiv","version":2}},"canonical_sha256":"281de719563821c9c1083c45ff0f9c97677438c1ec146f7c207cb939f19c8f98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"281de719563821c9c1083c45ff0f9c97677438c1ec146f7c207cb939f19c8f98","first_computed_at":"2026-07-05T04:32:51.924332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:51.924332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vik9Q9yOzDF/nwQQPPXa06Jb7J/wwACbCQlal7ejdfVSRGbdK0mPq8dQgHOGVnn01rBi6Da9+olmSlFYdqzMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:51.924825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02861","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c444660dff216ffdd6aae30bbce2f2db6f34307d0638c8b1dab0780c727a6bb7","sha256:1aeca3ef18b7ba55274939843cd656878bc9dd5a7979a36928622fc7a303dd7f"],"state_sha256":"d925daa7411cd0db0d3d4dc76e7b0010c0b0fe159276d12076ce48736785608b"}