{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FKTBKVF5AADGVHM4FOGQOQR3KW","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":"f9fe54376b66c187fe70564220f96911e687421fb4977f6b17302b032b6152d0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T10:27:17Z","title_canon_sha256":"7347f672dbea8f467d385b8bd7929c8faa6759b1786c4c1d0e1719cbb96c0cd5"},"schema_version":"1.0","source":{"id":"2309.01507","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01507","created_at":"2026-07-05T07:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01507v3","created_at":"2026-07-05T07:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01507","created_at":"2026-07-05T07:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"FKTBKVF5AADG","created_at":"2026-07-05T07:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"FKTBKVF5AADGVHM4","created_at":"2026-07-05T07:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"FKTBKVF5","created_at":"2026-07-05T07:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:46018c6895933af13691751947c456df6250b640b8d97a4b4d32774898b118ef","target":"graph","created_at":"2026-07-05T07:05:47Z","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/2309.01507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimizer states are a major source of memory consumption for training neural networks, limiting the maximum trainable model within given memory budget. Compressing the optimizer states from 32-bit floating points to lower bitwidth is promising to reduce the training memory footprint, while the current lowest achievable bitwidth is 8-bit. In this work, we push optimizer states bitwidth down to 4-bit through a detailed empirical analysis of first and second moments. Specifically, we find that moments have complicated outlier patterns, that current block-wise quantization cannot accurately appro","authors_text":"Bingrui Li, Jianfei Chen, Jun Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T10:27:17Z","title":"Memory Efficient Optimizers with 4-bit States"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01507","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:ce18359c89b9351e081751578ce241c76183edd4895bad6c84c38b020d4b7001","target":"record","created_at":"2026-07-05T07:05:47Z","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":"f9fe54376b66c187fe70564220f96911e687421fb4977f6b17302b032b6152d0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T10:27:17Z","title_canon_sha256":"7347f672dbea8f467d385b8bd7929c8faa6759b1786c4c1d0e1719cbb96c0cd5"},"schema_version":"1.0","source":{"id":"2309.01507","kind":"arxiv","version":3}},"canonical_sha256":"2aa61554bd00066a9d9c2b8d07423b55bd198fa0ee1248d6cb4f71fa556a82aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2aa61554bd00066a9d9c2b8d07423b55bd198fa0ee1248d6cb4f71fa556a82aa","first_computed_at":"2026-07-05T07:05:47.260175Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:47.260175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"480L+rLWDpFo6yiGRZcgpGKjuKasDM9V6yt1aucxWToPDAzrmhCYRbuLRrwTt3l0dyeWyVWZLFXFDU9H5CS3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:47.260554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.01507","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce18359c89b9351e081751578ce241c76183edd4895bad6c84c38b020d4b7001","sha256:46018c6895933af13691751947c456df6250b640b8d97a4b4d32774898b118ef"],"state_sha256":"7b8529a5040bbee8b728dc8c465f5d9bad79f18990e12b84fd10b92de1c048c7"}