{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IH5XHGLCHMPS2NJH4HTQ6VNYGO","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":"4fe810a373e09491184e7ce1b152919d3ec82b5a1d3ab0d02624f8546a407387","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T13:42:09Z","title_canon_sha256":"c98a7ad4f47f0a63014154c7bdb3816da5119baa8889a151dcdb78debc139b16"},"schema_version":"1.0","source":{"id":"2407.11722","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11722","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11722v2","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11722","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_12","alias_value":"IH5XHGLCHMPS","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_16","alias_value":"IH5XHGLCHMPS2NJH","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_8","alias_value":"IH5XHGLC","created_at":"2026-07-05T09:19:11Z"}],"graph_snapshots":[{"event_id":"sha256:c88f8e62628bd789398083ffec6630075f25d20bf0d24ad9a950839c1c85fc57","target":"graph","created_at":"2026-07-05T09:19:11Z","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/2407.11722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has proven to be effective after pre-training and during fine-tuning, applying quantization in Transformers during pre-training has remained largely unexplored at scale for language modeling. This study aims to explore the impact of quantization for efficient pre-training of Transformers, with a focus on linear layer components. By systematically applying straightforward linear quantization to weights, activations, gradients, and optimizer states, we assess its","authors_text":"Gon\\c{c}alo Mordido, Kamran Chitsaz, Quentin Fournier, Sarath Chandar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T13:42:09Z","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11722","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":"sha256:4ba331ae43e5793bf3781a263a2c2995da13280dd8e6eb8d2d57598cf49474d1","target":"record","created_at":"2026-07-05T09:19:11Z","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":"4fe810a373e09491184e7ce1b152919d3ec82b5a1d3ab0d02624f8546a407387","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T13:42:09Z","title_canon_sha256":"c98a7ad4f47f0a63014154c7bdb3816da5119baa8889a151dcdb78debc139b16"},"schema_version":"1.0","source":{"id":"2407.11722","kind":"arxiv","version":2}},"canonical_sha256":"41fb7399623b1f2d3527e1e70f55b8338656f53a15bee6b7b118fd78991bd2fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41fb7399623b1f2d3527e1e70f55b8338656f53a15bee6b7b118fd78991bd2fc","first_computed_at":"2026-07-05T09:19:11.423707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:11.423707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NhtNxcQot1lyA35OTN4YJIkBp+NL2jTg87Bd8hlYTbxsL8YzXK7olQXCl6cjiChPbJqN+bx25kr+hJC8k090Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:11.424189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11722","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ba331ae43e5793bf3781a263a2c2995da13280dd8e6eb8d2d57598cf49474d1","sha256:c88f8e62628bd789398083ffec6630075f25d20bf0d24ad9a950839c1c85fc57"],"state_sha256":"af2c631ffdf5a55436950be487b7a9312bc4448fb7d86c3f57668ada1499d8fb"}