{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IH5XHGLCHMPS2NJH4HTQ6VNYGO","short_pith_number":"pith:IH5XHGLC","schema_version":"1.0","canonical_sha256":"41fb7399623b1f2d3527e1e70f55b8338656f53a15bee6b7b118fd78991bd2fc","source":{"kind":"arxiv","id":"2407.11722","version":2},"attestation_state":"computed","paper":{"title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gon\\c{c}alo Mordido, Kamran Chitsaz, Quentin Fournier, Sarath Chandar","submitted_at":"2024-07-16T13:42:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.11722","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T13:42:09Z","cross_cats_sorted":[],"title_canon_sha256":"c98a7ad4f47f0a63014154c7bdb3816da5119baa8889a151dcdb78debc139b16","abstract_canon_sha256":"4fe810a373e09491184e7ce1b152919d3ec82b5a1d3ab0d02624f8546a407387"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:11.424189Z","signature_b64":"NhtNxcQot1lyA35OTN4YJIkBp+NL2jTg87Bd8hlYTbxsL8YzXK7olQXCl6cjiChPbJqN+bx25kr+hJC8k090Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41fb7399623b1f2d3527e1e70f55b8338656f53a15bee6b7b118fd78991bd2fc","last_reissued_at":"2026-07-05T09:19:11.423707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:11.423707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gon\\c{c}alo Mordido, Kamran Chitsaz, Quentin Fournier, Sarath Chandar","submitted_at":"2024-07-16T13:42:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11722","kind":"arxiv","version":2},"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/2407.11722/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.11722","created_at":"2026-07-05T09:19:11.423766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11722v2","created_at":"2026-07-05T09:19:11.423766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11722","created_at":"2026-07-05T09:19:11.423766+00:00"},{"alias_kind":"pith_short_12","alias_value":"IH5XHGLCHMPS","created_at":"2026-07-05T09:19:11.423766+00:00"},{"alias_kind":"pith_short_16","alias_value":"IH5XHGLCHMPS2NJH","created_at":"2026-07-05T09:19:11.423766+00:00"},{"alias_kind":"pith_short_8","alias_value":"IH5XHGLC","created_at":"2026-07-05T09:19:11.423766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22922","citing_title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO","json":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO.json","graph_json":"https://pith.science/api/pith-number/IH5XHGLCHMPS2NJH4HTQ6VNYGO/graph.json","events_json":"https://pith.science/api/pith-number/IH5XHGLCHMPS2NJH4HTQ6VNYGO/events.json","paper":"https://pith.science/paper/IH5XHGLC"},"agent_actions":{"view_html":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO","download_json":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO.json","view_paper":"https://pith.science/paper/IH5XHGLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11722&json=true","fetch_graph":"https://pith.science/api/pith-number/IH5XHGLCHMPS2NJH4HTQ6VNYGO/graph.json","fetch_events":"https://pith.science/api/pith-number/IH5XHGLCHMPS2NJH4HTQ6VNYGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO/action/storage_attestation","attest_author":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO/action/author_attestation","sign_citation":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO/action/citation_signature","submit_replication":"https://pith.science/pith/IH5XHGLCHMPS2NJH4HTQ6VNYGO/action/replication_record"}},"created_at":"2026-07-05T09:19:11.423766+00:00","updated_at":"2026-07-05T09:19:11.423766+00:00"}