{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WMMONMU22YDKRNG6WOY4F5H5XF","short_pith_number":"pith:WMMONMU2","schema_version":"1.0","canonical_sha256":"b318e6b29ad606a8b4deb3b1c2f4fdb9667de9ed382c67f920d406c5687f6895","source":{"kind":"arxiv","id":"2406.01392","version":2},"attestation_state":"computed","paper":{"title":"Sparsity-Accelerated Training for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Da Ma, Hanqi Li, Hongshen Xu, Kai Yu, Liangtai Sun, Lu Chen, Pengyu Wang, Shuai Fan, Su Zhu","submitted_at":"2024-06-03T14:56:09Z","abstract_excerpt":"Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-training and supervised fine-tuning. However, the costs associated with this, primarily due to their large parameter count, remain high. This paper proposes leveraging \\emph{sparsity} in pre-trained LLMs to expedite this training process. By observing sparsity in activated neurons during forward iterations, we identify the potential for computational speed-ups by excluding inactive neurons. We address associated challenge"},"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":"2406.01392","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T14:56:09Z","cross_cats_sorted":[],"title_canon_sha256":"9d27d6687027de4210a9416d5fb31cc7392bed69be826f432846f1aa2b48590b","abstract_canon_sha256":"3cbc01f56c2e6e2fbfbed63b09536059ba0c9571105fd8d5823ee7ad390019f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:27.638940Z","signature_b64":"MTbyoRZqxh6vlRKnwbjvu5Qm0Edyx5KsMcpnYSbCai30uGrorXSx5M+zrDzVbtv7QwnWnoQclj/x/bOvbot/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b318e6b29ad606a8b4deb3b1c2f4fdb9667de9ed382c67f920d406c5687f6895","last_reissued_at":"2026-07-05T08:28:27.638471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:27.638471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparsity-Accelerated Training for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Da Ma, Hanqi Li, Hongshen Xu, Kai Yu, Liangtai Sun, Lu Chen, Pengyu Wang, Shuai Fan, Su Zhu","submitted_at":"2024-06-03T14:56:09Z","abstract_excerpt":"Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-training and supervised fine-tuning. However, the costs associated with this, primarily due to their large parameter count, remain high. This paper proposes leveraging \\emph{sparsity} in pre-trained LLMs to expedite this training process. By observing sparsity in activated neurons during forward iterations, we identify the potential for computational speed-ups by excluding inactive neurons. We address associated challenge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01392","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/2406.01392/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":"2406.01392","created_at":"2026-07-05T08:28:27.638533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01392v2","created_at":"2026-07-05T08:28:27.638533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01392","created_at":"2026-07-05T08:28:27.638533+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMMONMU22YDK","created_at":"2026-07-05T08:28:27.638533+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMMONMU22YDKRNG6","created_at":"2026-07-05T08:28:27.638533+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMMONMU2","created_at":"2026-07-05T08:28:27.638533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF","json":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF.json","graph_json":"https://pith.science/api/pith-number/WMMONMU22YDKRNG6WOY4F5H5XF/graph.json","events_json":"https://pith.science/api/pith-number/WMMONMU22YDKRNG6WOY4F5H5XF/events.json","paper":"https://pith.science/paper/WMMONMU2"},"agent_actions":{"view_html":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF","download_json":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF.json","view_paper":"https://pith.science/paper/WMMONMU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01392&json=true","fetch_graph":"https://pith.science/api/pith-number/WMMONMU22YDKRNG6WOY4F5H5XF/graph.json","fetch_events":"https://pith.science/api/pith-number/WMMONMU22YDKRNG6WOY4F5H5XF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF/action/storage_attestation","attest_author":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF/action/author_attestation","sign_citation":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF/action/citation_signature","submit_replication":"https://pith.science/pith/WMMONMU22YDKRNG6WOY4F5H5XF/action/replication_record"}},"created_at":"2026-07-05T08:28:27.638533+00:00","updated_at":"2026-07-05T08:28:27.638533+00:00"}