{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BA6TJRI3MLIUOSVYMWFZXVW4XO","short_pith_number":"pith:BA6TJRI3","schema_version":"1.0","canonical_sha256":"083d34c51b62d1474ab8658b9bd6dcbb847361f607867af72a8263914a73b545","source":{"kind":"arxiv","id":"2401.02938","version":2},"attestation_state":"computed","paper":{"title":"Fast and Effective Weight Update for Pruned Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Vladim\\'ir Bo\\v{z}a","submitted_at":"2024-01-01T23:10:23Z","abstract_excerpt":"Pruning large language models (LLMs) is a challenging task due to their enormous size. The primary difficulty is fine-tuning the model after pruning, which is needed to recover the lost performance caused by dropping weights. Recent approaches have either ignored fine-tuning entirely, focusing on efficient pruning criteria, or attempted layer-wise weight updates, preserving the behavior of each layer. However, even layer-wise weight updates can be costly for LLMs, and previous works have resorted to various approximations.\n  In our paper, we propose a fast and effective weight update algorithm"},"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":"2401.02938","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T23:10:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a6c0e73fff97513fef2e09ce5179cbabf5ea72953d1a11e5389fa70ee27c0d93","abstract_canon_sha256":"6a2993b82efa628869923c80c3238e9d6809be46a484ff37daf0d4e0f828649f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:52.527727Z","signature_b64":"xPuJ2V39vyOuQjat9feTfQhMOshrfjXGfVOj96z+oMGHdtaF/aFHd97QOoADwWxsepH5PAUg31x3w3MgcuCnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"083d34c51b62d1474ab8658b9bd6dcbb847361f607867af72a8263914a73b545","last_reissued_at":"2026-07-05T08:46:52.527248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:52.527248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Effective Weight Update for Pruned Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Vladim\\'ir Bo\\v{z}a","submitted_at":"2024-01-01T23:10:23Z","abstract_excerpt":"Pruning large language models (LLMs) is a challenging task due to their enormous size. The primary difficulty is fine-tuning the model after pruning, which is needed to recover the lost performance caused by dropping weights. Recent approaches have either ignored fine-tuning entirely, focusing on efficient pruning criteria, or attempted layer-wise weight updates, preserving the behavior of each layer. However, even layer-wise weight updates can be costly for LLMs, and previous works have resorted to various approximations.\n  In our paper, we propose a fast and effective weight update algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02938","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/2401.02938/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":"2401.02938","created_at":"2026-07-05T08:46:52.527307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02938v2","created_at":"2026-07-05T08:46:52.527307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02938","created_at":"2026-07-05T08:46:52.527307+00:00"},{"alias_kind":"pith_short_12","alias_value":"BA6TJRI3MLIU","created_at":"2026-07-05T08:46:52.527307+00:00"},{"alias_kind":"pith_short_16","alias_value":"BA6TJRI3MLIUOSVY","created_at":"2026-07-05T08:46:52.527307+00:00"},{"alias_kind":"pith_short_8","alias_value":"BA6TJRI3","created_at":"2026-07-05T08:46:52.527307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01544","citing_title":"CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient Search","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17289","citing_title":"LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17289","citing_title":"LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11222","citing_title":"ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO","json":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO.json","graph_json":"https://pith.science/api/pith-number/BA6TJRI3MLIUOSVYMWFZXVW4XO/graph.json","events_json":"https://pith.science/api/pith-number/BA6TJRI3MLIUOSVYMWFZXVW4XO/events.json","paper":"https://pith.science/paper/BA6TJRI3"},"agent_actions":{"view_html":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO","download_json":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO.json","view_paper":"https://pith.science/paper/BA6TJRI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02938&json=true","fetch_graph":"https://pith.science/api/pith-number/BA6TJRI3MLIUOSVYMWFZXVW4XO/graph.json","fetch_events":"https://pith.science/api/pith-number/BA6TJRI3MLIUOSVYMWFZXVW4XO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/action/storage_attestation","attest_author":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/action/author_attestation","sign_citation":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/action/citation_signature","submit_replication":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/action/replication_record"}},"created_at":"2026-07-05T08:46:52.527307+00:00","updated_at":"2026-07-05T08:46:52.527307+00:00"}