{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IMS34KDQ7557O6ZYJE2BKXIBH4","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":"2665dfd95c139217881dc1402107b5ded008b3d259d07fe1b6c2f4bf16c16ff7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T18:28:38Z","title_canon_sha256":"62c22d83cc6ea112921536f0a2332706cc53d51d9ba2057b80be9a2223000ae0"},"schema_version":"1.0","source":{"id":"2310.06927","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06927","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06927v2","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06927","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"IMS34KDQ7557","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_16","alias_value":"IMS34KDQ7557O6ZY","created_at":"2026-07-05T07:00:29Z"},{"alias_kind":"pith_short_8","alias_value":"IMS34KDQ","created_at":"2026-07-05T07:00:29Z"}],"graph_snapshots":[{"event_id":"sha256:a8de4eee77fdf68ec01c4f89a55c568e77b257c5f48138ca2d71ccc9888d1817","target":"graph","created_at":"2026-07-05T07:00:29Z","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/2310.06927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard loss-based fine-tuning may fail to recover accuracy, especially at high sparsities. To address this, we perform a detailed study of distillation-type losses, determining an L2-based distillation approach we term SquareHead which enables accurate recovery even at higher sparsities, across all model types. On the practical efficiency side, we show that sparse LLMs","authors_text":"Dan Alistarh, Denis Kuznedelev, Eldar Kurtic, Elias Frantar, Michael Goin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T18:28:38Z","title":"Sparse Fine-tuning for Inference Acceleration of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06927","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:ba899755aa4330240e1d509fe99bc5994bcc9653ba5e99a873162d504b3ba6b0","target":"record","created_at":"2026-07-05T07:00:29Z","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":"2665dfd95c139217881dc1402107b5ded008b3d259d07fe1b6c2f4bf16c16ff7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T18:28:38Z","title_canon_sha256":"62c22d83cc6ea112921536f0a2332706cc53d51d9ba2057b80be9a2223000ae0"},"schema_version":"1.0","source":{"id":"2310.06927","kind":"arxiv","version":2}},"canonical_sha256":"4325be2870ff7bf77b384934155d013f347f154c6039b5799f3d9ab997332589","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4325be2870ff7bf77b384934155d013f347f154c6039b5799f3d9ab997332589","first_computed_at":"2026-07-05T07:00:29.698372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:29.698372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f40UH/mNHcdYCs3RqUtDWUNJ/J9iQbikavR7V6ABhF3Hb+iJFecVg0PVpyZXNSmq8AP8Esr6SieDoH2LWeigAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:29.698790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06927","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba899755aa4330240e1d509fe99bc5994bcc9653ba5e99a873162d504b3ba6b0","sha256:a8de4eee77fdf68ec01c4f89a55c568e77b257c5f48138ca2d71ccc9888d1817"],"state_sha256":"58452f0603c4041444fefd546411bfbd8a5c46098f9b30c42fd26510a133c040"}