{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VLEYFIMZ2R36XZMLXZQCMN2Q4G","short_pith_number":"pith:VLEYFIMZ","schema_version":"1.0","canonical_sha256":"aac982a199d477ebe58bbe60263750e1b81d05bdadaa0183be186545b8a2abc8","source":{"kind":"arxiv","id":"2312.13547","version":1},"attestation_state":"computed","paper":{"title":"How to Prune Your Language Model: Recovering Accuracy on the \"Sparsity May Cry'' Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Alistarh, Eldar Kurtic, Torsten Hoefler","submitted_at":"2023-12-21T03:11:30Z","abstract_excerpt":"Pruning large language models (LLMs) from the BERT family has emerged as a standard compression benchmark, and several pruning methods have been proposed for this task. The recent ``Sparsity May Cry'' (SMC) benchmark put into question the validity of all existing methods, exhibiting a more complex setup where many known pruning methods appear to fail. We revisit the question of accurate BERT-pruning during fine-tuning on downstream datasets, and propose a set of general guidelines for successful pruning, even on the challenging SMC benchmark. First, we perform a cost-vs-benefits analysis of pr"},"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":"2312.13547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T03:11:30Z","cross_cats_sorted":[],"title_canon_sha256":"96ef400058108177db93f2d71cbd7740e3f02aecab5f813d238286f09bf3aa20","abstract_canon_sha256":"5a0cd849383a7a0900b767db94273530f22e4a22aed8e76df47399b3f3a51033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:46.308402Z","signature_b64":"dGNKDzwQt7bD3zQbtBGltUdllikfho8pCHKuGzS2tJxHBcyoCYHWNllJuJ5pKOJT5ZdGRqwJtl5x8BF1KBE9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac982a199d477ebe58bbe60263750e1b81d05bdadaa0183be186545b8a2abc8","last_reissued_at":"2026-07-05T07:26:46.308065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:46.308065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Prune Your Language Model: Recovering Accuracy on the \"Sparsity May Cry'' Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Alistarh, Eldar Kurtic, Torsten Hoefler","submitted_at":"2023-12-21T03:11:30Z","abstract_excerpt":"Pruning large language models (LLMs) from the BERT family has emerged as a standard compression benchmark, and several pruning methods have been proposed for this task. The recent ``Sparsity May Cry'' (SMC) benchmark put into question the validity of all existing methods, exhibiting a more complex setup where many known pruning methods appear to fail. We revisit the question of accurate BERT-pruning during fine-tuning on downstream datasets, and propose a set of general guidelines for successful pruning, even on the challenging SMC benchmark. First, we perform a cost-vs-benefits analysis of pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13547","kind":"arxiv","version":1},"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/2312.13547/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":"2312.13547","created_at":"2026-07-05T07:26:46.308118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13547v1","created_at":"2026-07-05T07:26:46.308118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13547","created_at":"2026-07-05T07:26:46.308118+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLEYFIMZ2R36","created_at":"2026-07-05T07:26:46.308118+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLEYFIMZ2R36XZML","created_at":"2026-07-05T07:26:46.308118+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLEYFIMZ","created_at":"2026-07-05T07:26:46.308118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09816","citing_title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G","json":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G.json","graph_json":"https://pith.science/api/pith-number/VLEYFIMZ2R36XZMLXZQCMN2Q4G/graph.json","events_json":"https://pith.science/api/pith-number/VLEYFIMZ2R36XZMLXZQCMN2Q4G/events.json","paper":"https://pith.science/paper/VLEYFIMZ"},"agent_actions":{"view_html":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G","download_json":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G.json","view_paper":"https://pith.science/paper/VLEYFIMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13547&json=true","fetch_graph":"https://pith.science/api/pith-number/VLEYFIMZ2R36XZMLXZQCMN2Q4G/graph.json","fetch_events":"https://pith.science/api/pith-number/VLEYFIMZ2R36XZMLXZQCMN2Q4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G/action/storage_attestation","attest_author":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G/action/author_attestation","sign_citation":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G/action/citation_signature","submit_replication":"https://pith.science/pith/VLEYFIMZ2R36XZMLXZQCMN2Q4G/action/replication_record"}},"created_at":"2026-07-05T07:26:46.308118+00:00","updated_at":"2026-07-05T07:26:46.308118+00:00"}