{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IUEJN5VULTI6EGF4FQQKAGA3GS","short_pith_number":"pith:IUEJN5VU","schema_version":"1.0","canonical_sha256":"450896f6b45cd1e218bc2c20a0181b348b8b8aa60f8722675e1f10e99f4004a9","source":{"kind":"arxiv","id":"2402.11700","version":2},"attestation_state":"computed","paper":{"title":"Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bolei Ma, Ercong Nie, Michael F\\\"arber, Shuzhou Yuan","submitted_at":"2024-02-18T20:47:10Z","abstract_excerpt":"Large Language Models (LLMs) possess outstanding capabilities in addressing various natural language processing (NLP) tasks. However, the sheer size of these models poses challenges in terms of storage, training and inference due to the inclusion of billions of parameters through layer stacking. While traditional approaches such as model pruning or distillation offer ways for reducing model size, they often come at the expense of performance retention. In our investigation, we systematically explore the approach of reducing the number of layers in LLMs. Surprisingly, we observe that even with "},"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":"2402.11700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T20:47:10Z","cross_cats_sorted":[],"title_canon_sha256":"6ceefd44291f24be0fb789e589de5b4b1052acea64bd81eb498f6717a2049e66","abstract_canon_sha256":"7e7208620e0081923ebc1722308e6d36770c1913b10e93a6bd8d10b5aceb097b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:07.808616Z","signature_b64":"97J5OszdwRhNCXNu4Ws9uKOq83w53L/n8TpQeMKWUXWr4JZzCm3voaJ/0YGeijHLP7loUJ+kahp6FTG1mRlBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"450896f6b45cd1e218bc2c20a0181b348b8b8aa60f8722675e1f10e99f4004a9","last_reissued_at":"2026-07-05T10:50:07.808218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:07.808218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bolei Ma, Ercong Nie, Michael F\\\"arber, Shuzhou Yuan","submitted_at":"2024-02-18T20:47:10Z","abstract_excerpt":"Large Language Models (LLMs) possess outstanding capabilities in addressing various natural language processing (NLP) tasks. However, the sheer size of these models poses challenges in terms of storage, training and inference due to the inclusion of billions of parameters through layer stacking. While traditional approaches such as model pruning or distillation offer ways for reducing model size, they often come at the expense of performance retention. In our investigation, we systematically explore the approach of reducing the number of layers in LLMs. Surprisingly, we observe that even with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11700","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/2402.11700/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":"2402.11700","created_at":"2026-07-05T10:50:07.808272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11700v2","created_at":"2026-07-05T10:50:07.808272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11700","created_at":"2026-07-05T10:50:07.808272+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUEJN5VULTI6","created_at":"2026-07-05T10:50:07.808272+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUEJN5VULTI6EGF4","created_at":"2026-07-05T10:50:07.808272+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUEJN5VU","created_at":"2026-07-05T10:50:07.808272+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/IUEJN5VULTI6EGF4FQQKAGA3GS","json":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS.json","graph_json":"https://pith.science/api/pith-number/IUEJN5VULTI6EGF4FQQKAGA3GS/graph.json","events_json":"https://pith.science/api/pith-number/IUEJN5VULTI6EGF4FQQKAGA3GS/events.json","paper":"https://pith.science/paper/IUEJN5VU"},"agent_actions":{"view_html":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS","download_json":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS.json","view_paper":"https://pith.science/paper/IUEJN5VU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11700&json=true","fetch_graph":"https://pith.science/api/pith-number/IUEJN5VULTI6EGF4FQQKAGA3GS/graph.json","fetch_events":"https://pith.science/api/pith-number/IUEJN5VULTI6EGF4FQQKAGA3GS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/action/storage_attestation","attest_author":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/action/author_attestation","sign_citation":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/action/citation_signature","submit_replication":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/action/replication_record"}},"created_at":"2026-07-05T10:50:07.808272+00:00","updated_at":"2026-07-05T10:50:07.808272+00:00"}