{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IUEJN5VULTI6EGF4FQQKAGA3GS","short_pith_number":"pith:IUEJN5VU","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"},"canonical_sha256":"450896f6b45cd1e218bc2c20a0181b348b8b8aa60f8722675e1f10e99f4004a9","source":{"kind":"arxiv","id":"2402.11700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11700","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11700v2","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11700","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_12","alias_value":"IUEJN5VULTI6","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_16","alias_value":"IUEJN5VULTI6EGF4","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_8","alias_value":"IUEJN5VU","created_at":"2026-07-05T10:50:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IUEJN5VULTI6EGF4FQQKAGA3GS","target":"record","payload":{"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"},"canonical_sha256":"450896f6b45cd1e218bc2c20a0181b348b8b8aa60f8722675e1f10e99f4004a9","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"},"source_kind":"arxiv","source_id":"2402.11700","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ilA/JfH3v4PD9OItd6Pr5EzzoHdLVz9h7PKBvYPBNfbVEpcrOLNKPCgGBluU3V2WMNpAS1U4/mLwVLUDqtF6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:14:42.811279Z"},"content_sha256":"ac2b0dd640317c31ef6d5a694365a338bb344a0fca27e2bf031a39ee5749e252","schema_version":"1.0","event_id":"sha256:ac2b0dd640317c31ef6d5a694365a338bb344a0fca27e2bf031a39ee5749e252"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IUEJN5VULTI6EGF4FQQKAGA3GS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"etuLKwvqXYOJDrKmMxHTfbzWrAMjUDSYq8dVNjCPE8G2YyQtAEP/X7rwg6g1whNxLx3BQEtYVcOhvzfRYE/xCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:14:42.812318Z"},"content_sha256":"a467b9afec166eb2cb582fa3f0734f5679db47b5d904f14d20f9f6064dbe2401","schema_version":"1.0","event_id":"sha256:a467b9afec166eb2cb582fa3f0734f5679db47b5d904f14d20f9f6064dbe2401"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/bundle.json","state_url":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T06:14:42Z","links":{"resolver":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS","bundle":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/bundle.json","state":"https://pith.science/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUEJN5VULTI6EGF4FQQKAGA3GS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IUEJN5VULTI6EGF4FQQKAGA3GS","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":"7e7208620e0081923ebc1722308e6d36770c1913b10e93a6bd8d10b5aceb097b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T20:47:10Z","title_canon_sha256":"6ceefd44291f24be0fb789e589de5b4b1052acea64bd81eb498f6717a2049e66"},"schema_version":"1.0","source":{"id":"2402.11700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11700","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11700v2","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11700","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_12","alias_value":"IUEJN5VULTI6","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_16","alias_value":"IUEJN5VULTI6EGF4","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_8","alias_value":"IUEJN5VU","created_at":"2026-07-05T10:50:07Z"}],"graph_snapshots":[{"event_id":"sha256:a467b9afec166eb2cb582fa3f0734f5679db47b5d904f14d20f9f6064dbe2401","target":"graph","created_at":"2026-07-05T10:50:07Z","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/2402.11700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Bolei Ma, Ercong Nie, Michael F\\\"arber, Shuzhou Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T20:47:10Z","title":"Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11700","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:ac2b0dd640317c31ef6d5a694365a338bb344a0fca27e2bf031a39ee5749e252","target":"record","created_at":"2026-07-05T10:50:07Z","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":"7e7208620e0081923ebc1722308e6d36770c1913b10e93a6bd8d10b5aceb097b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T20:47:10Z","title_canon_sha256":"6ceefd44291f24be0fb789e589de5b4b1052acea64bd81eb498f6717a2049e66"},"schema_version":"1.0","source":{"id":"2402.11700","kind":"arxiv","version":2}},"canonical_sha256":"450896f6b45cd1e218bc2c20a0181b348b8b8aa60f8722675e1f10e99f4004a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"450896f6b45cd1e218bc2c20a0181b348b8b8aa60f8722675e1f10e99f4004a9","first_computed_at":"2026-07-05T10:50:07.808218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:07.808218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"97J5OszdwRhNCXNu4Ws9uKOq83w53L/n8TpQeMKWUXWr4JZzCm3voaJ/0YGeijHLP7loUJ+kahp6FTG1mRlBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:07.808616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac2b0dd640317c31ef6d5a694365a338bb344a0fca27e2bf031a39ee5749e252","sha256:a467b9afec166eb2cb582fa3f0734f5679db47b5d904f14d20f9f6064dbe2401"],"state_sha256":"56e3b26575b864b856502d966955c154098afda9c7de80a67d3daa8ca0f646aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"to2FWbcHKSEZaLAzGyMWTrAbxyYBvkbBnu7K9iIpKnoTkFOF+tNZ+q+D4Pw4/KPaR9w4Vs59FrFZUgZ4QRxsAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:14:42.847476Z","bundle_sha256":"b4ea65bd5618883089497c54a42b2a15357d4ce713636da87fd04cacdadb2b52"}}