{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BA6TJRI3MLIUOSVYMWFZXVW4XO","short_pith_number":"pith:BA6TJRI3","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"},"canonical_sha256":"083d34c51b62d1474ab8658b9bd6dcbb847361f607867af72a8263914a73b545","source":{"kind":"arxiv","id":"2401.02938","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02938","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02938v2","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02938","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"BA6TJRI3MLIU","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"BA6TJRI3MLIUOSVY","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"BA6TJRI3","created_at":"2026-07-05T08:46:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BA6TJRI3MLIUOSVYMWFZXVW4XO","target":"record","payload":{"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"},"canonical_sha256":"083d34c51b62d1474ab8658b9bd6dcbb847361f607867af72a8263914a73b545","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"},"source_kind":"arxiv","source_id":"2401.02938","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":"2026-07-05T08:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fqEwee0xE3ZbKQVz1zF8L6ZN8bIZIL7SFEoWD8T/WKmN4ZFoi2sr18dIsbsFfouWh+0/3QzlwYk3KSqCEamFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:11:27.478780Z"},"content_sha256":"272f9f055d57ae36c4925f6ecf4344551b9c7403130ac04692d23668b665f928","schema_version":"1.0","event_id":"sha256:272f9f055d57ae36c4925f6ecf4344551b9c7403130ac04692d23668b665f928"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BA6TJRI3MLIUOSVYMWFZXVW4XO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xf2i9VB1vgLVchFvcpLPp8uKJ0xBQvoAcypJLLecknzFhkFSDF+7hAC4tPEJB+8/EmGd/e/8z6MDXZD6mAECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:11:27.479794Z"},"content_sha256":"7c757d6c900b199b3b2d811face053774beaf160517ae49f3ccae603e731eaf3","schema_version":"1.0","event_id":"sha256:7c757d6c900b199b3b2d811face053774beaf160517ae49f3ccae603e731eaf3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/bundle.json","state_url":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/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":"2026-08-11T05:11:27Z","links":{"resolver":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO","bundle":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/bundle.json","state":"https://pith.science/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BA6TJRI3MLIUOSVYMWFZXVW4XO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BA6TJRI3MLIUOSVYMWFZXVW4XO","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":"6a2993b82efa628869923c80c3238e9d6809be46a484ff37daf0d4e0f828649f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T23:10:23Z","title_canon_sha256":"a6c0e73fff97513fef2e09ce5179cbabf5ea72953d1a11e5389fa70ee27c0d93"},"schema_version":"1.0","source":{"id":"2401.02938","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02938","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02938v2","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02938","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"BA6TJRI3MLIU","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"BA6TJRI3MLIUOSVY","created_at":"2026-07-05T08:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"BA6TJRI3","created_at":"2026-07-05T08:46:52Z"}],"graph_snapshots":[{"event_id":"sha256:7c757d6c900b199b3b2d811face053774beaf160517ae49f3ccae603e731eaf3","target":"graph","created_at":"2026-07-05T08:46:52Z","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/2401.02938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Vladim\\'ir Bo\\v{z}a","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T23:10:23Z","title":"Fast and Effective Weight Update for Pruned Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02938","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":"sha256:272f9f055d57ae36c4925f6ecf4344551b9c7403130ac04692d23668b665f928","target":"record","created_at":"2026-07-05T08:46:52Z","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":"6a2993b82efa628869923c80c3238e9d6809be46a484ff37daf0d4e0f828649f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T23:10:23Z","title_canon_sha256":"a6c0e73fff97513fef2e09ce5179cbabf5ea72953d1a11e5389fa70ee27c0d93"},"schema_version":"1.0","source":{"id":"2401.02938","kind":"arxiv","version":2}},"canonical_sha256":"083d34c51b62d1474ab8658b9bd6dcbb847361f607867af72a8263914a73b545","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"083d34c51b62d1474ab8658b9bd6dcbb847361f607867af72a8263914a73b545","first_computed_at":"2026-07-05T08:46:52.527248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:52.527248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xPuJ2V39vyOuQjat9feTfQhMOshrfjXGfVOj96z+oMGHdtaF/aFHd97QOoADwWxsepH5PAUg31x3w3MgcuCnDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:52.527727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02938","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:272f9f055d57ae36c4925f6ecf4344551b9c7403130ac04692d23668b665f928","sha256:7c757d6c900b199b3b2d811face053774beaf160517ae49f3ccae603e731eaf3"],"state_sha256":"fb87cb99b9bdb5e6b9808f3e3f40f67cda75cf355b2886b3325d4a35fba423fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zSjsET4G+1Wl2pYgTF3l8Tm5zbkMxRJ/ALwmCTB01TUHwJL2WItWnUBCxyRptfR1AqDLZ2aNeF7oRCI+CcLUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:11:27.486839Z","bundle_sha256":"35ff77b79310eda317c1e247a423e587c68c7eb567346f476080d54f490af8e9"}}