{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NHJIJCYRFPCXACZFYAKE4R5ENO","short_pith_number":"pith:NHJIJCYR","canonical_record":{"source":{"id":"2402.16880","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T12:44:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"46d452ba55eeb5a19aecabd0cb271ac4d7386e9415e2ef5c6a90f668314b5721","abstract_canon_sha256":"281ff48b66c8c1337bd60ef81d484a9d825c4c445b692d9aa3c8690af06dd69a"},"schema_version":"1.0"},"canonical_sha256":"69d2848b112bc5700b25c0144e47a46b9c5da093f28df21860dddd87a877258c","source":{"kind":"arxiv","id":"2402.16880","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16880","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16880v2","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16880","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"NHJIJCYRFPCX","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"NHJIJCYRFPCXACZF","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"NHJIJCYR","created_at":"2026-07-05T08:09:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NHJIJCYRFPCXACZFYAKE4R5ENO","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16880","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T12:44:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"46d452ba55eeb5a19aecabd0cb271ac4d7386e9415e2ef5c6a90f668314b5721","abstract_canon_sha256":"281ff48b66c8c1337bd60ef81d484a9d825c4c445b692d9aa3c8690af06dd69a"},"schema_version":"1.0"},"canonical_sha256":"69d2848b112bc5700b25c0144e47a46b9c5da093f28df21860dddd87a877258c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:48.662106Z","signature_b64":"PC01iTBJwdO6Fb+D3hiWrJWcWk2mMQwDDSnokiEz2lRKnkOexHGzPLbbcbK4CheZJigCvccAqhLevrmYZvsPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69d2848b112bc5700b25c0144e47a46b9c5da093f28df21860dddd87a877258c","last_reissued_at":"2026-07-05T08:09:48.661595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:48.661595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16880","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":"2026-07-05T08:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tYhV7TJZm1ghamE5F4egr2tw/wtPLSwDxZSxLilx6GxDGckoPBg7zp3SnnUWmhmylhXJxNSiD+asb6R2YCleAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:38:45.909791Z"},"content_sha256":"3da2a3376fbf280b9f3c805fe0b8805a6f5b2971d4aa7c83f8f95ed9f7b3734b","schema_version":"1.0","event_id":"sha256:3da2a3376fbf280b9f3c805fe0b8805a6f5b2971d4aa7c83f8f95ed9f7b3734b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NHJIJCYRFPCXACZFYAKE4R5ENO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Fengwei An, Kaipeng Zhang, Mengzhao Chen, Peng Gao, Peng Xu, Ping Luo, Shitao Tang, Wenqi Shao, Yu Qiao","submitted_at":"2024-02-18T12:44:15Z","abstract_excerpt":"Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. While their performance is impressive, the computational footprint due to their vast number of parameters can be prohibitive. Existing solutions such as SparseGPT and Wanda attempt to alleviate this issue through weight pruning. However, their layer-wise approach results in significant perturbation to the model's output and requires meticulous hyperparameter tuning, such as the pruning rate, which can adversely affect overall model performance. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16880","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/2402.16880/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":"2026-07-05T08:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGOZqdkL3nHlWEANFhLsreUHZUcZNp8A9oeJ5IZ1pROiY4HSDOHGRWVYCCamdodcY6O95PzHz1Fi3dWMI5coAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:38:45.910159Z"},"content_sha256":"ce4f4ce79b093818183cf508016dbb05db7c9131a7a3dd4fa4b37a70ebf201c9","schema_version":"1.0","event_id":"sha256:ce4f4ce79b093818183cf508016dbb05db7c9131a7a3dd4fa4b37a70ebf201c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHJIJCYRFPCXACZFYAKE4R5ENO/bundle.json","state_url":"https://pith.science/pith/NHJIJCYRFPCXACZFYAKE4R5ENO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHJIJCYRFPCXACZFYAKE4R5ENO/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":"2026-07-07T08:38:45Z","links":{"resolver":"https://pith.science/pith/NHJIJCYRFPCXACZFYAKE4R5ENO","bundle":"https://pith.science/pith/NHJIJCYRFPCXACZFYAKE4R5ENO/bundle.json","state":"https://pith.science/pith/NHJIJCYRFPCXACZFYAKE4R5ENO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHJIJCYRFPCXACZFYAKE4R5ENO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NHJIJCYRFPCXACZFYAKE4R5ENO","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":"281ff48b66c8c1337bd60ef81d484a9d825c4c445b692d9aa3c8690af06dd69a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T12:44:15Z","title_canon_sha256":"46d452ba55eeb5a19aecabd0cb271ac4d7386e9415e2ef5c6a90f668314b5721"},"schema_version":"1.0","source":{"id":"2402.16880","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16880","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16880v2","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16880","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"NHJIJCYRFPCX","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"NHJIJCYRFPCXACZF","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"NHJIJCYR","created_at":"2026-07-05T08:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:ce4f4ce79b093818183cf508016dbb05db7c9131a7a3dd4fa4b37a70ebf201c9","target":"graph","created_at":"2026-07-05T08:09:48Z","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/2402.16880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. While their performance is impressive, the computational footprint due to their vast number of parameters can be prohibitive. Existing solutions such as SparseGPT and Wanda attempt to alleviate this issue through weight pruning. However, their layer-wise approach results in significant perturbation to the model's output and requires meticulous hyperparameter tuning, such as the pruning rate, which can adversely affect overall model performance. ","authors_text":"Fengwei An, Kaipeng Zhang, Mengzhao Chen, Peng Gao, Peng Xu, Ping Luo, Shitao Tang, Wenqi Shao, Yu Qiao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T12:44:15Z","title":"BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16880","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":"sha256:3da2a3376fbf280b9f3c805fe0b8805a6f5b2971d4aa7c83f8f95ed9f7b3734b","target":"record","created_at":"2026-07-05T08:09:48Z","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":"281ff48b66c8c1337bd60ef81d484a9d825c4c445b692d9aa3c8690af06dd69a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T12:44:15Z","title_canon_sha256":"46d452ba55eeb5a19aecabd0cb271ac4d7386e9415e2ef5c6a90f668314b5721"},"schema_version":"1.0","source":{"id":"2402.16880","kind":"arxiv","version":2}},"canonical_sha256":"69d2848b112bc5700b25c0144e47a46b9c5da093f28df21860dddd87a877258c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69d2848b112bc5700b25c0144e47a46b9c5da093f28df21860dddd87a877258c","first_computed_at":"2026-07-05T08:09:48.661595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:48.661595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PC01iTBJwdO6Fb+D3hiWrJWcWk2mMQwDDSnokiEz2lRKnkOexHGzPLbbcbK4CheZJigCvccAqhLevrmYZvsPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:48.662106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16880","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3da2a3376fbf280b9f3c805fe0b8805a6f5b2971d4aa7c83f8f95ed9f7b3734b","sha256:ce4f4ce79b093818183cf508016dbb05db7c9131a7a3dd4fa4b37a70ebf201c9"],"state_sha256":"ec08391db061dd4d36df94a46f509aaa9476af32a9d154e63d04dd4ad0a75524"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYNxHc//Dd1wLi5iqspSV6O1TZCbmLtgQv8XS6x2OCyH515Xxcy6unEuBv873dFiwAYBxirY04DhjAkeOCsKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:38:45.912092Z","bundle_sha256":"df8a92aae40907f8e40e37f7581adcf9651ba4b27d240224db0ed789e3a11482"}}