{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O22F5HK3KVJIVFBKB2XNW4U776","short_pith_number":"pith:O22F5HK3","canonical_record":{"source":{"id":"2402.14800","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:56:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"feb735e9fd7e62b2883c24dce648267d9c1a4bc68fd77346e9f6a62cccbef930","abstract_canon_sha256":"37de7c1b5605434722e80a9cde42ad824871563555820b545086abb6456e7cc2"},"schema_version":"1.0"},"canonical_sha256":"76b45e9d5b55528a942a0eaedb729fff8ce0bab57e8a8ab9ae7a8a4ad164e9de","source":{"kind":"arxiv","id":"2402.14800","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14800","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14800v2","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14800","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"O22F5HK3KVJI","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"O22F5HK3KVJIVFBK","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"O22F5HK3","created_at":"2026-07-05T08:25:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O22F5HK3KVJIVFBKB2XNW4U776","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14800","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:56:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"feb735e9fd7e62b2883c24dce648267d9c1a4bc68fd77346e9f6a62cccbef930","abstract_canon_sha256":"37de7c1b5605434722e80a9cde42ad824871563555820b545086abb6456e7cc2"},"schema_version":"1.0"},"canonical_sha256":"76b45e9d5b55528a942a0eaedb729fff8ce0bab57e8a8ab9ae7a8a4ad164e9de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:00.947941Z","signature_b64":"j50/IvYYGutea2N8RMZf324J5NK27wCtiICTcBdtIn4qe74f5mnMhmG+o42hJE8dVnM1IU4uHb1OKYaoqpdeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76b45e9d5b55528a942a0eaedb729fff8ce0bab57e8a8ab9ae7a8a4ad164e9de","last_reissued_at":"2026-07-05T08:25:00.947460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:00.947460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14800","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":"2026-07-05T08:25:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BRQ68n7vPqql6U1aMhvR+6OeQj8Yh8g3Qcso3Y1ikVwGexAa/7qSwrZS6BeKVbvAsBFLqV86cdNWzYnBIdbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:19:07.215130Z"},"content_sha256":"a1022cc4977ecd180ad8cfe89a5751f5ff5a03f88ef7c68418f4de8ef13e3906","schema_version":"1.0","event_id":"sha256:a1022cc4977ecd180ad8cfe89a5751f5ff5a03f88ef7c68418f4de8ef13e3906"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O22F5HK3KVJIVFBKB2XNW4U776","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aojun Zhou, Bo Zhang, Hongsheng Li, Junchi Yan, Qi Liu, Siyuan Huang, Xudong Lu, Yuhui Xu","submitted_at":"2024-02-22T18:56:07Z","abstract_excerpt":"A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. Different from previous weight pruning methods that rely on specifically designed hardware, this paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques. Specifically, we propose, for the first time to our best knowledge, post-tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14800","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/2402.14800/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":"2026-07-05T08:25:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+WSWSM9cuWFZKoRpu1X1FDSPzZCHyhGwO8b3m0jNuYQBeZswZNEupSOpY3PhS+8PB5c55cy6rExZLausc6OBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:19:07.215980Z"},"content_sha256":"6bfc621ab03581dae4df82915b67c686198e3b31d4b24bc4f9b4a13d08c10ffa","schema_version":"1.0","event_id":"sha256:6bfc621ab03581dae4df82915b67c686198e3b31d4b24bc4f9b4a13d08c10ffa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O22F5HK3KVJIVFBKB2XNW4U776/bundle.json","state_url":"https://pith.science/pith/O22F5HK3KVJIVFBKB2XNW4U776/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O22F5HK3KVJIVFBKB2XNW4U776/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":"2026-08-05T12:19:07Z","links":{"resolver":"https://pith.science/pith/O22F5HK3KVJIVFBKB2XNW4U776","bundle":"https://pith.science/pith/O22F5HK3KVJIVFBKB2XNW4U776/bundle.json","state":"https://pith.science/pith/O22F5HK3KVJIVFBKB2XNW4U776/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O22F5HK3KVJIVFBKB2XNW4U776/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O22F5HK3KVJIVFBKB2XNW4U776","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":"37de7c1b5605434722e80a9cde42ad824871563555820b545086abb6456e7cc2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:56:07Z","title_canon_sha256":"feb735e9fd7e62b2883c24dce648267d9c1a4bc68fd77346e9f6a62cccbef930"},"schema_version":"1.0","source":{"id":"2402.14800","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14800","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14800v2","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14800","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"O22F5HK3KVJI","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"O22F5HK3KVJIVFBK","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"O22F5HK3","created_at":"2026-07-05T08:25:00Z"}],"graph_snapshots":[{"event_id":"sha256:6bfc621ab03581dae4df82915b67c686198e3b31d4b24bc4f9b4a13d08c10ffa","target":"graph","created_at":"2026-07-05T08:25:00Z","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/2402.14800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. Different from previous weight pruning methods that rely on specifically designed hardware, this paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques. Specifically, we propose, for the first time to our best knowledge, post-tr","authors_text":"Aojun Zhou, Bo Zhang, Hongsheng Li, Junchi Yan, Qi Liu, Siyuan Huang, Xudong Lu, Yuhui Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:56:07Z","title":"Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14800","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:a1022cc4977ecd180ad8cfe89a5751f5ff5a03f88ef7c68418f4de8ef13e3906","target":"record","created_at":"2026-07-05T08:25:00Z","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":"37de7c1b5605434722e80a9cde42ad824871563555820b545086abb6456e7cc2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:56:07Z","title_canon_sha256":"feb735e9fd7e62b2883c24dce648267d9c1a4bc68fd77346e9f6a62cccbef930"},"schema_version":"1.0","source":{"id":"2402.14800","kind":"arxiv","version":2}},"canonical_sha256":"76b45e9d5b55528a942a0eaedb729fff8ce0bab57e8a8ab9ae7a8a4ad164e9de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76b45e9d5b55528a942a0eaedb729fff8ce0bab57e8a8ab9ae7a8a4ad164e9de","first_computed_at":"2026-07-05T08:25:00.947460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:00.947460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j50/IvYYGutea2N8RMZf324J5NK27wCtiICTcBdtIn4qe74f5mnMhmG+o42hJE8dVnM1IU4uHb1OKYaoqpdeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:00.947941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14800","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1022cc4977ecd180ad8cfe89a5751f5ff5a03f88ef7c68418f4de8ef13e3906","sha256:6bfc621ab03581dae4df82915b67c686198e3b31d4b24bc4f9b4a13d08c10ffa"],"state_sha256":"ff565885ccd2836514125e52e0c5029427e1ddda1ca8a979f60632587fcae59d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMIM6+SOluIUt4Lz9RZ9q1mw540m/WfKf7nVYFxYv8a7pAOioCu8CosdHatr58aEQKFZdG9CZgEdJu/Fzu1VBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:19:07.221225Z","bundle_sha256":"85cfea5d5ad177044359e403c51a0c444cbf46356eba08bc72549cee319b244f"}}