{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MEF5PYBHQ75GIMQR6LPO4XBCTN","short_pith_number":"pith:MEF5PYBH","canonical_record":{"source":{"id":"2411.15708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-24T04:26:04Z","cross_cats_sorted":[],"title_canon_sha256":"c5272a1e31a7ab48c7a6cb9a870bce3e4f6fb01895b279a6034dde731a65d981","abstract_canon_sha256":"eadc5054343002e63027c2d0a40e8999a671d33dc9c8207995a91b996ba8c51d"},"schema_version":"1.0"},"canonical_sha256":"610bd7e02787fa643211f2deee5c229b4475ed6b16cb7d7f0d3bc58988e4c4e3","source":{"kind":"arxiv","id":"2411.15708","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15708","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15708v1","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15708","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"MEF5PYBHQ75G","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"MEF5PYBHQ75GIMQR","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"MEF5PYBH","created_at":"2026-07-05T09:39:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MEF5PYBHQ75GIMQR6LPO4XBCTN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-24T04:26:04Z","cross_cats_sorted":[],"title_canon_sha256":"c5272a1e31a7ab48c7a6cb9a870bce3e4f6fb01895b279a6034dde731a65d981","abstract_canon_sha256":"eadc5054343002e63027c2d0a40e8999a671d33dc9c8207995a91b996ba8c51d"},"schema_version":"1.0"},"canonical_sha256":"610bd7e02787fa643211f2deee5c229b4475ed6b16cb7d7f0d3bc58988e4c4e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:39.700804Z","signature_b64":"QqP/KereAPvnkjvc077gZp1Qy3RLkHZOU/2TiN9kCDkLZRMJEDrWNHHRG3suyiTjtd7y36bqSO2YSCj09ceCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"610bd7e02787fa643211f2deee5c229b4475ed6b16cb7d7f0d3bc58988e4c4e3","last_reissued_at":"2026-07-05T09:39:39.700267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:39.700267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15708","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"07DmqNh3+gyGsPtrZh0XBo6IsblqfRPCzXuPO3Ul9vz1MviTBTKTYdzA+RtjWqz3myrt64BHlp0HWQS8wwItBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:11:36.170920Z"},"content_sha256":"6d0a2aca3771f1b4584ab057039e7eefe707d4473bdad3a7d5b7e725668ace9d","schema_version":"1.0","event_id":"sha256:6d0a2aca3771f1b4584ab057039e7eefe707d4473bdad3a7d5b7e725668ace9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MEF5PYBHQ75GIMQR6LPO4XBCTN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daize Dong, Tong Zhu, Weigao Sun, Xiaoye Qu, Xuyang Hu, Yu Cheng","submitted_at":"2024-11-24T04:26:04Z","abstract_excerpt":"Recently, inspired by the concept of sparsity, Mixture-of-Experts (MoE) models have gained increasing popularity for scaling model size while keeping the number of activated parameters constant. In this study, we thoroughly investigate the sparsity of the dense LLaMA model by constructing MoE for both the attention (i.e., Attention MoE) and MLP (i.e., MLP MoE) modules in the transformer blocks. Specifically, we investigate different expert construction methods and granularities under the same activation conditions to analyze the impact of sparsifying the model. Additionally, to comprehensively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15708","kind":"arxiv","version":1},"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/2411.15708/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":"2026-07-05T09:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mQev+G/73PO/tyjyr0iuBEtZsxeUsJEsbYceJnHfQr0bJMZYxEjqRdglslT148f+rUlUEQG9rBPitIhlpUtoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:11:36.171411Z"},"content_sha256":"d74a5380afaf7a47e2ec381ea1d4dedad6227978353dc231770a38a3baa782e4","schema_version":"1.0","event_id":"sha256:d74a5380afaf7a47e2ec381ea1d4dedad6227978353dc231770a38a3baa782e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MEF5PYBHQ75GIMQR6LPO4XBCTN/bundle.json","state_url":"https://pith.science/pith/MEF5PYBHQ75GIMQR6LPO4XBCTN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MEF5PYBHQ75GIMQR6LPO4XBCTN/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":"2026-08-10T10:11:36Z","links":{"resolver":"https://pith.science/pith/MEF5PYBHQ75GIMQR6LPO4XBCTN","bundle":"https://pith.science/pith/MEF5PYBHQ75GIMQR6LPO4XBCTN/bundle.json","state":"https://pith.science/pith/MEF5PYBHQ75GIMQR6LPO4XBCTN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MEF5PYBHQ75GIMQR6LPO4XBCTN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MEF5PYBHQ75GIMQR6LPO4XBCTN","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":"eadc5054343002e63027c2d0a40e8999a671d33dc9c8207995a91b996ba8c51d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-24T04:26:04Z","title_canon_sha256":"c5272a1e31a7ab48c7a6cb9a870bce3e4f6fb01895b279a6034dde731a65d981"},"schema_version":"1.0","source":{"id":"2411.15708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15708","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15708v1","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15708","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"MEF5PYBHQ75G","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"MEF5PYBHQ75GIMQR","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"MEF5PYBH","created_at":"2026-07-05T09:39:39Z"}],"graph_snapshots":[{"event_id":"sha256:d74a5380afaf7a47e2ec381ea1d4dedad6227978353dc231770a38a3baa782e4","target":"graph","created_at":"2026-07-05T09:39:39Z","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/2411.15708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, inspired by the concept of sparsity, Mixture-of-Experts (MoE) models have gained increasing popularity for scaling model size while keeping the number of activated parameters constant. In this study, we thoroughly investigate the sparsity of the dense LLaMA model by constructing MoE for both the attention (i.e., Attention MoE) and MLP (i.e., MLP MoE) modules in the transformer blocks. Specifically, we investigate different expert construction methods and granularities under the same activation conditions to analyze the impact of sparsifying the model. Additionally, to comprehensively","authors_text":"Daize Dong, Tong Zhu, Weigao Sun, Xiaoye Qu, Xuyang Hu, Yu Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-24T04:26:04Z","title":"LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15708","kind":"arxiv","version":1},"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":"sha256:6d0a2aca3771f1b4584ab057039e7eefe707d4473bdad3a7d5b7e725668ace9d","target":"record","created_at":"2026-07-05T09:39:39Z","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":"eadc5054343002e63027c2d0a40e8999a671d33dc9c8207995a91b996ba8c51d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-24T04:26:04Z","title_canon_sha256":"c5272a1e31a7ab48c7a6cb9a870bce3e4f6fb01895b279a6034dde731a65d981"},"schema_version":"1.0","source":{"id":"2411.15708","kind":"arxiv","version":1}},"canonical_sha256":"610bd7e02787fa643211f2deee5c229b4475ed6b16cb7d7f0d3bc58988e4c4e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"610bd7e02787fa643211f2deee5c229b4475ed6b16cb7d7f0d3bc58988e4c4e3","first_computed_at":"2026-07-05T09:39:39.700267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:39.700267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QqP/KereAPvnkjvc077gZp1Qy3RLkHZOU/2TiN9kCDkLZRMJEDrWNHHRG3suyiTjtd7y36bqSO2YSCj09ceCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:39.700804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d0a2aca3771f1b4584ab057039e7eefe707d4473bdad3a7d5b7e725668ace9d","sha256:d74a5380afaf7a47e2ec381ea1d4dedad6227978353dc231770a38a3baa782e4"],"state_sha256":"2d864f3e044472d784e68ca2107298eefdc97a381c4ffbdbfc9c3e58d12b43a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jaNnu6gzpNN6vJhEzSj4UH329wBcpk+grAmBKueqJLw7dfPpVIx46e2h71CqDwaf67n/zGvmGn7q3Wl+kz27DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:11:36.175763Z","bundle_sha256":"7b77595f9f986798839ffbef26a557c58a044a11a2024a418bf161750a3844f9"}}