{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q6RRYL5IQDCKNONB2AVJCXZH7N","short_pith_number":"pith:Q6RRYL5I","canonical_record":{"source":{"id":"2411.01016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T20:37:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a60e7037ebd41932a1e93f55a1e004b78c0e978205d2f8856e317f850c1d91e","abstract_canon_sha256":"c703a89f884bc637ff26ddc654d0f78b7c27b987905ee5c49f00f066f7b22fbf"},"schema_version":"1.0"},"canonical_sha256":"87a31c2fa880c4a6b9a1d02a915f27fb4a9eb03e0a61cbbbb4ded39964d9f0c6","source":{"kind":"arxiv","id":"2411.01016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01016","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01016v1","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01016","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"Q6RRYL5IQDCK","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"pith_short_16","alias_value":"Q6RRYL5IQDCKNONB","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"pith_short_8","alias_value":"Q6RRYL5I","created_at":"2026-07-05T09:29:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q6RRYL5IQDCKNONB2AVJCXZH7N","target":"record","payload":{"canonical_record":{"source":{"id":"2411.01016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T20:37:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a60e7037ebd41932a1e93f55a1e004b78c0e978205d2f8856e317f850c1d91e","abstract_canon_sha256":"c703a89f884bc637ff26ddc654d0f78b7c27b987905ee5c49f00f066f7b22fbf"},"schema_version":"1.0"},"canonical_sha256":"87a31c2fa880c4a6b9a1d02a915f27fb4a9eb03e0a61cbbbb4ded39964d9f0c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:54.162877Z","signature_b64":"/fR20agDjqbidTTFUbTpqJGeLRhBV7z/h0UkocA2xtcwJJaD7cMbBmD1psZv44ceiU4kcpFX1YzVmWbwmIX1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87a31c2fa880c4a6b9a1d02a915f27fb4a9eb03e0a61cbbbb4ded39964d9f0c6","last_reissued_at":"2026-07-05T09:29:54.162394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:54.162394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.01016","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":"2026-07-05T09:29:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ie7UXB+RecNP+zihYQb8ELRMEVEOsdwyxxddt41PY+FGML4qcobbPoai4JNB1uIGykhce7Hv/l7fFt6Uo/9qBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:33:20.831839Z"},"content_sha256":"ef1a0c8cee5db8e35ffbf1b6da5f904e7d35df78cd6c5113e82f0fa88a8aa89b","schema_version":"1.0","event_id":"sha256:ef1a0c8cee5db8e35ffbf1b6da5f904e7d35df78cd6c5113e82f0fa88a8aa89b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q6RRYL5IQDCKNONB2AVJCXZH7N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Cheng Yang, Jinqi Xiao, Lingyi Huang, Miao Yin, Wenqi Jia, Yang Sui, Yuanlin Duan, Yu Cheng, Yu Gong","submitted_at":"2024-11-01T20:37:58Z","abstract_excerpt":"The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer activated parameters. Despite this efficiency, their enormous parameter size still leads to high deployment costs. In this paper, we introduce a two-stage compression method tailored for MoE to reduce the model size and decrease the computational cost. First, in the inter-expert pruning stage, we analyze the importance of each layer and propose the Layer-wise Genet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01016","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/2411.01016/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":"2026-07-05T09:29:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OPOd6zdkFw+MCcH+ud0t8pYRYtpwP091ZUvs+jYngL9llcMvT1T4DckCGbelWpE9D5Fj0LizRayLBqgahtQqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:33:20.832863Z"},"content_sha256":"d905f01f81b823407f4c022cc8631fa283b4d6d0dbe8ae7122c2f61f047a19d8","schema_version":"1.0","event_id":"sha256:d905f01f81b823407f4c022cc8631fa283b4d6d0dbe8ae7122c2f61f047a19d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6RRYL5IQDCKNONB2AVJCXZH7N/bundle.json","state_url":"https://pith.science/pith/Q6RRYL5IQDCKNONB2AVJCXZH7N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6RRYL5IQDCKNONB2AVJCXZH7N/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":"2026-08-07T18:33:20Z","links":{"resolver":"https://pith.science/pith/Q6RRYL5IQDCKNONB2AVJCXZH7N","bundle":"https://pith.science/pith/Q6RRYL5IQDCKNONB2AVJCXZH7N/bundle.json","state":"https://pith.science/pith/Q6RRYL5IQDCKNONB2AVJCXZH7N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6RRYL5IQDCKNONB2AVJCXZH7N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q6RRYL5IQDCKNONB2AVJCXZH7N","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":"c703a89f884bc637ff26ddc654d0f78b7c27b987905ee5c49f00f066f7b22fbf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T20:37:58Z","title_canon_sha256":"5a60e7037ebd41932a1e93f55a1e004b78c0e978205d2f8856e317f850c1d91e"},"schema_version":"1.0","source":{"id":"2411.01016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01016","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01016v1","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01016","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"Q6RRYL5IQDCK","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"pith_short_16","alias_value":"Q6RRYL5IQDCKNONB","created_at":"2026-07-05T09:29:54Z"},{"alias_kind":"pith_short_8","alias_value":"Q6RRYL5I","created_at":"2026-07-05T09:29:54Z"}],"graph_snapshots":[{"event_id":"sha256:d905f01f81b823407f4c022cc8631fa283b4d6d0dbe8ae7122c2f61f047a19d8","target":"graph","created_at":"2026-07-05T09:29:54Z","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/2411.01016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer activated parameters. Despite this efficiency, their enormous parameter size still leads to high deployment costs. In this paper, we introduce a two-stage compression method tailored for MoE to reduce the model size and decrease the computational cost. First, in the inter-expert pruning stage, we analyze the importance of each layer and propose the Layer-wise Genet","authors_text":"Bo Yuan, Cheng Yang, Jinqi Xiao, Lingyi Huang, Miao Yin, Wenqi Jia, Yang Sui, Yuanlin Duan, Yu Cheng, Yu Gong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T20:37:58Z","title":"MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01016","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:ef1a0c8cee5db8e35ffbf1b6da5f904e7d35df78cd6c5113e82f0fa88a8aa89b","target":"record","created_at":"2026-07-05T09:29:54Z","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":"c703a89f884bc637ff26ddc654d0f78b7c27b987905ee5c49f00f066f7b22fbf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T20:37:58Z","title_canon_sha256":"5a60e7037ebd41932a1e93f55a1e004b78c0e978205d2f8856e317f850c1d91e"},"schema_version":"1.0","source":{"id":"2411.01016","kind":"arxiv","version":1}},"canonical_sha256":"87a31c2fa880c4a6b9a1d02a915f27fb4a9eb03e0a61cbbbb4ded39964d9f0c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87a31c2fa880c4a6b9a1d02a915f27fb4a9eb03e0a61cbbbb4ded39964d9f0c6","first_computed_at":"2026-07-05T09:29:54.162394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:54.162394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/fR20agDjqbidTTFUbTpqJGeLRhBV7z/h0UkocA2xtcwJJaD7cMbBmD1psZv44ceiU4kcpFX1YzVmWbwmIX1Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:54.162877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef1a0c8cee5db8e35ffbf1b6da5f904e7d35df78cd6c5113e82f0fa88a8aa89b","sha256:d905f01f81b823407f4c022cc8631fa283b4d6d0dbe8ae7122c2f61f047a19d8"],"state_sha256":"88ce2a13460e0e3fa1bf49a1da47e5ad8af02c763aa2bfac9a9aae608181b616"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73nZBYHSwGUVUWwMTQFSw9jaL30GmNLiDtQJXQsKS8oA9dzgjUEK9iHr3PVdxaQ3GKOdRpyR4HrDX0I0oweoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:33:20.840285Z","bundle_sha256":"8f34b8adfd552fce4c838b09ee2f95e2c5a2795d1ad5efd91bdaff8284649c1e"}}