{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YAZCFPFMQDBEIH3UG4YH5A4CJB","short_pith_number":"pith:YAZCFPFM","canonical_record":{"source":{"id":"2407.00945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T03:57:35Z","cross_cats_sorted":[],"title_canon_sha256":"126003e00ad1463443b6f4ccbb780165a469441e60709992a75bad0646adc5d7","abstract_canon_sha256":"5e6cc79f841159e1e9c1a50b675105cf88426efd92ef07244051f49d8ca2bd66"},"schema_version":"1.0"},"canonical_sha256":"c03222bcac80c2441f7437307e8382485dddd493e106698c64e2807723d107e7","source":{"kind":"arxiv","id":"2407.00945","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00945","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00945v1","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00945","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"pith_short_12","alias_value":"YAZCFPFMQDBE","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"pith_short_16","alias_value":"YAZCFPFMQDBEIH3U","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"pith_short_8","alias_value":"YAZCFPFM","created_at":"2026-07-05T08:38:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YAZCFPFMQDBEIH3UG4YH5A4CJB","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T03:57:35Z","cross_cats_sorted":[],"title_canon_sha256":"126003e00ad1463443b6f4ccbb780165a469441e60709992a75bad0646adc5d7","abstract_canon_sha256":"5e6cc79f841159e1e9c1a50b675105cf88426efd92ef07244051f49d8ca2bd66"},"schema_version":"1.0"},"canonical_sha256":"c03222bcac80c2441f7437307e8382485dddd493e106698c64e2807723d107e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:26.613261Z","signature_b64":"YsRyolTtCx1p/34GIPXRin+S5qqldH8Xwxz2Qu9uCqUB+NIeRYaPGe8El3rm1EW09NjIOwXnNztRKVTDc2hsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c03222bcac80c2441f7437307e8382485dddd493e106698c64e2807723d107e7","last_reissued_at":"2026-07-05T08:38:26.612918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:26.612918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00945","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":"2026-07-05T08:38:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XlAGRv49TrYg4BsLJUJTsZWpMU1EzZl/v1erwWovnzyme7A1LVIC9W+VPnwIi/UAn5t5jb9tPyqD4K7roCgzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:41:32.510430Z"},"content_sha256":"56146d6c03d8bf8048ea93b4a469ac67bf893031eed90cbf48a04dc026fec161","schema_version":"1.0","event_id":"sha256:56146d6c03d8bf8048ea93b4a469ac67bf893031eed90cbf48a04dc026fec161"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YAZCFPFMQDBEIH3UG4YH5A4CJB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Enshu Liu, Guohao Dai, Huazhong Yang, Junyi Zhu, Matthew B. Blaschko, Shengen Yan, Xuefei Ning, Yu Wang, Zinan Lin","submitted_at":"2024-07-01T03:57:35Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their substantial demands on memory, processing power, and energy consumption. Sparse Mixture-of-Experts (SMoE) architectures have emerged as a solution, activating only a subset of parameters per token, thereby achieving faster inference while maintaining performance. However, SMoE models still face limitations in broader deployment due to their large parameter counts and significant GPU memory requirements. In this work, we i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00945","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/2407.00945/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":"2026-07-05T08:38:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zolbqrY9k6A/L24Rtop/YCdFBBVysdxw9PrXWUPTqMfV46GUo3E99ExhdVgXPy/gQlLaItnRd3sFeIf4bVyCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:41:32.510999Z"},"content_sha256":"6e18cf8d2b8d72806bbb9513d6673d4a7eeea33af2e157394c6b012b3d6645a7","schema_version":"1.0","event_id":"sha256:6e18cf8d2b8d72806bbb9513d6673d4a7eeea33af2e157394c6b012b3d6645a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAZCFPFMQDBEIH3UG4YH5A4CJB/bundle.json","state_url":"https://pith.science/pith/YAZCFPFMQDBEIH3UG4YH5A4CJB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAZCFPFMQDBEIH3UG4YH5A4CJB/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":"2026-08-14T10:41:32Z","links":{"resolver":"https://pith.science/pith/YAZCFPFMQDBEIH3UG4YH5A4CJB","bundle":"https://pith.science/pith/YAZCFPFMQDBEIH3UG4YH5A4CJB/bundle.json","state":"https://pith.science/pith/YAZCFPFMQDBEIH3UG4YH5A4CJB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAZCFPFMQDBEIH3UG4YH5A4CJB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YAZCFPFMQDBEIH3UG4YH5A4CJB","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":"5e6cc79f841159e1e9c1a50b675105cf88426efd92ef07244051f49d8ca2bd66","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T03:57:35Z","title_canon_sha256":"126003e00ad1463443b6f4ccbb780165a469441e60709992a75bad0646adc5d7"},"schema_version":"1.0","source":{"id":"2407.00945","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00945","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00945v1","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00945","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"pith_short_12","alias_value":"YAZCFPFMQDBE","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"pith_short_16","alias_value":"YAZCFPFMQDBEIH3U","created_at":"2026-07-05T08:38:26Z"},{"alias_kind":"pith_short_8","alias_value":"YAZCFPFM","created_at":"2026-07-05T08:38:26Z"}],"graph_snapshots":[{"event_id":"sha256:6e18cf8d2b8d72806bbb9513d6673d4a7eeea33af2e157394c6b012b3d6645a7","target":"graph","created_at":"2026-07-05T08:38:26Z","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/2407.00945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their substantial demands on memory, processing power, and energy consumption. Sparse Mixture-of-Experts (SMoE) architectures have emerged as a solution, activating only a subset of parameters per token, thereby achieving faster inference while maintaining performance. However, SMoE models still face limitations in broader deployment due to their large parameter counts and significant GPU memory requirements. In this work, we i","authors_text":"Enshu Liu, Guohao Dai, Huazhong Yang, Junyi Zhu, Matthew B. Blaschko, Shengen Yan, Xuefei Ning, Yu Wang, Zinan Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T03:57:35Z","title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00945","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":"sha256:56146d6c03d8bf8048ea93b4a469ac67bf893031eed90cbf48a04dc026fec161","target":"record","created_at":"2026-07-05T08:38:26Z","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":"5e6cc79f841159e1e9c1a50b675105cf88426efd92ef07244051f49d8ca2bd66","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T03:57:35Z","title_canon_sha256":"126003e00ad1463443b6f4ccbb780165a469441e60709992a75bad0646adc5d7"},"schema_version":"1.0","source":{"id":"2407.00945","kind":"arxiv","version":1}},"canonical_sha256":"c03222bcac80c2441f7437307e8382485dddd493e106698c64e2807723d107e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c03222bcac80c2441f7437307e8382485dddd493e106698c64e2807723d107e7","first_computed_at":"2026-07-05T08:38:26.612918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:26.612918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YsRyolTtCx1p/34GIPXRin+S5qqldH8Xwxz2Qu9uCqUB+NIeRYaPGe8El3rm1EW09NjIOwXnNztRKVTDc2hsBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:26.613261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00945","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56146d6c03d8bf8048ea93b4a469ac67bf893031eed90cbf48a04dc026fec161","sha256:6e18cf8d2b8d72806bbb9513d6673d4a7eeea33af2e157394c6b012b3d6645a7"],"state_sha256":"2b1f2fcf46da42e978414d9673a039de2605f06d471d6fab081c2e91130dffea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iOSmxeCL14JoqXNGnLqa8dNlsDJc2fmdbhm8OB5beRlz5aC0WlZcSEde0d5nd3DYAYtHzEzLt17qNFbsw6URBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:41:32.517182Z","bundle_sha256":"3f50b373423d2ee65c69611d690163183a55c9fdd6ee33d61bf78c4b70f491d0"}}