{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GVEUMU2ZTQF4Z4SMZFGIYJDO6T","short_pith_number":"pith:GVEUMU2Z","canonical_record":{"source":{"id":"2606.09885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T07:49:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4aaf8a8daa2363a7f5458c1726750285e76305234a0c4ad11a0edc1a85eae81c","abstract_canon_sha256":"b676b6a69dd6139f4fae335e81592e76eb2a06241f5de5d226dc24a2e9d59e67"},"schema_version":"1.0"},"canonical_sha256":"35494653599c0bccf24cc94c8c246ef4e2976e8c984d1c06c61aabfc3a88129e","source":{"kind":"arxiv","id":"2606.09885","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09885","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09885v1","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09885","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"GVEUMU2ZTQF4","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"GVEUMU2ZTQF4Z4SM","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"GVEUMU2Z","created_at":"2026-06-10T00:08:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GVEUMU2ZTQF4Z4SMZFGIYJDO6T","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T07:49:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4aaf8a8daa2363a7f5458c1726750285e76305234a0c4ad11a0edc1a85eae81c","abstract_canon_sha256":"b676b6a69dd6139f4fae335e81592e76eb2a06241f5de5d226dc24a2e9d59e67"},"schema_version":"1.0"},"canonical_sha256":"35494653599c0bccf24cc94c8c246ef4e2976e8c984d1c06c61aabfc3a88129e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:31.260959Z","signature_b64":"qJEtx5M5hQARmIoQaAMh+hu4IPAaDmcvRwpSlFLP8JJyVUZ5Be+V0hZKhb/5NimKvPODFeFlAyZNmNA/0h7MAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35494653599c0bccf24cc94c8c246ef4e2976e8c984d1c06c61aabfc3a88129e","last_reissued_at":"2026-06-10T00:08:31.260284Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:31.260284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09885","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":"2026-06-10T00:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wM2pDPQIM/Sv5qrXiXJoxgLjnQ0AY4m1Sfhh07z1x1mVk+zExhBTaVxxC+Y7M+lI+n8uDyYLATb3z6mrxFrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:37:26.335691Z"},"content_sha256":"2a9b213aa9b42a68ffb045b6b30760b37a610215e22e4f3b83dfaa66bbef3884","schema_version":"1.0","event_id":"sha256:2a9b213aa9b42a68ffb045b6b30760b37a610215e22e4f3b83dfaa66bbef3884"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GVEUMU2ZTQF4Z4SMZFGIYJDO6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Deyi Xiong, Jiangyang He, Shaolin Zhu","submitted_at":"2026-06-03T07:49:31Z","abstract_excerpt":"Mixture-of-Experts large language models (LLMs) scale efficiently through sparse activation, yet their deployment is fundamentally constrained by the large static parameter footprint of experts. Existing compression approaches either remove entire experts, disrupting routing topology and harming performance, or rely on unstructured weight pruning with limited practical efficiency. To address the limitations, we propose TENP, a structured Trapezoidal ExpertNeuron Pruning framework. Using a few samples, we identify and retain important experts, while applying expert neuron pruning (ENP) to less "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09885","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/2606.09885/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":"2026-06-10T00:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWYqT/GCXsfwbtTs/ItIU6QX2LFzFraEjwnfWogTem5u90JOOAyPnAG2591ACFwzp9n7POkrZEKKoZH7I8LUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:37:26.336067Z"},"content_sha256":"9aef5b4671811542a4419bbc2972fb84761d36dc6372e5dfe80f2ca078227e5d","schema_version":"1.0","event_id":"sha256:9aef5b4671811542a4419bbc2972fb84761d36dc6372e5dfe80f2ca078227e5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVEUMU2ZTQF4Z4SMZFGIYJDO6T/bundle.json","state_url":"https://pith.science/pith/GVEUMU2ZTQF4Z4SMZFGIYJDO6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVEUMU2ZTQF4Z4SMZFGIYJDO6T/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":"2026-06-28T15:37:26Z","links":{"resolver":"https://pith.science/pith/GVEUMU2ZTQF4Z4SMZFGIYJDO6T","bundle":"https://pith.science/pith/GVEUMU2ZTQF4Z4SMZFGIYJDO6T/bundle.json","state":"https://pith.science/pith/GVEUMU2ZTQF4Z4SMZFGIYJDO6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVEUMU2ZTQF4Z4SMZFGIYJDO6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GVEUMU2ZTQF4Z4SMZFGIYJDO6T","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":"b676b6a69dd6139f4fae335e81592e76eb2a06241f5de5d226dc24a2e9d59e67","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T07:49:31Z","title_canon_sha256":"4aaf8a8daa2363a7f5458c1726750285e76305234a0c4ad11a0edc1a85eae81c"},"schema_version":"1.0","source":{"id":"2606.09885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09885","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09885v1","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09885","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"GVEUMU2ZTQF4","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"GVEUMU2ZTQF4Z4SM","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"GVEUMU2Z","created_at":"2026-06-10T00:08:31Z"}],"graph_snapshots":[{"event_id":"sha256:9aef5b4671811542a4419bbc2972fb84761d36dc6372e5dfe80f2ca078227e5d","target":"graph","created_at":"2026-06-10T00:08:31Z","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/2606.09885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts large language models (LLMs) scale efficiently through sparse activation, yet their deployment is fundamentally constrained by the large static parameter footprint of experts. Existing compression approaches either remove entire experts, disrupting routing topology and harming performance, or rely on unstructured weight pruning with limited practical efficiency. To address the limitations, we propose TENP, a structured Trapezoidal ExpertNeuron Pruning framework. Using a few samples, we identify and retain important experts, while applying expert neuron pruning (ENP) to less ","authors_text":"Deyi Xiong, Jiangyang He, Shaolin Zhu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T07:49:31Z","title":"TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09885","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":"sha256:2a9b213aa9b42a68ffb045b6b30760b37a610215e22e4f3b83dfaa66bbef3884","target":"record","created_at":"2026-06-10T00:08:31Z","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":"b676b6a69dd6139f4fae335e81592e76eb2a06241f5de5d226dc24a2e9d59e67","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T07:49:31Z","title_canon_sha256":"4aaf8a8daa2363a7f5458c1726750285e76305234a0c4ad11a0edc1a85eae81c"},"schema_version":"1.0","source":{"id":"2606.09885","kind":"arxiv","version":1}},"canonical_sha256":"35494653599c0bccf24cc94c8c246ef4e2976e8c984d1c06c61aabfc3a88129e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35494653599c0bccf24cc94c8c246ef4e2976e8c984d1c06c61aabfc3a88129e","first_computed_at":"2026-06-10T00:08:31.260284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:31.260284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qJEtx5M5hQARmIoQaAMh+hu4IPAaDmcvRwpSlFLP8JJyVUZ5Be+V0hZKhb/5NimKvPODFeFlAyZNmNA/0h7MAg==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:31.260959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a9b213aa9b42a68ffb045b6b30760b37a610215e22e4f3b83dfaa66bbef3884","sha256:9aef5b4671811542a4419bbc2972fb84761d36dc6372e5dfe80f2ca078227e5d"],"state_sha256":"1149992cb9b73ae574bb3612951206ee6a6c28872cc9be345ece236f7614a11f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rodJHttg1oEBfBj4VrOSiJ7e1CXe2ndOFdajfSSOD5GJh6cE7AzSMZRYCj0y17K7d981ioW04pUsZE6ZPrWYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T15:37:26.338382Z","bundle_sha256":"176571919c4c372463e88d46fb02c140c1d2c3ed163e3f87959ac862ac88c2c0"}}