{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ACZBDNQM2QPK76MAFQXFN4SFQO","short_pith_number":"pith:ACZBDNQM","canonical_record":{"source":{"id":"2406.08155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T12:44:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"934c37ffb2949aee9b4481715df0b3bb6675ca2c16216db35c3ac1dd84387aa2","abstract_canon_sha256":"5b49e2e58673e95b74e43f7642152667c87329fe405964d90691b958be441140"},"schema_version":"1.0"},"canonical_sha256":"00b211b60cd41eaff9802c2e56f2458388b3cf357ff50e88296559ec07013d41","source":{"kind":"arxiv","id":"2406.08155","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08155","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08155v2","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08155","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"ACZBDNQM2QPK","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"ACZBDNQM2QPK76MA","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"ACZBDNQM","created_at":"2026-07-05T10:19:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ACZBDNQM2QPK76MAFQXFN4SFQO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T12:44:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"934c37ffb2949aee9b4481715df0b3bb6675ca2c16216db35c3ac1dd84387aa2","abstract_canon_sha256":"5b49e2e58673e95b74e43f7642152667c87329fe405964d90691b958be441140"},"schema_version":"1.0"},"canonical_sha256":"00b211b60cd41eaff9802c2e56f2458388b3cf357ff50e88296559ec07013d41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:25.101921Z","signature_b64":"+maPKmAoKjEY5GrqnUVfZPyfD1AI9n+eyl/0MnJCuih1pK1jI3M/T+7erRRCuTsMKA3S81BwW2OKmU++Y+v8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00b211b60cd41eaff9802c2e56f2458388b3cf357ff50e88296559ec07013d41","last_reissued_at":"2026-07-05T10:19:25.101435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:25.101435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08155","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":"2026-07-05T10:19:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3hqKf2Z3FTR8cDMAZV4xHBw7lsvC64MjZt5fZSR7pw6bZKzhZCOrQBNLEU/V+WPzWnQ5fYf/gvFZv6byKKDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:14:39.015787Z"},"content_sha256":"891f5faa602d8b1387063c1dc697a4c099975a8072cd114c23220d61bd0cfabe","schema_version":"1.0","event_id":"sha256:891f5faa602d8b1387063c1dc697a4c099975a8072cd114c23220d61bd0cfabe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ACZBDNQM2QPK76MAFQXFN4SFQO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Pingzhi Li, Tianlong Chen, Xiaolong Jin, Yu Cheng, Zhen Tan","submitted_at":"2024-06-12T12:44:48Z","abstract_excerpt":"Mixture-of-Experts (MoE) is a promising way to scale up the learning capacity of large language models. It increases the number of parameters while keeping FLOPs nearly constant during inference through sparse activation. Yet, it still suffers from significant memory overheads due to the vast parameter size, necessitating model compression techniques. Post-training quantization offers a powerful approach for model compression. Existing methods adopt a fixed quantization precision for the entire MoE model. This rigid setup can lead to suboptimal performance, without considering the inherent spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08155","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/2406.08155/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":"2026-07-05T10:19:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0g1hS9HydW99hIIzXVHSkmZ9CL3owgV4jmk69/qyEc9oIZuBDLkhZiVqrzija8EjAg9uYOdYeyXlQJbf4CoSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:14:39.016324Z"},"content_sha256":"f945838f4dc7aa4eef90795d7dfcd0dac21f46ef2150113a60b942e605a4d598","schema_version":"1.0","event_id":"sha256:f945838f4dc7aa4eef90795d7dfcd0dac21f46ef2150113a60b942e605a4d598"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACZBDNQM2QPK76MAFQXFN4SFQO/bundle.json","state_url":"https://pith.science/pith/ACZBDNQM2QPK76MAFQXFN4SFQO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACZBDNQM2QPK76MAFQXFN4SFQO/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":"2026-08-05T11:14:39Z","links":{"resolver":"https://pith.science/pith/ACZBDNQM2QPK76MAFQXFN4SFQO","bundle":"https://pith.science/pith/ACZBDNQM2QPK76MAFQXFN4SFQO/bundle.json","state":"https://pith.science/pith/ACZBDNQM2QPK76MAFQXFN4SFQO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACZBDNQM2QPK76MAFQXFN4SFQO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ACZBDNQM2QPK76MAFQXFN4SFQO","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":"5b49e2e58673e95b74e43f7642152667c87329fe405964d90691b958be441140","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T12:44:48Z","title_canon_sha256":"934c37ffb2949aee9b4481715df0b3bb6675ca2c16216db35c3ac1dd84387aa2"},"schema_version":"1.0","source":{"id":"2406.08155","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08155","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08155v2","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08155","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"ACZBDNQM2QPK","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"ACZBDNQM2QPK76MA","created_at":"2026-07-05T10:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"ACZBDNQM","created_at":"2026-07-05T10:19:25Z"}],"graph_snapshots":[{"event_id":"sha256:f945838f4dc7aa4eef90795d7dfcd0dac21f46ef2150113a60b942e605a4d598","target":"graph","created_at":"2026-07-05T10:19:25Z","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/2406.08155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE) is a promising way to scale up the learning capacity of large language models. It increases the number of parameters while keeping FLOPs nearly constant during inference through sparse activation. Yet, it still suffers from significant memory overheads due to the vast parameter size, necessitating model compression techniques. Post-training quantization offers a powerful approach for model compression. Existing methods adopt a fixed quantization precision for the entire MoE model. This rigid setup can lead to suboptimal performance, without considering the inherent spa","authors_text":"Pingzhi Li, Tianlong Chen, Xiaolong Jin, Yu Cheng, Zhen Tan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T12:44:48Z","title":"QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08155","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":"sha256:891f5faa602d8b1387063c1dc697a4c099975a8072cd114c23220d61bd0cfabe","target":"record","created_at":"2026-07-05T10:19:25Z","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":"5b49e2e58673e95b74e43f7642152667c87329fe405964d90691b958be441140","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T12:44:48Z","title_canon_sha256":"934c37ffb2949aee9b4481715df0b3bb6675ca2c16216db35c3ac1dd84387aa2"},"schema_version":"1.0","source":{"id":"2406.08155","kind":"arxiv","version":2}},"canonical_sha256":"00b211b60cd41eaff9802c2e56f2458388b3cf357ff50e88296559ec07013d41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00b211b60cd41eaff9802c2e56f2458388b3cf357ff50e88296559ec07013d41","first_computed_at":"2026-07-05T10:19:25.101435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:25.101435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+maPKmAoKjEY5GrqnUVfZPyfD1AI9n+eyl/0MnJCuih1pK1jI3M/T+7erRRCuTsMKA3S81BwW2OKmU++Y+v8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:25.101921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08155","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:891f5faa602d8b1387063c1dc697a4c099975a8072cd114c23220d61bd0cfabe","sha256:f945838f4dc7aa4eef90795d7dfcd0dac21f46ef2150113a60b942e605a4d598"],"state_sha256":"49a0627a8d47639e5f21bc676d675a10beca9e76bab46b47e451812533b866b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8/1R4RsCVLXWDgvp5H5Hq91mLz365z8g/3Ur3AV8EYRbn8C6Ztqnqj/lv5hWO4BjNO0URLFMfK0bS24MSoeAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:14:39.021296Z","bundle_sha256":"8713a84ee70e7c9fa4e0491f55fce3ba61110c0170f9bc7661144f869b1338c6"}}