{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3OCNODIJX6HIEDDBLHLCGFLL4I","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":"d131cbbfb37867389ea419a664a399c3ae662b4fda326cfebf3202dc30502a2b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-04T00:28:21Z","title_canon_sha256":"4c53dc18a570861d28d16131313f1053c893feb671f5ccf032128e2d9516b5b0"},"schema_version":"1.0","source":{"id":"2206.01861","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01861","created_at":"2026-07-05T04:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01861v1","created_at":"2026-07-05T04:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01861","created_at":"2026-07-05T04:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"3OCNODIJX6HI","created_at":"2026-07-05T04:28:56Z"},{"alias_kind":"pith_short_16","alias_value":"3OCNODIJX6HIEDDB","created_at":"2026-07-05T04:28:56Z"},{"alias_kind":"pith_short_8","alias_value":"3OCNODIJ","created_at":"2026-07-05T04:28:56Z"}],"graph_snapshots":[{"event_id":"sha256:240fb1f5d7c0e1ea30f1a98744aa0784ff6c5efb8dc7f4c030443f34f33c699c","target":"graph","created_at":"2026-07-05T04:28:56Z","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/2206.01861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements. In this work, we present an efficient and affordable post-training quantization approach to compress large Transformer-based models, termed as ZeroQuant. ZeroQuant is an end-to-end quantization and inference pipeline with three main components: (1) a fine-grained hardware-friendly quantization scheme for both weight and activations; (2) a novel affordable layer-by-layer knowledge distillat","authors_text":"Conglong Li, Minjia Zhang, Reza Yazdani Aminabadi, Xiaoxia Wu, Yuxiong He, Zhewei Yao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-04T00:28:21Z","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01861","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":"sha256:2a68ec92cc804dad024ef3a0613a3117872084f8c629a1a8512e3d4e9ab489e4","target":"record","created_at":"2026-07-05T04:28:56Z","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":"d131cbbfb37867389ea419a664a399c3ae662b4fda326cfebf3202dc30502a2b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-04T00:28:21Z","title_canon_sha256":"4c53dc18a570861d28d16131313f1053c893feb671f5ccf032128e2d9516b5b0"},"schema_version":"1.0","source":{"id":"2206.01861","kind":"arxiv","version":1}},"canonical_sha256":"db84d70d09bf8e820c6159d623156be22df0dce187aeaf4b2e8f4c1920dfedcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db84d70d09bf8e820c6159d623156be22df0dce187aeaf4b2e8f4c1920dfedcc","first_computed_at":"2026-07-05T04:28:56.983893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:56.983893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vOvJVeYjeA1ofYiphHaRct6nskQzYE9uH1OdXg/FhJ0bPvQfyi2ws5J7z970s9Sao1R4NNFUoGWccFuD259uAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:56.984347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01861","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a68ec92cc804dad024ef3a0613a3117872084f8c629a1a8512e3d4e9ab489e4","sha256:240fb1f5d7c0e1ea30f1a98744aa0784ff6c5efb8dc7f4c030443f34f33c699c"],"state_sha256":"f7e8a125cf9c95c0883b1c290a89edb9d82fa24f97a2c632cd2d023d583af5a8"}