{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MWRLQGOOWMQJMVKI5IUM5T4CZD","short_pith_number":"pith:MWRLQGOO","canonical_record":{"source":{"id":"2311.00502","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T13:08:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b28efea4faeea74655e52a4b16474058e341b3feec8d415d084716c7dc20b66e","abstract_canon_sha256":"59b5890c44ac7a19b685ed034e775c1011cba22620342d0756f738fa2925ace0"},"schema_version":"1.0"},"canonical_sha256":"65a2b819ceb320965548ea28cecf82c8c8bad78756a8527e87aea44c303b2817","source":{"kind":"arxiv","id":"2311.00502","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00502","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00502v2","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00502","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"MWRLQGOOWMQJ","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"MWRLQGOOWMQJMVKI","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"MWRLQGOO","created_at":"2026-07-05T07:21:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MWRLQGOOWMQJMVKI5IUM5T4CZD","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00502","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T13:08:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b28efea4faeea74655e52a4b16474058e341b3feec8d415d084716c7dc20b66e","abstract_canon_sha256":"59b5890c44ac7a19b685ed034e775c1011cba22620342d0756f738fa2925ace0"},"schema_version":"1.0"},"canonical_sha256":"65a2b819ceb320965548ea28cecf82c8c8bad78756a8527e87aea44c303b2817","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:28.718087Z","signature_b64":"TVIYdUWJ4I2G03nTu2ysK6eyaG3HD6447TvtdTRVH0pwJFoZqpaFEEMuKZ6LlQpm2/EJKVJLlud6SGsCHZYHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65a2b819ceb320965548ea28cecf82c8c8bad78756a8527e87aea44c303b2817","last_reissued_at":"2026-07-05T07:21:28.717585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:28.717585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00502","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":"2026-07-05T07:21:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Kw8g8Ri09jGtm4Cu+DTzAyFX+Ui5Rwxd+nTXCGld9MvTyygvGcYf2x14F5bBvPoPY5+bBP6TTMraJbbU5VrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:38:58.029883Z"},"content_sha256":"ea20d7e42d05cc664e4d2d9cf14ae2ecb522f86380c90297a4237b5c148b7d71","schema_version":"1.0","event_id":"sha256:ea20d7e42d05cc664e4d2d9cf14ae2ecb522f86380c90297a4237b5c148b7d71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MWRLQGOOWMQJMVKI5IUM5T4CZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient LLM Inference on CPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Dong, Haihao Shen, Hanwen Chang, Hengyu Meng, Yu Luo","submitted_at":"2023-11-01T13:08:50Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance and tremendous potential across a wide range of tasks. However, deploying these models has been challenging due to the astronomical amount of model parameters, which requires a demand for large memory capacity and high memory bandwidth. In this paper, we propose an effective approach that can make the deployment of LLMs more efficiently. We support an automatic INT4 weight-only quantization flow and design a special LLM runtime with highly-optimized kernels to accelerate the LLM inference on CPUs. We demonstrate the general "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00502","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/2311.00502/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":"2026-07-05T07:21:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtUX09fk54Uo8d6l/NMARJN5FkyoENwu4moqyy3dFJQ3oXw0hBo2q3etuWDv/DEPCH2NEo84Sfn41vB4NPFFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:38:58.030396Z"},"content_sha256":"58369c9f937fc4d27186c815b973afc5abb51e88584e41401cbc5255add3e8d0","schema_version":"1.0","event_id":"sha256:58369c9f937fc4d27186c815b973afc5abb51e88584e41401cbc5255add3e8d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWRLQGOOWMQJMVKI5IUM5T4CZD/bundle.json","state_url":"https://pith.science/pith/MWRLQGOOWMQJMVKI5IUM5T4CZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWRLQGOOWMQJMVKI5IUM5T4CZD/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":"2026-08-03T20:38:58Z","links":{"resolver":"https://pith.science/pith/MWRLQGOOWMQJMVKI5IUM5T4CZD","bundle":"https://pith.science/pith/MWRLQGOOWMQJMVKI5IUM5T4CZD/bundle.json","state":"https://pith.science/pith/MWRLQGOOWMQJMVKI5IUM5T4CZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWRLQGOOWMQJMVKI5IUM5T4CZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MWRLQGOOWMQJMVKI5IUM5T4CZD","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":"59b5890c44ac7a19b685ed034e775c1011cba22620342d0756f738fa2925ace0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T13:08:50Z","title_canon_sha256":"b28efea4faeea74655e52a4b16474058e341b3feec8d415d084716c7dc20b66e"},"schema_version":"1.0","source":{"id":"2311.00502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00502","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00502v2","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00502","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"MWRLQGOOWMQJ","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"MWRLQGOOWMQJMVKI","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"MWRLQGOO","created_at":"2026-07-05T07:21:28Z"}],"graph_snapshots":[{"event_id":"sha256:58369c9f937fc4d27186c815b973afc5abb51e88584e41401cbc5255add3e8d0","target":"graph","created_at":"2026-07-05T07:21:28Z","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/2311.00502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance and tremendous potential across a wide range of tasks. However, deploying these models has been challenging due to the astronomical amount of model parameters, which requires a demand for large memory capacity and high memory bandwidth. In this paper, we propose an effective approach that can make the deployment of LLMs more efficiently. We support an automatic INT4 weight-only quantization flow and design a special LLM runtime with highly-optimized kernels to accelerate the LLM inference on CPUs. We demonstrate the general ","authors_text":"Bo Dong, Haihao Shen, Hanwen Chang, Hengyu Meng, Yu Luo","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T13:08:50Z","title":"Efficient LLM Inference on CPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00502","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:ea20d7e42d05cc664e4d2d9cf14ae2ecb522f86380c90297a4237b5c148b7d71","target":"record","created_at":"2026-07-05T07:21:28Z","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":"59b5890c44ac7a19b685ed034e775c1011cba22620342d0756f738fa2925ace0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T13:08:50Z","title_canon_sha256":"b28efea4faeea74655e52a4b16474058e341b3feec8d415d084716c7dc20b66e"},"schema_version":"1.0","source":{"id":"2311.00502","kind":"arxiv","version":2}},"canonical_sha256":"65a2b819ceb320965548ea28cecf82c8c8bad78756a8527e87aea44c303b2817","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65a2b819ceb320965548ea28cecf82c8c8bad78756a8527e87aea44c303b2817","first_computed_at":"2026-07-05T07:21:28.717585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:28.717585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TVIYdUWJ4I2G03nTu2ysK6eyaG3HD6447TvtdTRVH0pwJFoZqpaFEEMuKZ6LlQpm2/EJKVJLlud6SGsCHZYHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:28.718087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea20d7e42d05cc664e4d2d9cf14ae2ecb522f86380c90297a4237b5c148b7d71","sha256:58369c9f937fc4d27186c815b973afc5abb51e88584e41401cbc5255add3e8d0"],"state_sha256":"b84b2c5c5df0beef25cb7964f1354067ff85864ec4bc23ccc6bea76c1940e803"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WA01GC9O/dZS+IbbU9IfiqLtqeCZPTuktKSG3AidHmMpV/4YiNBc/e8aZox7jMj+Rihm6yg0M8a18vmY45jdCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:38:58.035168Z","bundle_sha256":"602da956300fa6c3e5418db8a0c41bbe4a93fa8b0be3fe1b430522c285481942"}}