{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OPYM6Q6K7RYFFW2XYZ7NLVAQJF","short_pith_number":"pith:OPYM6Q6K","canonical_record":{"source":{"id":"2211.10438","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-18T18:59:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dda0db0ff0b94b80fac9950e2f16e09a5a98cd31d8ac2a0215f4572c9276b0c2","abstract_canon_sha256":"5c306c6424100baa9868bd92f05ce573ea8cead5e0fd2a8ff0269bd7bb4f9045"},"schema_version":"1.0"},"canonical_sha256":"73f0cf43cafc7052db57c67ed5d4104966bf8ef25bb53e8c28301368f07f45da","source":{"kind":"arxiv","id":"2211.10438","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10438","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10438v7","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10438","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"OPYM6Q6K7RYF","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"OPYM6Q6K7RYFFW2X","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"OPYM6Q6K","created_at":"2026-07-05T08:03:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OPYM6Q6K7RYFFW2XYZ7NLVAQJF","target":"record","payload":{"canonical_record":{"source":{"id":"2211.10438","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-18T18:59:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dda0db0ff0b94b80fac9950e2f16e09a5a98cd31d8ac2a0215f4572c9276b0c2","abstract_canon_sha256":"5c306c6424100baa9868bd92f05ce573ea8cead5e0fd2a8ff0269bd7bb4f9045"},"schema_version":"1.0"},"canonical_sha256":"73f0cf43cafc7052db57c67ed5d4104966bf8ef25bb53e8c28301368f07f45da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:05.386167Z","signature_b64":"5yFtCsByEs2cAnDbwvqe+rq138EaPFu3kvCsX6E2fysTWFWnLmfR5dUTmY0Cj+NH1o5MbWdxJXsdg7ORicGGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73f0cf43cafc7052db57c67ed5d4104966bf8ef25bb53e8c28301368f07f45da","last_reissued_at":"2026-07-05T08:03:05.385664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:05.385664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.10438","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"15hf21qGlVN85BAZOHZPstZ7boKWP+YCxqp0S14hfqvSSI8lzib/HsUF70BVM7vqJeAAD3jm1dLZu/2praCYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:09:30.692862Z"},"content_sha256":"767caf38a13dffa9fd3d2518da32fe4793cdeb337713866f1590fd0e29f6f3ed","schema_version":"1.0","event_id":"sha256:767caf38a13dffa9fd3d2518da32fe4793cdeb337713866f1590fd0e29f6f3ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OPYM6Q6K7RYFFW2XYZ7NLVAQJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guangxuan Xiao, Hao Wu, Ji Lin, Julien Demouth, Mickael Seznec, Song Han","submitted_at":"2022-11-18T18:59:33Z","abstract_excerpt":"Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same time. We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs. Based on the fact that weights are easy to quantize while activations are not, SmoothQuant smooths the activation outliers by offline migrating the quantization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10438","kind":"arxiv","version":7},"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/2211.10438/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":"2026-07-05T08:03:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtfBG8Mb3err0RR8xR5qDnS+JfR6szmb2GAnDQboO9M+rdj3oifrURSlT2IAuFT/vnXzSe6jFdW5etENvNoZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:09:30.693228Z"},"content_sha256":"aed0bc84c34587ab47a739036d21a3a35b13c2d4c3463b49a0747174eae794fd","schema_version":"1.0","event_id":"sha256:aed0bc84c34587ab47a739036d21a3a35b13c2d4c3463b49a0747174eae794fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPYM6Q6K7RYFFW2XYZ7NLVAQJF/bundle.json","state_url":"https://pith.science/pith/OPYM6Q6K7RYFFW2XYZ7NLVAQJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPYM6Q6K7RYFFW2XYZ7NLVAQJF/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":"2026-07-07T11:09:30Z","links":{"resolver":"https://pith.science/pith/OPYM6Q6K7RYFFW2XYZ7NLVAQJF","bundle":"https://pith.science/pith/OPYM6Q6K7RYFFW2XYZ7NLVAQJF/bundle.json","state":"https://pith.science/pith/OPYM6Q6K7RYFFW2XYZ7NLVAQJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPYM6Q6K7RYFFW2XYZ7NLVAQJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OPYM6Q6K7RYFFW2XYZ7NLVAQJF","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":"5c306c6424100baa9868bd92f05ce573ea8cead5e0fd2a8ff0269bd7bb4f9045","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-18T18:59:33Z","title_canon_sha256":"dda0db0ff0b94b80fac9950e2f16e09a5a98cd31d8ac2a0215f4572c9276b0c2"},"schema_version":"1.0","source":{"id":"2211.10438","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10438","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10438v7","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10438","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"OPYM6Q6K7RYF","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"OPYM6Q6K7RYFFW2X","created_at":"2026-07-05T08:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"OPYM6Q6K","created_at":"2026-07-05T08:03:05Z"}],"graph_snapshots":[{"event_id":"sha256:aed0bc84c34587ab47a739036d21a3a35b13c2d4c3463b49a0747174eae794fd","target":"graph","created_at":"2026-07-05T08:03:05Z","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/2211.10438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same time. We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs. Based on the fact that weights are easy to quantize while activations are not, SmoothQuant smooths the activation outliers by offline migrating the quantization","authors_text":"Guangxuan Xiao, Hao Wu, Ji Lin, Julien Demouth, Mickael Seznec, Song Han","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-18T18:59:33Z","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10438","kind":"arxiv","version":7},"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":"sha256:767caf38a13dffa9fd3d2518da32fe4793cdeb337713866f1590fd0e29f6f3ed","target":"record","created_at":"2026-07-05T08:03:05Z","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":"5c306c6424100baa9868bd92f05ce573ea8cead5e0fd2a8ff0269bd7bb4f9045","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-18T18:59:33Z","title_canon_sha256":"dda0db0ff0b94b80fac9950e2f16e09a5a98cd31d8ac2a0215f4572c9276b0c2"},"schema_version":"1.0","source":{"id":"2211.10438","kind":"arxiv","version":7}},"canonical_sha256":"73f0cf43cafc7052db57c67ed5d4104966bf8ef25bb53e8c28301368f07f45da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73f0cf43cafc7052db57c67ed5d4104966bf8ef25bb53e8c28301368f07f45da","first_computed_at":"2026-07-05T08:03:05.385664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:05.385664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5yFtCsByEs2cAnDbwvqe+rq138EaPFu3kvCsX6E2fysTWFWnLmfR5dUTmY0Cj+NH1o5MbWdxJXsdg7ORicGGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:05.386167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.10438","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:767caf38a13dffa9fd3d2518da32fe4793cdeb337713866f1590fd0e29f6f3ed","sha256:aed0bc84c34587ab47a739036d21a3a35b13c2d4c3463b49a0747174eae794fd"],"state_sha256":"b92dfb34d8112aa5099bf7112f97cde0a372ab0d5abf248a7f3e91493d06e073"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8aoanuBKeFsCOZa9I/1IudKP+W7SBbRi8Ls7/aBWPpQNlVpuFYYJF63IOSvG1n7IBGZvEyJjJxdcB6Cr2S6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:09:30.695119Z","bundle_sha256":"e2109ba166f9d5d96f5c23673203131c706adc24c291e61ff0a97de9baa03ad3"}}