{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ADNIMAYEF7HHHIS47QAWM2J5LF","short_pith_number":"pith:ADNIMAYE","canonical_record":{"source":{"id":"2411.07762","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:52:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d3916b1ee64b1569def94e25d1bfc110deeb268d8ce2144d49d58d2573a71e8d","abstract_canon_sha256":"777a6e0a22c61c87d9fe12e2b61d3fa2174643c63bf7765042b7a75196debf36"},"schema_version":"1.0"},"canonical_sha256":"00da8603042fce73a25cfc0166693d5963546382168a14cab081ebbc21cdb437","source":{"kind":"arxiv","id":"2411.07762","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07762","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07762v2","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07762","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"ADNIMAYEF7HH","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"pith_short_16","alias_value":"ADNIMAYEF7HHHIS4","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"pith_short_8","alias_value":"ADNIMAYE","created_at":"2026-07-05T09:47:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ADNIMAYEF7HHHIS47QAWM2J5LF","target":"record","payload":{"canonical_record":{"source":{"id":"2411.07762","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:52:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d3916b1ee64b1569def94e25d1bfc110deeb268d8ce2144d49d58d2573a71e8d","abstract_canon_sha256":"777a6e0a22c61c87d9fe12e2b61d3fa2174643c63bf7765042b7a75196debf36"},"schema_version":"1.0"},"canonical_sha256":"00da8603042fce73a25cfc0166693d5963546382168a14cab081ebbc21cdb437","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:57.355947Z","signature_b64":"s7EsrbmcG7wfREqkiBNn3puEgZt9erTj9nvOGa6S7ZP88CBHiTT8IDBpGGIJ1rT7TsSuCUSxlmPyH1W5hLztDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00da8603042fce73a25cfc0166693d5963546382168a14cab081ebbc21cdb437","last_reissued_at":"2026-07-05T09:47:57.355406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:57.355406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.07762","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":"2026-07-05T09:47:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dzSmpjcFNrwlxOpFZClkFesBLmGx7CFW70FXxLGFX7WLUPzY/4WBreX8VLykwWpp3VLuagMKduR4CphcqwbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:09:49.385475Z"},"content_sha256":"5105d23e3573bdbc35a40012e53ea25549121b6c43f693dc1395e75052b22da2","schema_version":"1.0","event_id":"sha256:5105d23e3573bdbc35a40012e53ea25549121b6c43f693dc1395e75052b22da2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ADNIMAYEF7HHHIS47QAWM2J5LF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shen Li, Wanchen Sui, Weibo Zhao, Xinyu Lyu, Yong Li, Yubin Shi","submitted_at":"2024-11-12T12:52:04Z","abstract_excerpt":"Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The limited numerical mapping makes the quantized model produce a non-trivial error, bringing out intolerable performance degration. This paper is anchored in the basic idea of model compression objectives, and delves into the layer-wise error distribution of LLMs during post-training quantization. Subsequently, we introduce ASER, an algorithm consisting of (1) Error Reconstruction: low-rank compensation for quantizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07762","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/2411.07762/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":"2026-07-05T09:47:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z/XdCDsXSBL9yvnK6/N0KYT6krFnBJcnIMitNVn65AVq0IpG0pxEpURvJoPSqJCpBosf9q1At6xAUiXlpBS4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:09:49.385971Z"},"content_sha256":"3422959a4d8fe2bec5558ec2cb0bfb158c3e8a42dbb4638290fb8da5f642a4e6","schema_version":"1.0","event_id":"sha256:3422959a4d8fe2bec5558ec2cb0bfb158c3e8a42dbb4638290fb8da5f642a4e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/bundle.json","state_url":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/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":"2026-08-23T09:09:49Z","links":{"resolver":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF","bundle":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/bundle.json","state":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ADNIMAYEF7HHHIS47QAWM2J5LF","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":"777a6e0a22c61c87d9fe12e2b61d3fa2174643c63bf7765042b7a75196debf36","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:52:04Z","title_canon_sha256":"d3916b1ee64b1569def94e25d1bfc110deeb268d8ce2144d49d58d2573a71e8d"},"schema_version":"1.0","source":{"id":"2411.07762","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07762","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07762v2","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07762","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"ADNIMAYEF7HH","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"pith_short_16","alias_value":"ADNIMAYEF7HHHIS4","created_at":"2026-07-05T09:47:57Z"},{"alias_kind":"pith_short_8","alias_value":"ADNIMAYE","created_at":"2026-07-05T09:47:57Z"}],"graph_snapshots":[{"event_id":"sha256:3422959a4d8fe2bec5558ec2cb0bfb158c3e8a42dbb4638290fb8da5f642a4e6","target":"graph","created_at":"2026-07-05T09:47:57Z","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/2411.07762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The limited numerical mapping makes the quantized model produce a non-trivial error, bringing out intolerable performance degration. This paper is anchored in the basic idea of model compression objectives, and delves into the layer-wise error distribution of LLMs during post-training quantization. Subsequently, we introduce ASER, an algorithm consisting of (1) Error Reconstruction: low-rank compensation for quantizatio","authors_text":"Shen Li, Wanchen Sui, Weibo Zhao, Xinyu Lyu, Yong Li, Yubin Shi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:52:04Z","title":"ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07762","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":"sha256:5105d23e3573bdbc35a40012e53ea25549121b6c43f693dc1395e75052b22da2","target":"record","created_at":"2026-07-05T09:47:57Z","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":"777a6e0a22c61c87d9fe12e2b61d3fa2174643c63bf7765042b7a75196debf36","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:52:04Z","title_canon_sha256":"d3916b1ee64b1569def94e25d1bfc110deeb268d8ce2144d49d58d2573a71e8d"},"schema_version":"1.0","source":{"id":"2411.07762","kind":"arxiv","version":2}},"canonical_sha256":"00da8603042fce73a25cfc0166693d5963546382168a14cab081ebbc21cdb437","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00da8603042fce73a25cfc0166693d5963546382168a14cab081ebbc21cdb437","first_computed_at":"2026-07-05T09:47:57.355406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:57.355406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s7EsrbmcG7wfREqkiBNn3puEgZt9erTj9nvOGa6S7ZP88CBHiTT8IDBpGGIJ1rT7TsSuCUSxlmPyH1W5hLztDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:57.355947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07762","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5105d23e3573bdbc35a40012e53ea25549121b6c43f693dc1395e75052b22da2","sha256:3422959a4d8fe2bec5558ec2cb0bfb158c3e8a42dbb4638290fb8da5f642a4e6"],"state_sha256":"f38d085a0bbd0e511ffe9adaab5b2a7eabc4748807627e9c7230882539a231ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9NsBC+AvL0JjA5NyWCKhpmB37WGiSbxnW4hzo3n5N092Oxth/6NZncdJehYJyxn6vs6Br61auuhUmYcRATdBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T09:09:49.390525Z","bundle_sha256":"afc0a7b72cd1740acb46f00c8c06f1dc7a139637f8c50ca58bcb90e787880957"}}