{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ADNIMAYEF7HHHIS47QAWM2J5LF","short_pith_number":"pith:ADNIMAYE","schema_version":"1.0","canonical_sha256":"00da8603042fce73a25cfc0166693d5963546382168a14cab081ebbc21cdb437","source":{"kind":"arxiv","id":"2411.07762","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.07762","created_at":"2026-07-05T09:47:57.355468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07762v2","created_at":"2026-07-05T09:47:57.355468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07762","created_at":"2026-07-05T09:47:57.355468+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADNIMAYEF7HH","created_at":"2026-07-05T09:47:57.355468+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADNIMAYEF7HHHIS4","created_at":"2026-07-05T09:47:57.355468+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADNIMAYE","created_at":"2026-07-05T09:47:57.355468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF","json":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF.json","graph_json":"https://pith.science/api/pith-number/ADNIMAYEF7HHHIS47QAWM2J5LF/graph.json","events_json":"https://pith.science/api/pith-number/ADNIMAYEF7HHHIS47QAWM2J5LF/events.json","paper":"https://pith.science/paper/ADNIMAYE"},"agent_actions":{"view_html":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF","download_json":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF.json","view_paper":"https://pith.science/paper/ADNIMAYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07762&json=true","fetch_graph":"https://pith.science/api/pith-number/ADNIMAYEF7HHHIS47QAWM2J5LF/graph.json","fetch_events":"https://pith.science/api/pith-number/ADNIMAYEF7HHHIS47QAWM2J5LF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/action/storage_attestation","attest_author":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/action/author_attestation","sign_citation":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/action/citation_signature","submit_replication":"https://pith.science/pith/ADNIMAYEF7HHHIS47QAWM2J5LF/action/replication_record"}},"created_at":"2026-07-05T09:47:57.355468+00:00","updated_at":"2026-07-05T09:47:57.355468+00:00"}