{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:THRPCIKSMEY3HLF6ULYXWZL2JO","short_pith_number":"pith:THRPCIKS","schema_version":"1.0","canonical_sha256":"99e2f121526131b3acbea2f17b657a4b86704cc30258817c73aa2a0948976b68","source":{"kind":"arxiv","id":"2303.08302","version":3},"attestation_state":"computed","paper":{"title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cheng Li, Stephen Youn, Xiaoxia Wu, Yuxiong He, Zhewei Yao","submitted_at":"2023-03-15T01:27:15Z","abstract_excerpt":"Post-training quantization (PTQ) has emerged as a promising technique for mitigating memory consumption and computational costs in large language models (LLMs). However, a systematic examination of various quantization schemes, model families, and quantization bit precision has been absent from the literature. In this paper, we conduct a comprehensive analysis of these factors by investigating the effects of PTQ on weight-only, activation-only, and weight-and-activation quantization using diverse methods such as round-to-nearest (RTN), GPTQ, ZeroQuant, and their variants. We apply these method"},"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":"2303.08302","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T01:27:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bc46c2f0aab5b43f09b9758124820b9fff9bf9218e1b5506a20b62058fd51939","abstract_canon_sha256":"2c537ed78ffd5bf271ccf235a063b15047e228e20cdbba2e7fc3d066afa52b8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:09.124115Z","signature_b64":"mOl1f2Xn72Pl20UM6ZHvDqAH1AojTuBVjev4ecXycZWrcb51NkpoPbRTNfE8aQeAV2TFcMroAInUtXwOk095Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99e2f121526131b3acbea2f17b657a4b86704cc30258817c73aa2a0948976b68","last_reissued_at":"2026-07-05T06:14:09.123753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:09.123753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cheng Li, Stephen Youn, Xiaoxia Wu, Yuxiong He, Zhewei Yao","submitted_at":"2023-03-15T01:27:15Z","abstract_excerpt":"Post-training quantization (PTQ) has emerged as a promising technique for mitigating memory consumption and computational costs in large language models (LLMs). However, a systematic examination of various quantization schemes, model families, and quantization bit precision has been absent from the literature. In this paper, we conduct a comprehensive analysis of these factors by investigating the effects of PTQ on weight-only, activation-only, and weight-and-activation quantization using diverse methods such as round-to-nearest (RTN), GPTQ, ZeroQuant, and their variants. We apply these method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08302","kind":"arxiv","version":3},"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/2303.08302/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":"2303.08302","created_at":"2026-07-05T06:14:09.123799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08302v3","created_at":"2026-07-05T06:14:09.123799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08302","created_at":"2026-07-05T06:14:09.123799+00:00"},{"alias_kind":"pith_short_12","alias_value":"THRPCIKSMEY3","created_at":"2026-07-05T06:14:09.123799+00:00"},{"alias_kind":"pith_short_16","alias_value":"THRPCIKSMEY3HLF6","created_at":"2026-07-05T06:14:09.123799+00:00"},{"alias_kind":"pith_short_8","alias_value":"THRPCIKS","created_at":"2026-07-05T06:14:09.123799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01556","citing_title":"TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01412","citing_title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00494","citing_title":"ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2511.06516","citing_title":"You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19929","citing_title":"Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2305.05176","citing_title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21026","citing_title":"MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO","json":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO.json","graph_json":"https://pith.science/api/pith-number/THRPCIKSMEY3HLF6ULYXWZL2JO/graph.json","events_json":"https://pith.science/api/pith-number/THRPCIKSMEY3HLF6ULYXWZL2JO/events.json","paper":"https://pith.science/paper/THRPCIKS"},"agent_actions":{"view_html":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO","download_json":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO.json","view_paper":"https://pith.science/paper/THRPCIKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08302&json=true","fetch_graph":"https://pith.science/api/pith-number/THRPCIKSMEY3HLF6ULYXWZL2JO/graph.json","fetch_events":"https://pith.science/api/pith-number/THRPCIKSMEY3HLF6ULYXWZL2JO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO/action/storage_attestation","attest_author":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO/action/author_attestation","sign_citation":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO/action/citation_signature","submit_replication":"https://pith.science/pith/THRPCIKSMEY3HLF6ULYXWZL2JO/action/replication_record"}},"created_at":"2026-07-05T06:14:09.123799+00:00","updated_at":"2026-07-05T06:14:09.123799+00:00"}