{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EUCIWHZUCAGOSXLPLHAZUCYIL6","short_pith_number":"pith:EUCIWHZU","schema_version":"1.0","canonical_sha256":"25048b1f34100ce95d6f59c19a0b085f92e3cdc3d61311ac9634167c2d4b1cf3","source":{"kind":"arxiv","id":"2403.12544","version":1},"attestation_state":"computed","paper":{"title":"AffineQuant: Affine Transformation Quantization for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Chao, Feng Ling, Huixia Li, Rongrong Ji, Rui Wang, Shilei Wen, Xiawu Zheng, Xuefeng Xiao, Yuexiao Ma","submitted_at":"2024-03-19T08:40:21Z","abstract_excerpt":"The significant resource requirements associated with Large-scale Language Models (LLMs) have generated considerable interest in the development of techniques aimed at compressing and accelerating neural networks. Among these techniques, Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its noteworthy compression efficiency and cost-effectiveness in the context of training. Existing PTQ methods for LLMs limit the optimization scope to scaling transformations between pre- and post-quantization weights. In this paper, we advocate for the direct optimizatio"},"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":"2403.12544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T08:40:21Z","cross_cats_sorted":[],"title_canon_sha256":"3003f417ea6cd507ae3a50789c6e94cde4d22e1eec94cae77e6bb6c38bc1cbd0","abstract_canon_sha256":"efb7760508dcc723af2277bd0557d3135c0a17333cba8149ce1d5a5575fe82ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:03.243116Z","signature_b64":"FLz5ncrfSVAT0GRt0AWvWKHm96HcswYT42H2IvlvBRZW8f0JTKfir6xWcmZKa8hjJjuhPswRbweTZv/xqsZjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25048b1f34100ce95d6f59c19a0b085f92e3cdc3d61311ac9634167c2d4b1cf3","last_reissued_at":"2026-07-05T07:58:03.242667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:03.242667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AffineQuant: Affine Transformation Quantization for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Chao, Feng Ling, Huixia Li, Rongrong Ji, Rui Wang, Shilei Wen, Xiawu Zheng, Xuefeng Xiao, Yuexiao Ma","submitted_at":"2024-03-19T08:40:21Z","abstract_excerpt":"The significant resource requirements associated with Large-scale Language Models (LLMs) have generated considerable interest in the development of techniques aimed at compressing and accelerating neural networks. Among these techniques, Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its noteworthy compression efficiency and cost-effectiveness in the context of training. Existing PTQ methods for LLMs limit the optimization scope to scaling transformations between pre- and post-quantization weights. In this paper, we advocate for the direct optimizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12544","kind":"arxiv","version":1},"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/2403.12544/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":"2403.12544","created_at":"2026-07-05T07:58:03.242727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12544v1","created_at":"2026-07-05T07:58:03.242727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12544","created_at":"2026-07-05T07:58:03.242727+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUCIWHZUCAGO","created_at":"2026-07-05T07:58:03.242727+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUCIWHZUCAGOSXLP","created_at":"2026-07-05T07:58:03.242727+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUCIWHZU","created_at":"2026-07-05T07:58:03.242727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26587","citing_title":"SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00535","citing_title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","ref_index":47,"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":35,"is_internal_anchor":false},{"citing_arxiv_id":"2506.12040","citing_title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01725","citing_title":"Motion-Aware Caching for Efficient Autoregressive Video Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13734","citing_title":"KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17789","citing_title":"DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6","json":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6.json","graph_json":"https://pith.science/api/pith-number/EUCIWHZUCAGOSXLPLHAZUCYIL6/graph.json","events_json":"https://pith.science/api/pith-number/EUCIWHZUCAGOSXLPLHAZUCYIL6/events.json","paper":"https://pith.science/paper/EUCIWHZU"},"agent_actions":{"view_html":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6","download_json":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6.json","view_paper":"https://pith.science/paper/EUCIWHZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12544&json=true","fetch_graph":"https://pith.science/api/pith-number/EUCIWHZUCAGOSXLPLHAZUCYIL6/graph.json","fetch_events":"https://pith.science/api/pith-number/EUCIWHZUCAGOSXLPLHAZUCYIL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6/action/storage_attestation","attest_author":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6/action/author_attestation","sign_citation":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6/action/citation_signature","submit_replication":"https://pith.science/pith/EUCIWHZUCAGOSXLPLHAZUCYIL6/action/replication_record"}},"created_at":"2026-07-05T07:58:03.242727+00:00","updated_at":"2026-07-05T07:58:03.242727+00:00"}