{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5B6U63D4BI4RAZROAKCED4V6FZ","short_pith_number":"pith:5B6U63D4","schema_version":"1.0","canonical_sha256":"e87d4f6c7c0a3910662e028441f2be2e54bcbcb1b586a1a34470b1765750b616","source":{"kind":"arxiv","id":"2410.13212","version":1},"attestation_state":"computed","paper":{"title":"AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingren Zhou, Qian Tao, Wenyuan Yu","submitted_at":"2024-10-17T04:35:57Z","abstract_excerpt":"Large language models have shown exceptional capabilities in a wide range of tasks, such as text generation and video generation, among others. However, due to their massive parameter count, these models often require substantial storage space, imposing significant constraints on the machines deploying LLMs. To overcome this limitation, one research direction proposes to compress the models using integer replacements for floating-point numbers, in a process known as Quantization. Some recent studies suggest quantizing the key and value cache (KV Cache) of LLMs, and designing quantization techn"},"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":"2410.13212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T04:35:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e69b88793381b3323383378250793a761b37e542c1359979b796d7875819a718","abstract_canon_sha256":"e9cc17913a4ac44b4fbf070a6742d513cfa8a1a63f4cf1dc0a460a390c7ab088"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:57.162852Z","signature_b64":"Nrn+ovT715t646r7blS+IhixHZCeeTGrDpy8ViIhasT4Td3RfbNmneEo2GT2+oHZHxxKNS7INqNUMAAr7PBDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e87d4f6c7c0a3910662e028441f2be2e54bcbcb1b586a1a34470b1765750b616","last_reissued_at":"2026-07-05T09:21:57.162463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:57.162463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingren Zhou, Qian Tao, Wenyuan Yu","submitted_at":"2024-10-17T04:35:57Z","abstract_excerpt":"Large language models have shown exceptional capabilities in a wide range of tasks, such as text generation and video generation, among others. However, due to their massive parameter count, these models often require substantial storage space, imposing significant constraints on the machines deploying LLMs. To overcome this limitation, one research direction proposes to compress the models using integer replacements for floating-point numbers, in a process known as Quantization. Some recent studies suggest quantizing the key and value cache (KV Cache) of LLMs, and designing quantization techn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13212","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/2410.13212/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":"2410.13212","created_at":"2026-07-05T09:21:57.162519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13212v1","created_at":"2026-07-05T09:21:57.162519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13212","created_at":"2026-07-05T09:21:57.162519+00:00"},{"alias_kind":"pith_short_12","alias_value":"5B6U63D4BI4R","created_at":"2026-07-05T09:21:57.162519+00:00"},{"alias_kind":"pith_short_16","alias_value":"5B6U63D4BI4RAZRO","created_at":"2026-07-05T09:21:57.162519+00:00"},{"alias_kind":"pith_short_8","alias_value":"5B6U63D4","created_at":"2026-07-05T09:21:57.162519+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03562","citing_title":"HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24971","citing_title":"PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03562","citing_title":"HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ","json":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ.json","graph_json":"https://pith.science/api/pith-number/5B6U63D4BI4RAZROAKCED4V6FZ/graph.json","events_json":"https://pith.science/api/pith-number/5B6U63D4BI4RAZROAKCED4V6FZ/events.json","paper":"https://pith.science/paper/5B6U63D4"},"agent_actions":{"view_html":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ","download_json":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ.json","view_paper":"https://pith.science/paper/5B6U63D4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13212&json=true","fetch_graph":"https://pith.science/api/pith-number/5B6U63D4BI4RAZROAKCED4V6FZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5B6U63D4BI4RAZROAKCED4V6FZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ/action/storage_attestation","attest_author":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ/action/author_attestation","sign_citation":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ/action/citation_signature","submit_replication":"https://pith.science/pith/5B6U63D4BI4RAZROAKCED4V6FZ/action/replication_record"}},"created_at":"2026-07-05T09:21:57.162519+00:00","updated_at":"2026-07-05T09:21:57.162519+00:00"}