{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FIR7I2HYU5GWRZZ7O6MKGYFVVX","short_pith_number":"pith:FIR7I2HY","schema_version":"1.0","canonical_sha256":"2a23f468f8a74d68e73f7798a360b5adfc077092ec29a9fe0165f32edef1ae11","source":{"kind":"arxiv","id":"2607.16248","version":1},"attestation_state":"computed","paper":{"title":"High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donglei Wu, Gradwell Dzikanyanga, Hao Huang, Weihao Yang, Wen Xia, Yanqi Pan","submitted_at":"2026-06-27T01:22:47Z","abstract_excerpt":"Long-context large language model inference relies on the KV cache to avoid redundant attention computation, but incurs high memory and bandwidth overheads. Low-bit KV-cache quantization reduces this cost, yet it severely degrade quality; particularly, one-bit quantization reduces accuracy from 84.2% to 47.8% on Llama-3.1-8B under RULER.\n  Rather than common beliefs that absolute error of logits, we find that the root cause is structured local misranking, where the distribution of logits in top-K region is drifted. We thereby propose local distribution restoration, a new technique that detects"},"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":"2607.16248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T01:22:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"133fc79ddc206db4cb076a0a7d88a77af054ebc7cfd7f3d757ab516f8a321e73","abstract_canon_sha256":"4be2431b46d22825e9b8302f0765a32860b5ee9a219947c960ad8baf877d47ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:08.105715Z","signature_b64":"Lfqa11CKAtu+s2ky9MxQvYTTy9WNVCukmH+tU+wTd0xBOGarMzSEbVAzSS2N5MQokKfncDbNRds84lijmfexBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a23f468f8a74d68e73f7798a360b5adfc077092ec29a9fe0165f32edef1ae11","last_reissued_at":"2026-07-21T00:20:08.104856Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:08.104856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donglei Wu, Gradwell Dzikanyanga, Hao Huang, Weihao Yang, Wen Xia, Yanqi Pan","submitted_at":"2026-06-27T01:22:47Z","abstract_excerpt":"Long-context large language model inference relies on the KV cache to avoid redundant attention computation, but incurs high memory and bandwidth overheads. Low-bit KV-cache quantization reduces this cost, yet it severely degrade quality; particularly, one-bit quantization reduces accuracy from 84.2% to 47.8% on Llama-3.1-8B under RULER.\n  Rather than common beliefs that absolute error of logits, we find that the root cause is structured local misranking, where the distribution of logits in top-K region is drifted. We thereby propose local distribution restoration, a new technique that detects"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16248","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/2607.16248/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":"2607.16248","created_at":"2026-07-21T00:20:08.105285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16248v1","created_at":"2026-07-21T00:20:08.105285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16248","created_at":"2026-07-21T00:20:08.105285+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIR7I2HYU5GW","created_at":"2026-07-21T00:20:08.105285+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIR7I2HYU5GWRZZ7","created_at":"2026-07-21T00:20:08.105285+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIR7I2HY","created_at":"2026-07-21T00:20:08.105285+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/FIR7I2HYU5GWRZZ7O6MKGYFVVX","json":"https://pith.science/pith/FIR7I2HYU5GWRZZ7O6MKGYFVVX.json","graph_json":"https://pith.science/api/pith-number/FIR7I2HYU5GWRZZ7O6MKGYFVVX/graph.json","events_json":"https://pith.science/api/pith-number/FIR7I2HYU5GWRZZ7O6MKGYFVVX/events.json","paper":"https://pith.science/paper/FIR7I2HY"},"agent_actions":{"view_html":"https://pith.science/pith/FIR7I2HYU5GWRZZ7O6MKGYFVVX","download_json":"https://pith.science/pith/FIR7I2HYU5GWRZZ7O6MKGYFVVX.json","view_paper":"https://pith.science/paper/FIR7I2HY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16248&json=true","fetch_graph":"https://pith.science/api/pith-number/FIR7I2HYU5GWRZZ7O6MKGYFVVX/graph.json","fetch_events":"https://pith.science/api/pith-number/FIR7I2HYU5GWRZZ7O6MKGYFVVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIR7I2HYU5GWRZZ7O6MKGYFVVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIR7I2HYU5GWRZZ7O6MKGYFVVX/action/storage_attestation","attest_author":"https://pith.science/pith/FIR7I2HYU5GWRZZ7O6MKGYFVVX/action/author_attestation","sign_citation":"https://pith.science/pith/FIR7I2HYU5GWRZZ7O6MKGYFVVX/action/citation_signature","submit_replication":"https://pith.science/pith/FIR7I2HYU5GWRZZ7O6MKGYFVVX/action/replication_record"}},"created_at":"2026-07-21T00:20:08.105285+00:00","updated_at":"2026-07-21T00:20:08.105285+00:00"}