{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RHBC7CNYI5MGVJ7K35VMVDOJGX","short_pith_number":"pith:RHBC7CNY","canonical_record":{"source":{"id":"2505.16210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T04:23:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e1ca5c25f639bf469ffeeff716854118c0483abba19871118d2871a70d723061","abstract_canon_sha256":"5847afeeb882a5507a3eeed30964ff3af54d1906045458a105f2e263d6ca2093"},"schema_version":"1.0"},"canonical_sha256":"89c22f89b847586aa7eadf6aca8dc935cce8200ef895f33378f5efeb1b8e9e6b","source":{"kind":"arxiv","id":"2505.16210","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16210","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16210v1","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16210","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"pith_short_12","alias_value":"RHBC7CNYI5MG","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"pith_short_16","alias_value":"RHBC7CNYI5MGVJ7K","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"pith_short_8","alias_value":"RHBC7CNY","created_at":"2026-07-05T11:07:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RHBC7CNYI5MGVJ7K35VMVDOJGX","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T04:23:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e1ca5c25f639bf469ffeeff716854118c0483abba19871118d2871a70d723061","abstract_canon_sha256":"5847afeeb882a5507a3eeed30964ff3af54d1906045458a105f2e263d6ca2093"},"schema_version":"1.0"},"canonical_sha256":"89c22f89b847586aa7eadf6aca8dc935cce8200ef895f33378f5efeb1b8e9e6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:31.742976Z","signature_b64":"spI1DKmjNK26AiPFKEm4nlltcymxGMJ5Z//uymeppGgCqRHCYA5pV35b2KozZMS64nxHQTccxergLXWj/T8BBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c22f89b847586aa7eadf6aca8dc935cce8200ef895f33378f5efeb1b8e9e6b","last_reissued_at":"2026-07-05T11:07:31.742523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:31.742523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16210","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PClCZCfFGi4ccsSpkxYxJa0ycpFbjJ8F3zjz8oYcwORPby1XKAHIsNE0Lcp3kqzi7EjgAHyJxaJV6suwWJWdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:42:04.707234Z"},"content_sha256":"65cc89077cd7466fbcd527a8ecf4f071382670fe47c2facea215bff3bb5cbc80","schema_version":"1.0","event_id":"sha256:65cc89077cd7466fbcd527a8ecf4f071382670fe47c2facea215bff3bb5cbc80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RHBC7CNYI5MGVJ7K35VMVDOJGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NQKV: A KV Cache Quantization Scheme Based on Normal Distribution Characteristics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Xingjun Zhang, Zhendong Tan, Zheng Wei, Zhihang Cai","submitted_at":"2025-05-22T04:23:19Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly increases the memory resource consumption of the Key-Value (KV) cache during inference, becoming a major bottleneck in LLM deployment. To address this issue, quantization is a common and straightforward approach. Currently, quantization methods for activations are limited to 8-bit, and quantization to even lower bits can lead to substantial accuracy drops. To f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16210","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/2505.16210/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nexIJgjbmztUQdVu+H25yD9lT5E82YgCh1MJY9PmLhX0iQsGOqSgGcLqOtARF/t2JKw2b03b46nAuDb31hl+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:42:04.707619Z"},"content_sha256":"ff19be0b5791edd16ee019427895e9315401028ec4dc770b5797bf3dc2009f73","schema_version":"1.0","event_id":"sha256:ff19be0b5791edd16ee019427895e9315401028ec4dc770b5797bf3dc2009f73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHBC7CNYI5MGVJ7K35VMVDOJGX/bundle.json","state_url":"https://pith.science/pith/RHBC7CNYI5MGVJ7K35VMVDOJGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHBC7CNYI5MGVJ7K35VMVDOJGX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T03:42:04Z","links":{"resolver":"https://pith.science/pith/RHBC7CNYI5MGVJ7K35VMVDOJGX","bundle":"https://pith.science/pith/RHBC7CNYI5MGVJ7K35VMVDOJGX/bundle.json","state":"https://pith.science/pith/RHBC7CNYI5MGVJ7K35VMVDOJGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHBC7CNYI5MGVJ7K35VMVDOJGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RHBC7CNYI5MGVJ7K35VMVDOJGX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5847afeeb882a5507a3eeed30964ff3af54d1906045458a105f2e263d6ca2093","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T04:23:19Z","title_canon_sha256":"e1ca5c25f639bf469ffeeff716854118c0483abba19871118d2871a70d723061"},"schema_version":"1.0","source":{"id":"2505.16210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16210","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16210v1","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16210","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"pith_short_12","alias_value":"RHBC7CNYI5MG","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"pith_short_16","alias_value":"RHBC7CNYI5MGVJ7K","created_at":"2026-07-05T11:07:31Z"},{"alias_kind":"pith_short_8","alias_value":"RHBC7CNY","created_at":"2026-07-05T11:07:31Z"}],"graph_snapshots":[{"event_id":"sha256:ff19be0b5791edd16ee019427895e9315401028ec4dc770b5797bf3dc2009f73","target":"graph","created_at":"2026-07-05T11:07:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.16210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly increases the memory resource consumption of the Key-Value (KV) cache during inference, becoming a major bottleneck in LLM deployment. To address this issue, quantization is a common and straightforward approach. Currently, quantization methods for activations are limited to 8-bit, and quantization to even lower bits can lead to substantial accuracy drops. To f","authors_text":"Xingjun Zhang, Zhendong Tan, Zheng Wei, Zhihang Cai","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T04:23:19Z","title":"NQKV: A KV Cache Quantization Scheme Based on Normal Distribution Characteristics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16210","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:65cc89077cd7466fbcd527a8ecf4f071382670fe47c2facea215bff3bb5cbc80","target":"record","created_at":"2026-07-05T11:07:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5847afeeb882a5507a3eeed30964ff3af54d1906045458a105f2e263d6ca2093","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T04:23:19Z","title_canon_sha256":"e1ca5c25f639bf469ffeeff716854118c0483abba19871118d2871a70d723061"},"schema_version":"1.0","source":{"id":"2505.16210","kind":"arxiv","version":1}},"canonical_sha256":"89c22f89b847586aa7eadf6aca8dc935cce8200ef895f33378f5efeb1b8e9e6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89c22f89b847586aa7eadf6aca8dc935cce8200ef895f33378f5efeb1b8e9e6b","first_computed_at":"2026-07-05T11:07:31.742523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:31.742523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"spI1DKmjNK26AiPFKEm4nlltcymxGMJ5Z//uymeppGgCqRHCYA5pV35b2KozZMS64nxHQTccxergLXWj/T8BBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:31.742976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65cc89077cd7466fbcd527a8ecf4f071382670fe47c2facea215bff3bb5cbc80","sha256:ff19be0b5791edd16ee019427895e9315401028ec4dc770b5797bf3dc2009f73"],"state_sha256":"e5c95abc155c6cc09c4bca563376cd4ac63cab0135518d7df383e1d6f1f617ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tBMWF13nZWXET9kO+VeuiBjuwyYH+gohvEP8mXg1dDjbOM1aNVGY5EqAzyhi7uZxAOpOx18bzZfn2IQx8xsZCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:42:04.710062Z","bundle_sha256":"6ea3c88b4c989fccb245034ba25c7df49ff798b167c2f78bdf6997246b00e161"}}