{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RBZF6FO757MOLOM7DAE6HQZRET","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":"3c02d56b6ca32635aff58691eb35b3586b227b47e076c48fba5d7dbe26529972","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T06:43:14Z","title_canon_sha256":"94fd42ea5f7adcd0d2c3840aeb2512a1b0af1d4af7efae8f89bd05ea195eec67"},"schema_version":"1.0","source":{"id":"2507.19823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19823","created_at":"2026-07-05T11:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19823v1","created_at":"2026-07-05T11:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19823","created_at":"2026-07-05T11:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"RBZF6FO757MO","created_at":"2026-07-05T11:43:42Z"},{"alias_kind":"pith_short_16","alias_value":"RBZF6FO757MOLOM7","created_at":"2026-07-05T11:43:42Z"},{"alias_kind":"pith_short_8","alias_value":"RBZF6FO7","created_at":"2026-07-05T11:43:42Z"}],"graph_snapshots":[{"event_id":"sha256:c2ce1423ad5291bf4e90700bd9d60b71ad606ce9a407ec794f11a9c93019ea9d","target":"graph","created_at":"2026-07-05T11:43:42Z","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/2507.19823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Processing long-context inputs with large language models presents a significant challenge due to the enormous memory requirements of the Key-Value (KV) cache during inference. Existing KV cache compression methods exhibit noticeable performance degradation when memory is reduced by more than 85%. Additionally, strategies that leverage GPU-CPU collaboration for approximate attention remain underexplored in this setting. We propose HCAttention, a heterogeneous attention computation framework that integrates key quantization, value offloading, and dynamic KV eviction to enable efficient inferenc","authors_text":"Dongquan Yang, Rong Xiao, Xianbiao Qi, Xiaotian Yu, Yifan Yang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T06:43:14Z","title":"HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19823","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:f140498c2c1a5db27938fda3ea9d0a2ed336b1477d86d1dfbc3b7f0c8906ab8e","target":"record","created_at":"2026-07-05T11:43:42Z","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":"3c02d56b6ca32635aff58691eb35b3586b227b47e076c48fba5d7dbe26529972","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T06:43:14Z","title_canon_sha256":"94fd42ea5f7adcd0d2c3840aeb2512a1b0af1d4af7efae8f89bd05ea195eec67"},"schema_version":"1.0","source":{"id":"2507.19823","kind":"arxiv","version":1}},"canonical_sha256":"88725f15dfefd8e5b99f1809e3c33124f2687403b66c51a19ad2b51f5b2e5cdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88725f15dfefd8e5b99f1809e3c33124f2687403b66c51a19ad2b51f5b2e5cdf","first_computed_at":"2026-07-05T11:43:42.701948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:42.701948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DzxRyt1oh3Jlk+stSCtGVTHnbyMii8tJdoV1vDjEE+S2zvRPFh1Idc6r9l3867gsoBdlcnU5XJmD5gf3kadyBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:42.702404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f140498c2c1a5db27938fda3ea9d0a2ed336b1477d86d1dfbc3b7f0c8906ab8e","sha256:c2ce1423ad5291bf4e90700bd9d60b71ad606ce9a407ec794f11a9c93019ea9d"],"state_sha256":"d9140f57cfba848f7f2f544a5f9532ae58dcecc0c75b8e92fd23c02abd22284d"}