{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KPLWSFH7JI6QQDLVU62VVFVGIX","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":"18b428bf26d42cab40702c97e3a552d392ace3cb97f1f84b9522c5fa3089071e","cross_cats_sorted":["cs.AI","cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T22:17:40Z","title_canon_sha256":"7b495aec909cbdc957ebabdf25a7aacd6d4b720aee9d519e66ccd2a62062737f"},"schema_version":"1.0","source":{"id":"2402.06082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06082","created_at":"2026-07-05T07:43:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06082v1","created_at":"2026-07-05T07:43:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06082","created_at":"2026-07-05T07:43:18Z"},{"alias_kind":"pith_short_12","alias_value":"KPLWSFH7JI6Q","created_at":"2026-07-05T07:43:18Z"},{"alias_kind":"pith_short_16","alias_value":"KPLWSFH7JI6QQDLV","created_at":"2026-07-05T07:43:18Z"},{"alias_kind":"pith_short_8","alias_value":"KPLWSFH7","created_at":"2026-07-05T07:43:18Z"}],"graph_snapshots":[{"event_id":"sha256:0ccaed6d6bb32fa4dc23d37c83d732bdb694f73837b45129fff346be2770324f","target":"graph","created_at":"2026-07-05T07:43:18Z","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/2402.06082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the necessity to store all previous tokens in the attention module, a requirement imposed by key-value (KV) caching. In this work, our focus is on developing an efficient compression technique for the KV cache. Empirical evidence indicates a significant clustering tendency within key embeddings in the attention module. Building on this key insight, we have devised a ","authors_text":"Amin Karbasi, Amir Zandieh, Insu Han, Vahab Mirrokni","cross_cats":["cs.AI","cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T22:17:40Z","title":"SubGen: Token Generation in Sublinear Time and Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06082","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":"sha256:136c8c8b8ecbaa47186667be73abba40d7ccc29ec17ce28c9e27bc5bf1fe1ea3","target":"record","created_at":"2026-07-05T07:43:18Z","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":"18b428bf26d42cab40702c97e3a552d392ace3cb97f1f84b9522c5fa3089071e","cross_cats_sorted":["cs.AI","cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T22:17:40Z","title_canon_sha256":"7b495aec909cbdc957ebabdf25a7aacd6d4b720aee9d519e66ccd2a62062737f"},"schema_version":"1.0","source":{"id":"2402.06082","kind":"arxiv","version":1}},"canonical_sha256":"53d76914ff4a3d080d75a7b55a96a645fc3d1f07793d3b554307728cd2a071c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53d76914ff4a3d080d75a7b55a96a645fc3d1f07793d3b554307728cd2a071c3","first_computed_at":"2026-07-05T07:43:18.312042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:18.312042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WKuEHEZuLsHGq3e8qNMwGxRG1QNwTtACYDYK5BiteR0+MpM80iFLbNiQWAADkc9oHTsCsDtvNBfPPp11xFt5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:18.312576Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:136c8c8b8ecbaa47186667be73abba40d7ccc29ec17ce28c9e27bc5bf1fe1ea3","sha256:0ccaed6d6bb32fa4dc23d37c83d732bdb694f73837b45129fff346be2770324f"],"state_sha256":"49df932203d0161391ff5535db3a4d30eb9252d9d2678d80218b0086ee3ad588"}