{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MDKHGZ274OU37MDK547FMZZZ74","short_pith_number":"pith:MDKHGZ27","canonical_record":{"source":{"id":"2411.05787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T18:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"1087110f4061b98e5bd82a1dc99afedf0f9cf3e3fbc8284faf47b9776c2a5e73","abstract_canon_sha256":"05d31c1f94ec79b2c0a348bf63193655ebe0992e3b1d58725aad3cf508b4888f"},"schema_version":"1.0"},"canonical_sha256":"60d473675fe3a9bfb06aef3e566739ff008f63a209587a46830932c8ae53da30","source":{"kind":"arxiv","id":"2411.05787","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05787","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05787v2","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05787","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"MDKHGZ274OU3","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"pith_short_16","alias_value":"MDKHGZ274OU37MDK","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"pith_short_8","alias_value":"MDKHGZ27","created_at":"2026-07-05T10:22:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MDKHGZ274OU37MDK547FMZZZ74","target":"record","payload":{"canonical_record":{"source":{"id":"2411.05787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T18:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"1087110f4061b98e5bd82a1dc99afedf0f9cf3e3fbc8284faf47b9776c2a5e73","abstract_canon_sha256":"05d31c1f94ec79b2c0a348bf63193655ebe0992e3b1d58725aad3cf508b4888f"},"schema_version":"1.0"},"canonical_sha256":"60d473675fe3a9bfb06aef3e566739ff008f63a209587a46830932c8ae53da30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:53.681357Z","signature_b64":"AMa69KPe5Fzn+jHL9GDjkwJ93EmBxL5aqYjn0YjW13y6M48k4rgEWd3q81bjPfMjwmt9fU/02UNR1oDK6PA/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60d473675fe3a9bfb06aef3e566739ff008f63a209587a46830932c8ae53da30","last_reissued_at":"2026-07-05T10:22:53.680773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:53.680773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.05787","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eMh8iA+GmoO6HSIhQUSCyhC00URxiW7AkQJXY+wYoZQBD9eNfEUYz90NCGYdz9bXifEfC4pIxVpQWj1Mw9S2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:04:20.983445Z"},"content_sha256":"445cdf405147173e161059f7847a1d733ddab97e28bd5b04f0f686ca9115b8a2","schema_version":"1.0","event_id":"sha256:445cdf405147173e161059f7847a1d733ddab97e28bd5b04f0f686ca9115b8a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MDKHGZ274OU37MDK547FMZZZ74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RefreshKV: Updating Small KV Cache During Long-form Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Fangyuan Xu, Tanya Goyal","submitted_at":"2024-11-08T18:57:07Z","abstract_excerpt":"Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache, relieving LLMs from computing attention over a long sequence of tokens. While such methods work well to generate short sequences, their performance degrades rapidly for long-form generation. Most KV compression happens once, prematurely removing tokens that can be useful later in the generation. We propose a new inference method, RefreshKV, that flexibly alternate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05787","kind":"arxiv","version":2},"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/2411.05787/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":"2026-07-05T10:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1NW9gQdIrAYK0Q1hcgWZRN6+eM5ToZShCuId/5sov9vxlNm9FCM9L10p1tOS15TdfilrpqUhApMlNXgY9PcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:04:20.983946Z"},"content_sha256":"c97bcc7aba7afa9db450ded5a8c4d7691f2b127d4659d6386a7dc0143c1820ad","schema_version":"1.0","event_id":"sha256:c97bcc7aba7afa9db450ded5a8c4d7691f2b127d4659d6386a7dc0143c1820ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MDKHGZ274OU37MDK547FMZZZ74/bundle.json","state_url":"https://pith.science/pith/MDKHGZ274OU37MDK547FMZZZ74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MDKHGZ274OU37MDK547FMZZZ74/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":"2026-08-08T22:04:20Z","links":{"resolver":"https://pith.science/pith/MDKHGZ274OU37MDK547FMZZZ74","bundle":"https://pith.science/pith/MDKHGZ274OU37MDK547FMZZZ74/bundle.json","state":"https://pith.science/pith/MDKHGZ274OU37MDK547FMZZZ74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MDKHGZ274OU37MDK547FMZZZ74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MDKHGZ274OU37MDK547FMZZZ74","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":"05d31c1f94ec79b2c0a348bf63193655ebe0992e3b1d58725aad3cf508b4888f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T18:57:07Z","title_canon_sha256":"1087110f4061b98e5bd82a1dc99afedf0f9cf3e3fbc8284faf47b9776c2a5e73"},"schema_version":"1.0","source":{"id":"2411.05787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05787","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05787v2","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05787","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"MDKHGZ274OU3","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"pith_short_16","alias_value":"MDKHGZ274OU37MDK","created_at":"2026-07-05T10:22:53Z"},{"alias_kind":"pith_short_8","alias_value":"MDKHGZ27","created_at":"2026-07-05T10:22:53Z"}],"graph_snapshots":[{"event_id":"sha256:c97bcc7aba7afa9db450ded5a8c4d7691f2b127d4659d6386a7dc0143c1820ad","target":"graph","created_at":"2026-07-05T10:22:53Z","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/2411.05787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache, relieving LLMs from computing attention over a long sequence of tokens. While such methods work well to generate short sequences, their performance degrades rapidly for long-form generation. Most KV compression happens once, prematurely removing tokens that can be useful later in the generation. We propose a new inference method, RefreshKV, that flexibly alternate","authors_text":"Eunsol Choi, Fangyuan Xu, Tanya Goyal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T18:57:07Z","title":"RefreshKV: Updating Small KV Cache During Long-form Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05787","kind":"arxiv","version":2},"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":"sha256:445cdf405147173e161059f7847a1d733ddab97e28bd5b04f0f686ca9115b8a2","target":"record","created_at":"2026-07-05T10:22:53Z","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":"05d31c1f94ec79b2c0a348bf63193655ebe0992e3b1d58725aad3cf508b4888f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T18:57:07Z","title_canon_sha256":"1087110f4061b98e5bd82a1dc99afedf0f9cf3e3fbc8284faf47b9776c2a5e73"},"schema_version":"1.0","source":{"id":"2411.05787","kind":"arxiv","version":2}},"canonical_sha256":"60d473675fe3a9bfb06aef3e566739ff008f63a209587a46830932c8ae53da30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60d473675fe3a9bfb06aef3e566739ff008f63a209587a46830932c8ae53da30","first_computed_at":"2026-07-05T10:22:53.680773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:53.680773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AMa69KPe5Fzn+jHL9GDjkwJ93EmBxL5aqYjn0YjW13y6M48k4rgEWd3q81bjPfMjwmt9fU/02UNR1oDK6PA/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:53.681357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:445cdf405147173e161059f7847a1d733ddab97e28bd5b04f0f686ca9115b8a2","sha256:c97bcc7aba7afa9db450ded5a8c4d7691f2b127d4659d6386a7dc0143c1820ad"],"state_sha256":"56d1ac7d5764ccfad8f626bcdbd5a7c936e438e9bbbba1cf48d061668477925d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/L7ZFI0fosrMENu68GiJBh5SDK2cukFsRH8JSvPrfg9kYbQmEL9hfGDeKrIe+6KdTjf/kX6V5RAYrlxCXrtZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:04:20.988551Z","bundle_sha256":"096b130b1e20b1913f5af81a71b972e230c8ad04762a41016013edca5e2963be"}}