{"as_of":"2026-08-23T08:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2952ee9ea6c0cd4c14c6cb26ed4d186d9a7967751e48d0588f40d57d8875992b","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-20T22:08:45.016196Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T10:41:08.967261Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.18825","snapshot_observed_at":"2026-07-14T10:41:08.967261Z","title":"Not all tokens are worth caching: Learning semantic- aware eviction for LLM prefix caches,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.10582","last_updated":"2026-07-12T05:35:26Z","snapshot_observed_at":"2026-08-21T08:29:21.515207Z","submitted_at":"2026-07-12T05:35:26Z","title":"MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-14T10:41:08.967261Z"},"links":{"cited_paper":"/paper/2605.18825","citing_paper":"/paper/2607.10582"},"observation_digest":"sha256:83915a468eb780413725cb100fb41c99a00862e4b4d612c7fc45314c5d0ea5bb","observation_id":"cf72e7fd-b383-499b-a431-a20a9ebec4c2","resolution":{"observed_at":"2026-07-14T10:41:08.967261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.18825/citation-record","integrity":"/paper/2605.18825/integrity","json":"/paper/2605.18825/citation-record.json","paper":"/paper/2605.18825"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gonzalez and Clark W","venue":null,"work_id":"748f2cd2-4cb8-41c1-91a2-8f147d71465d","year":2024},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:9116a799b4c3df816d120345022a5ea1e7b8a3d8c9dd325e2d120eaf54d191e3","observation_id":"25c6b07b-0a5e-4d25-9cdd-d47df59e1cf8","resolution":{"observed_at":"2026-05-20T22:09:07.787084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention , booktitle =","venue":null,"work_id":"52efc12c-5393-4bd9-bd1f-bda5ecd50c94","year":2024},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:9b64758c8c0c5a14a79148726d897c6cb7b6b5aae68340b9c0e2a8aa376dcfbd","observation_id":"9a54bd5d-6c5c-443a-baa2-bd1c3e134544","resolution":{"observed_at":"2026-05-20T22:09:07.750572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The Thirteenth International Conference on Learning Representations","venue":null,"work_id":"54d7a96c-07ff-4d08-a4e9-bb209e4020c8","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:c1a512792c09abca6cb0b31eb13f2533f2fd18314ab27c07dfb6624b1bf7dec8","observation_id":"7e884ae1-2dbf-4ec7-b2c4-fa408dea7869","resolution":{"observed_at":"2026-05-20T22:09:07.777996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"2025 , eprint=","venue":null,"work_id":"cfa4f000-d6b2-40b8-b0f3-395d6b9e184d","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:2c2caae02f0878ff30b9af577d00ea4423e74eee4236b743d93720be44cc7cb4","observation_id":"287ad4b2-6007-4523-95f6-ee90fac8d837","resolution":{"observed_at":"2026-05-20T22:09:07.754299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"2025 , eprint=","venue":null,"work_id":"7b0b3f12-ae86-48fa-9f0d-c26c4b796167","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:93cac670c636c17f5002ca39b87535015d351601747d55d5e486b9d1c084b9f8","observation_id":"30a22117-dc70-4a1c-9726-12149b80bd92","resolution":{"observed_at":"2026-05-20T22:09:07.759517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learned Prefix Caching for Efficient","venue":null,"work_id":"f92fcf1d-bac8-4e11-9385-2204ece886a9","year":2026},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:45d5c6ed640a134af4e79b25a3ed47f701495e1afed4eb41d6bf66632c8d8498","observation_id":"3f6588c1-3427-483e-b8f6-71085a2ec512","resolution":{"observed_at":"2026-05-20T22:09:07.765623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"QWEN Bailian usage traces (anon.)","venue":null,"work_id":"0d2f397c-8956-4dd1-80a8-9edaff5cc4ab","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:4f8e725409cfedb4d8230381453cd515dfdd289d2192c57785f71ca74a987591","observation_id":"946af7ae-3d2b-44d2-b01b-9dc3e34ecdb6","resolution":{"observed_at":"2026-05-20T22:09:07.773394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"5803.2025","doi":"10.1109/iwqos65803.2025.11143380","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Unicache: A unified batch-level learning-based content caching","venue":null,"work_id":"a322d649-9017-41eb-832e-0f3f40baf352","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:068a16608952f0ce57541a40898b78a43925de9f3ef9302768f9c356829e0e22","observation_id":"176759fe-8140-4c63-b50d-ff26d65463aa","resolution":{"observed_at":"2026-05-20T22:09:06.583928Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.emnlp-main.810","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Token prediction as implicit classification to identify LLM -generated text","venue":null,"work_id":"34103b10-143b-4713-abc0-3b9c7b73ff0a","year":2023},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:15a5233cc9cc00ec4c841fcd9502e9aac829140e6abcaa0a195ff02daa72bc35","observation_id":"3e535bcb-a957-4ae8-b71c-de68cddc909f","resolution":{"observed_at":"2026-05-20T22:09:06.591135Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cost-efficient large language model serving for multi-turn conversations with cachedattention","venue":null,"work_id":"2b146c7f-65f5-4a1f-9879-fc1d9213ce2e","year":2024},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:9821b85cb43776f4e55a69c3aea1be4c84b470c80417ca962ce509d1c73499e2","observation_id":"13527145-d746-4e92-b1a2-107121e6b2fa","resolution":{"observed_at":"2026-05-20T22:09:07.783225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"0006.361316","doi":"10.1145/3600006.3613163","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention , booktitle =","venue":null,"work_id":"1b10f2a9-a178-4d23-97fb-8db2354c7e6c","year":2023},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:399dfb49a006ea46125cac2e12bee0308b3445d60f73b71eaee5697ba2232089","observation_id":"0fdbb4bb-1968-4bcf-a4d0-4431f548ebbd","resolution":{"observed_at":"2026-05-20T22:09:06.601169Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.02230","last_updated":"2026-05-25T23:34:23Z","snapshot_observed_at":"2026-08-20T02:29:27.571369Z","submitted_at":"2025-11-04T03:43:05Z","title":"Continuum: Efficient and Robust Multi-Turn LLM Agent Scheduling with KV Cache Time-to-Live","version":6},"cited_work":{"arxiv_id":"2511.02230","doi":"10.48550/arxiv.2511.02230","metadata_source":"pith","pith_arxiv_id":"2511.02230","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Continuum: Efficient and Robust Multi-Turn LLM Agent Scheduling with KV Cache Time-to-Live","venue":"cs.OS","work_id":"50faa21f-3471-40f4-bc11-18d9804c0576","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"cited_paper":"/paper/2511.02230","citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:0234acb0f2fe6025e41143217684a4b950d718733a3e05222096173abe008e1a","observation_id":"7f108d38-d26a-4f55-9ae2-4b854f539519","resolution":{"observed_at":"2026-05-20T22:09:06.568706Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19379","last_updated":"2025-04-10T05:06:29Z","snapshot_observed_at":"2026-08-16T06:11:44.384590Z","submitted_at":"2024-11-28T21:10:20Z","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","version":3},"cited_work":{"arxiv_id":"2411.19379","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.19379","snapshot_observed_at":"2026-07-04T07:29:39.044039Z","title":"Marconi: Prefix caching for the era of hybrid llms","venue":null,"work_id":"03b57d6a-20bc-4aa0-96d6-67aaf18b6a1f","year":2024},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"cited_paper":"/paper/2411.19379","citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:9fff4005da8bc3aab5d91ed51ddb56818a4c83ed6c02c2481190f624951a954d","observation_id":"e176b16c-08e1-4438-9d7e-68302af0c6c8","resolution":{"observed_at":"2026-05-20T22:09:07.011959Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.07400","last_updated":"2025-07-10T03:39:23Z","snapshot_observed_at":"2026-08-21T10:43:57.862686Z","submitted_at":"2025-07-10T03:39:23Z","title":"KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows","version":1},"cited_work":{"arxiv_id":"2507.07400","doi":"10.48550/arxiv.2507.07400","metadata_source":"arxiv_reference","pith_arxiv_id":"2507.07400","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Kvflow: Efficient prefix caching for accelerating llm-based multi-agent workflows, 2025 b","venue":"ArXiv.org","work_id":"bebb74f0-0026-4dbc-b12f-9cf357437882","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"cited_paper":"/paper/2507.07400","citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:b8ad7135a0ce1cdde9fd1a40f00167564a2d8e7eaf820a560946b7aed341c591","observation_id":"d7ec5bef-2697-4fe9-be9a-fa4b5f8e50a3","resolution":{"observed_at":"2026-05-20T22:09:07.016867Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Preble: Efficient distributed prompt scheduling for LLM serving","venue":null,"work_id":"228940a6-e2fb-4dc7-9ad0-4d7936b52b58","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:b065cb700ecf0e7b71e2576e3db2a7c00c8dad450b9aefc8c81e0cbcfc71710e","observation_id":"3b68995f-6bd6-435a-85eb-9440e5820ee4","resolution":{"observed_at":"2026-05-20T22:09:07.743158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learned prefix caching for efficient LLM inference","venue":null,"work_id":"27eac4c5-c28d-4984-a49f-6a88a25b3da3","year":2026},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:74f17f675e9915c26a35ce9c41b106894dc6bf47cbba7a8abb9f510cd9aeb729","observation_id":"7cea0dd1-b8c9-4162-b42d-0c0a7161c3be","resolution":{"observed_at":"2026-05-20T22:09:07.735076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"CC-Bench trajectories: Agentic coding task trajectories","venue":null,"work_id":"7a273c08-3a14-48bb-8c3a-6b8f39977abd","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:38f4e921226b59dfc2a4de1bddf6024e7b7d4a94857141cd18915c1da51ac4bb","observation_id":"88f6127d-6148-4e40-8d08-48b7bd619163","resolution":{"observed_at":"2026-05-20T22:09:07.739223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1569.376482","doi":"10.1145/3731569.3764820","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Jenga: Effective memory management for serving LLM with heterogeneity","venue":null,"work_id":"02603c5b-363e-4fe0-b044-c59cd6dcef04","year":2025},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:34a48be2ce1b4c620ad28ae4a7c8f38ed8c8975130e839abce41fc523def7f28","observation_id":"70da8ef4-c32d-42a0-a79e-9146900d9507","resolution":{"observed_at":"2026-05-20T22:09:06.607602Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gonzalez, Clark W","venue":null,"work_id":"c9305e07-3299-49e8-8d36-fb809970b7dd","year":2024},"citing_paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-05-20T22:08:45.016196Z"},"links":{"citing_paper":"/paper/2605.18825"},"observation_digest":"sha256:4c79ed7c763ebeccdbfa5aed6a2e2f1876a91c64921842414faa8e987701bfbd","observation_id":"9dceac49-8284-4ee1-8c5b-62768e437d6c","resolution":{"observed_at":"2026-05-20T22:09:07.746684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.18825","last_updated":"2026-05-12T18:38:24Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T20:26:58.135553Z","submitted_at":"2026-05-12T18:38:24Z","title":"Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":0,"verified_exact":5,"verified_fuzzy":12},"total_outbound_references":19},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 1 inbound Pith citation observation for arXiv:2605.18825."}