{"as_of":"2026-08-09T04:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ff921bcb07ff386f0cc118f94c9fcb5308d8b19434ec3907be8c16bf97046a83","coverage":[{"denominator":4,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T20:45:51.193966Z","state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"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":[],"links":{"evidence":"/evidence","html":"/paper/2606.00024/citation-record","integrity":"/paper/2606.00024/integrity","json":"/paper/2606.00024/citation-record.json","paper":"/paper/2606.00024"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.07518","last_updated":"2026-05-14T23:37:13Z","snapshot_observed_at":"2026-07-06T20:50:00.422560Z","submitted_at":"2025-03-10T16:41:14Z","title":"TokenButler: Token Importance is Predictable","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.07518","snapshot_observed_at":"2026-07-12T20:45:51.193966Z","title":"URLhttp://arxiv.org/abs/2503.07518","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.00024","last_updated":"2026-06-15T19:01:17Z","snapshot_observed_at":"2026-08-01T17:09:48.094858Z","submitted_at":"2026-04-15T06:55:14Z","title":"ART: Attention Run-time Termination for Efficient Large Language Model Decoding","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T20:45:51.193966Z"},"links":{"cited_paper":"/paper/2503.07518","citing_paper":"/paper/2606.00024"},"observation_digest":"sha256:726b60a0f86ddec6d39895105c80dd8f3143af35c6ae1a43c7244a142bbaf621","observation_id":"b3d0c913-1852-4810-aaa8-ac78b270358b","resolution":{"observed_at":"2026-07-12T20:45:51.193966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12335","last_updated":"2024-10-02T00:19:13Z","snapshot_observed_at":"2026-08-05T13:25:45.819642Z","submitted_at":"2024-06-18T07:01:11Z","title":"Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.12335","snapshot_observed_at":"2026-07-12T20:45:51.193966Z","title":"URLhttp://arxiv.org/abs/2406.12335","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.00024","last_updated":"2026-06-15T19:01:17Z","snapshot_observed_at":"2026-08-01T17:09:48.094858Z","submitted_at":"2026-04-15T06:55:14Z","title":"ART: Attention Run-time Termination for Efficient Large Language Model Decoding","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T20:45:51.193966Z"},"links":{"cited_paper":"/paper/2406.12335","citing_paper":"/paper/2606.00024"},"observation_digest":"sha256:e0bea446ca3e84022e263c5fb0916261bd24cd1b84db10a869abd09fbaf854ea","observation_id":"5b2cf985-19a3-4ef8-aa5e-ece1f013ada2","resolution":{"observed_at":"2026-07-12T20:45:51.193966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-07-12T20:45:51.193966Z","title":"URLhttp://arxiv.org/abs/2310.06825","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.00024","last_updated":"2026-06-15T19:01:17Z","snapshot_observed_at":"2026-08-01T17:09:48.094858Z","submitted_at":"2026-04-15T06:55:14Z","title":"ART: Attention Run-time Termination for Efficient Large Language Model Decoding","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T20:45:51.193966Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2606.00024"},"observation_digest":"sha256:65bb42326bcd665c8befe601a5daa9796aa7aac3e64bc74b511bb1a4e0991402","observation_id":"6b038ee4-3077-439e-947e-03765fe68c51","resolution":{"observed_at":"2026-07-12T20:45:51.193966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T20:45:51.193966Z","title":"perplexity surge","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.00024","last_updated":"2026-06-15T19:01:17Z","snapshot_observed_at":"2026-08-01T17:09:48.094858Z","submitted_at":"2026-04-15T06:55:14Z","title":"ART: Attention Run-time Termination for Efficient Large Language Model Decoding","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T20:45:51.193966Z"},"links":{"citing_paper":"/paper/2606.00024"},"observation_digest":"sha256:31060b27d84889050bd078dd4b90628bdd3bf19b704c0909129b9c3342095847","observation_id":"77c6ec60-1b11-466c-a099-ca1d44c7d7b5","resolution":{"observed_at":"2026-07-12T20:45:51.193966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.00024","last_updated":"2026-06-15T19:01:17Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-01T17:09:48.094858Z","submitted_at":"2026-04-15T06:55:14Z","title":"ART: Attention Run-time Termination for Efficient Large Language Model Decoding"},"reference_resolution":{"displayed":4,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":4},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2606.00024."}