{"as_of":"2026-08-08T15:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c10b5954918db33f0b9fc0db5cd69c8ac9cddaf76d2a40f363916d8d1a1512fa","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:16:45.426202Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T07:59:40.308368Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.08585","last_updated":"2024-12-17T05:40:09Z","snapshot_observed_at":"2026-07-06T20:05:23.685854Z","submitted_at":"2024-12-11T18:03:05Z","title":"TurboAttention: Efficient Attention Approximation For High Throughputs LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.08585","snapshot_observed_at":"2026-08-07T14:16:45.426202Z","title":"Turboat- tention: Efficient attention approximation for high throughputs llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.19481","last_updated":"2025-05-26T04:03:48Z","snapshot_observed_at":"2026-08-07T14:11:12.334794Z","submitted_at":"2025-05-26T04:03:48Z","title":"Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:16:45.426202Z"},"links":{"cited_paper":"/paper/2412.08585","citing_paper":"/paper/2505.19481"},"observation_digest":"sha256:8cead5d2fa640b50b41c1bb49743c4c02d302a8deb62b7aa8894bca8a93fcefb","observation_id":"5ef6b394-a704-4f99-9dea-3ab8253335be","resolution":{"observed_at":"2026-08-07T14:16:45.426202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.08585","last_updated":"2024-12-17T05:40:09Z","snapshot_observed_at":"2026-07-06T20:05:23.685854Z","submitted_at":"2024-12-11T18:03:05Z","title":"TurboAttention: Efficient Attention Approximation For High Throughputs LLMs","version":3},"cited_work":{"arxiv_id":"2412.08585","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.08585","snapshot_observed_at":"2026-07-04T07:59:40.308368Z","title":"TurboAttention: Efficient attention approximation for high throughputs LLMs.arXiv preprint arXiv:2412.08585","venue":null,"work_id":"ca4792ec-ec3f-4c6d-8151-358f2456846a","year":null},"citing_paper":{"arxiv_id":"2605.23081","last_updated":"2026-05-21T22:28:27Z","snapshot_observed_at":"2026-08-04T11:05:52.350024Z","submitted_at":"2026-05-21T22:28:27Z","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-25T05:28:40.888215Z"},"links":{"cited_paper":"/paper/2412.08585","citing_paper":"/paper/2605.23081"},"observation_digest":"sha256:a6f322f2d169a661b586b2bd413d9fd75a85ba99ea6ede32af8901476c26bf9f","observation_id":"82b4feb1-9013-4037-ada4-c1f1795d7270","resolution":{"observed_at":"2026-05-25T05:30:22.844922Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.08585","last_updated":"2024-12-17T05:40:09Z","snapshot_observed_at":"2026-07-06T20:05:23.685854Z","submitted_at":"2024-12-11T18:03:05Z","title":"TurboAttention: Efficient Attention Approximation For High Throughputs LLMs","version":3},"cited_work":{"arxiv_id":"2412.08585","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.08585","snapshot_observed_at":"2026-07-04T07:59:40.308368Z","title":"TurboAttention: Efficient attention approximation for high throughputs LLMs.arXiv preprint arXiv:2412.08585","venue":null,"work_id":"ca4792ec-ec3f-4c6d-8151-358f2456846a","year":null},"citing_paper":{"arxiv_id":"2606.21848","last_updated":"2026-07-31T19:30:57Z","snapshot_observed_at":"2026-08-06T23:11:21.421315Z","submitted_at":"2026-06-20T03:12:30Z","title":"Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-06-26T12:20:42.292943Z"},"links":{"cited_paper":"/paper/2412.08585","citing_paper":"/paper/2606.21848"},"observation_digest":"sha256:f9b1ba7075ad4bbb7f301c7c24ff445ba53f1a3129cdb87a19323710cc1e4ed7","observation_id":"7bbc0733-69ea-4a14-b09e-11d81d0d3f85","resolution":{"observed_at":"2026-07-04T07:59:40.309763Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.08585/citation-record","integrity":"/paper/2412.08585/integrity","json":"/paper/2412.08585/citation-record.json","paper":"/paper/2412.08585"},"outbound":[],"paper":{"arxiv_id":"2412.08585","last_updated":"2024-12-17T05:40:09Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T20:05:23.685854Z","submitted_at":"2024-12-11T18:03:05Z","title":"TurboAttention: Efficient Attention Approximation For High Throughputs LLMs"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2412.08585."}