{"as_of":"2026-08-07T18:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4ad99e13e9540e429e4cec1162691de80d25789c09c9fbb03a83510b356e237f","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:51:53.296205Z","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":"2026-07-01T21:56:15.724063Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.20552","last_updated":"2025-03-26T13:48:35Z","snapshot_observed_at":"2026-08-07T16:35:30.599070Z","submitted_at":"2025-03-26T13:48:35Z","title":"Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20552","snapshot_observed_at":"2026-08-07T00:51:53.296205Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12708","last_updated":"2025-06-19T12:27:10Z","snapshot_observed_at":"2026-08-07T00:41:26.353928Z","submitted_at":"2025-06-15T03:41:34Z","title":"Serving Large Language Models on Huawei CloudMatrix384","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T00:51:53.296205Z"},"links":{"cited_paper":"/paper/2503.20552","citing_paper":"/paper/2506.12708"},"observation_digest":"sha256:5a0ea1a685e9cb49250deac54ce6e59dcccbe538d49f750a13e184506e900e6a","observation_id":"f71bca3b-0307-4582-a210-56e50cda3acf","resolution":{"observed_at":"2026-08-07T00:51:53.296205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20552","last_updated":"2025-03-26T13:48:35Z","snapshot_observed_at":"2026-08-07T16:35:30.599070Z","submitted_at":"2025-03-26T13:48:35Z","title":"Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation","version":1},"cited_work":{"arxiv_id":"2503.20552","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20552","snapshot_observed_at":"2026-07-01T21:56:15.724063Z","title":null,"venue":null,"work_id":"3142c487-1494-4a2f-bbe1-cb4b4e10b03b","year":2025},"citing_paper":{"arxiv_id":"2606.01502","last_updated":"2026-05-31T23:53:24Z","snapshot_observed_at":"2026-08-01T12:05:36.187697Z","submitted_at":"2026-05-31T23:53:24Z","title":"Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T16:02:53.294235Z"},"links":{"cited_paper":"/paper/2503.20552","citing_paper":"/paper/2606.01502"},"observation_digest":"sha256:36426da9ee54f905ea5a80aee1ff388bf902ed6db0c0a533f429170ed5bc837e","observation_id":"bb5949f9-76b2-42ab-8c82-18a94e730760","resolution":{"observed_at":"2026-07-01T21:56:15.725752Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.20552/citation-record","integrity":"/paper/2503.20552/integrity","json":"/paper/2503.20552/citation-record.json","paper":"/paper/2503.20552"},"outbound":[],"paper":{"arxiv_id":"2503.20552","last_updated":"2025-03-26T13:48:35Z","latest_version":1,"primary_category":"cs.DC","snapshot_observed_at":"2026-08-07T16:35:30.599070Z","submitted_at":"2025-03-26T13:48:35Z","title":"Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2503.20552."}