{"as_of":"2026-08-19T10:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b4dc958745a8279f1737e838ac52626e27c49c4fec3ae359744e6fbeb6563a0f","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":"2026-08-19T06:32:44.657259+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":"2026-08-16T12:24:02.398469Z","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":"2026-07-04T08:39:41.979435Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.05248","last_updated":"2025-03-07T09:02:21Z","snapshot_observed_at":"2026-08-18T10:40:23.170895Z","submitted_at":"2025-03-07T09:02:21Z","title":"Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.05248","snapshot_observed_at":"2026-08-16T12:24:02.398469Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.15302","last_updated":"2025-04-17T15:04:47Z","snapshot_observed_at":"2026-08-19T00:54:01.686552Z","submitted_at":"2025-04-17T15:04:47Z","title":"RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T12:24:02.398469Z"},"links":{"cited_paper":"/paper/2503.05248","citing_paper":"/paper/2504.15302"},"observation_digest":"sha256:85097be510f35a93e5e678fcfabe66924a25bc8aa0d8555bd3f35c76f96ff882","observation_id":"adbb3d01-9990-4c71-94d2-fe7ccc6fdbdf","resolution":{"observed_at":"2026-08-16T12:24:02.398469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.05248","last_updated":"2025-03-07T09:02:21Z","snapshot_observed_at":"2026-08-18T10:40:23.170895Z","submitted_at":"2025-03-07T09:02:21Z","title":"Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching","version":1},"cited_work":{"arxiv_id":"2503.05248","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.05248","snapshot_observed_at":"2026-07-04T08:39:41.979435Z","title":"memory shadow","venue":null,"work_id":"d8b724a9-0436-4e13-9eb8-03dd2e25cbc3","year":2025},"citing_paper":{"arxiv_id":"2605.06046","last_updated":"2026-05-07T11:34:10Z","snapshot_observed_at":"2026-08-13T17:59:15.848573Z","submitted_at":"2026-05-07T11:34:10Z","title":"Requests of a Feather Must Flock Together: Batch Size vs. Prefix Homogeneity in LLM Inference","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-08T14:06:01.934357Z"},"links":{"cited_paper":"/paper/2503.05248","citing_paper":"/paper/2605.06046"},"observation_digest":"sha256:b1a5dd6159b6f1649b6ed8b6a3631d394a23c3c9ee1c4f2587c4814f3ef23ca0","observation_id":"b4ae374b-e8a2-48b1-aa1b-93b15d7f55e6","resolution":{"observed_at":"2026-05-11T18:46:09.164546Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.05248","last_updated":"2025-03-07T09:02:21Z","snapshot_observed_at":"2026-08-18T10:40:23.170895Z","submitted_at":"2025-03-07T09:02:21Z","title":"Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching","version":1},"cited_work":{"arxiv_id":"2503.05248","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.05248","snapshot_observed_at":"2026-07-04T08:39:41.979435Z","title":"memory shadow","venue":null,"work_id":"d8b724a9-0436-4e13-9eb8-03dd2e25cbc3","year":2025},"citing_paper":{"arxiv_id":"2606.22327","last_updated":"2026-06-24T14:02:53Z","snapshot_observed_at":"2026-08-14T07:05:03.431408Z","submitted_at":"2026-06-21T04:05:38Z","title":"Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-26T11:17:35.860286Z"},"links":{"cited_paper":"/paper/2503.05248","citing_paper":"/paper/2606.22327"},"observation_digest":"sha256:ee30c4959fd4570ab6abb15c200a509c312074f1ff28ec9b3bbc7db6bf0de7bc","observation_id":"c254bb20-2cd2-4bd7-8017-9d4e69ae1a3b","resolution":{"observed_at":"2026-07-04T08:39:41.980709Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.05248/citation-record","integrity":"/paper/2503.05248/integrity","json":"/paper/2503.05248/citation-record.json","paper":"/paper/2503.05248"},"outbound":[],"paper":{"arxiv_id":"2503.05248","last_updated":"2025-03-07T09:02:21Z","latest_version":1,"primary_category":"cs.DC","snapshot_observed_at":"2026-08-18T10:40:23.170895Z","submitted_at":"2025-03-07T09:02:21Z","title":"Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.05248."}