{"as_of":"2026-08-08T16:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d735ff3df0b5ae2b48d0f4bde79ccc1ec488fa47f8ca7897f753b738d3b31b62","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":"2026-08-07T12:58:04.729125Z","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":"2026-06-30T13:04:40.372153Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.14351","last_updated":"2024-07-25T08:08:11Z","snapshot_observed_at":"2026-08-05T17:30:19.943478Z","submitted_at":"2024-01-25T17:55:07Z","title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14351","snapshot_observed_at":"2026-08-07T12:58:04.729125Z","title":"ServerlessLLM: Locality-Enhanced Serverless Inference for Large Language Models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23072","last_updated":"2025-05-29T04:24:56Z","snapshot_observed_at":"2026-08-07T12:51:48.896109Z","submitted_at":"2025-05-29T04:24:56Z","title":"Speeding up Model Loading with fastsafetensors","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T12:58:04.729125Z"},"links":{"cited_paper":"/paper/2401.14351","citing_paper":"/paper/2505.23072"},"observation_digest":"sha256:52b604b399b3e0144ea1db16f72eaa42c0eae0da00d58c64dbf8a89a57c9a2aa","observation_id":"cda45ea4-2e7e-4ab7-952f-e4009f79e25f","resolution":{"observed_at":"2026-08-07T12:58:04.729125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14351","last_updated":"2024-07-25T08:08:11Z","snapshot_observed_at":"2026-08-05T17:30:19.943478Z","submitted_at":"2024-01-25T17:55:07Z","title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models","version":2},"cited_work":{"arxiv_id":"2401.14351","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.14351","snapshot_observed_at":"2026-06-30T13:04:40.372153Z","title":"Serverlessllm: Low-latency serverless inference for large language models, 2024","venue":null,"work_id":"ec58c310-d55d-46e3-9a4c-4bf3c46c39a5","year":2024},"citing_paper":{"arxiv_id":"2604.24203","last_updated":"2026-04-27T09:07:15Z","snapshot_observed_at":"2026-07-06T23:10:16.426836Z","submitted_at":"2026-04-27T09:07:15Z","title":"Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-08T02:57:11.715370Z"},"links":{"cited_paper":"/paper/2401.14351","citing_paper":"/paper/2604.24203"},"observation_digest":"sha256:0addb05f8caaedc1cf80cc7e1dc32f1ca0c024351f2d6a379c1cd6a1f752dfa7","observation_id":"2a8adde5-7101-4616-a4d9-591ba7208cad","resolution":{"observed_at":"2026-05-11T22:21:31.801281Z","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":"2401.14351","last_updated":"2024-07-25T08:08:11Z","snapshot_observed_at":"2026-08-05T17:30:19.943478Z","submitted_at":"2024-01-25T17:55:07Z","title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models","version":2},"cited_work":{"arxiv_id":"2401.14351","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.14351","snapshot_observed_at":"2026-06-30T13:04:40.372153Z","title":"Serverlessllm: Low-latency serverless inference for large language models, 2024","venue":null,"work_id":"ec58c310-d55d-46e3-9a4c-4bf3c46c39a5","year":2024},"citing_paper":{"arxiv_id":"2605.24754","last_updated":"2026-05-23T22:09:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-23T22:09:34Z","title":"Motion-Compensated Weight Compression","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-30T12:58:27.637822Z"},"links":{"cited_paper":"/paper/2401.14351","citing_paper":"/paper/2605.24754"},"observation_digest":"sha256:94181c23269a25b27ea81b19e88ad45b18cfde19b2bf90ee3258098aaad0c38f","observation_id":"448bd01e-ebc4-4186-8157-b3a019037da5","resolution":{"observed_at":"2026-06-30T13:04:40.373956Z","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/2401.14351/citation-record","integrity":"/paper/2401.14351/integrity","json":"/paper/2401.14351/citation-record.json","paper":"/paper/2401.14351"},"outbound":[],"paper":{"arxiv_id":"2401.14351","last_updated":"2024-07-25T08:08:11Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T17:30:19.943478Z","submitted_at":"2024-01-25T17:55:07Z","title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models"},"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:2401.14351."}