{"as_of":"2026-08-09T21:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bb9f0a79946ea0841f87c9bad113c184c88f8151aeb32b40ada47839b05c0c06","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":"2026-08-09T06:31:02.800959+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":"2026-08-06T23:00:11.235417Z","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":"2026-05-20T05:13:03.753402Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.17312","last_updated":"2024-03-26T01:46:34Z","snapshot_observed_at":"2026-08-08T22:15:15.963337Z","submitted_at":"2024-03-26T01:46:34Z","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.17312","snapshot_observed_at":"2026-08-06T23:00:11.235417Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20187","last_updated":"2025-07-02T05:12:29Z","snapshot_observed_at":"2026-08-07T20:42:38.846597Z","submitted_at":"2025-06-25T07:26:42Z","title":"Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:11.235417Z"},"links":{"cited_paper":"/paper/2403.17312","citing_paper":"/paper/2506.20187"},"observation_digest":"sha256:ea02650b0597639b33a41a9e92905cca19870d9f1474f606d15a33e4fcb07a48","observation_id":"dd39bc2f-a8a1-4b66-ac9e-69c0233636d2","resolution":{"observed_at":"2026-08-06T23:00:11.235417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17312","last_updated":"2024-03-26T01:46:34Z","snapshot_observed_at":"2026-08-08T22:15:15.963337Z","submitted_at":"2024-03-26T01:46:34Z","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","version":1},"cited_work":{"arxiv_id":"2403.17312","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.17312","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Merino: Entropy-driven design for generative language models on iot devices","venue":null,"work_id":"050a9645-22c8-4e90-9bb0-8c7a3689caed","year":null},"citing_paper":{"arxiv_id":"2605.00831","last_updated":"2026-03-26T13:27:57Z","snapshot_observed_at":"2026-08-08T10:38:53.859809Z","submitted_at":"2026-03-26T13:27:57Z","title":"GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-15T00:37:08.671539Z"},"links":{"cited_paper":"/paper/2403.17312","citing_paper":"/paper/2605.00831"},"observation_digest":"sha256:f8af4895031bc386602a09ec955f701162528b60e5d0f63fdd7f536350710482","observation_id":"6f8048e6-cdaa-4392-ac5a-1e1291b86f2a","resolution":{"observed_at":"2026-05-15T00:38:23.111335Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17312","last_updated":"2024-03-26T01:46:34Z","snapshot_observed_at":"2026-08-08T22:15:15.963337Z","submitted_at":"2024-03-26T01:46:34Z","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","version":1},"cited_work":{"arxiv_id":"2403.17312","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.17312","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Merino: Entropy-driven design for generative language models on iot devices","venue":null,"work_id":"050a9645-22c8-4e90-9bb0-8c7a3689caed","year":null},"citing_paper":{"arxiv_id":"2605.20179","last_updated":"2026-05-19T17:59:08Z","snapshot_observed_at":"2026-08-06T13:50:23.608176Z","submitted_at":"2026-05-19T17:59:08Z","title":"TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-20T05:08:07.318040Z"},"links":{"cited_paper":"/paper/2403.17312","citing_paper":"/paper/2605.20179"},"observation_digest":"sha256:0b4a5473c46193d305b4a823e9c6cd6dc12defe60c3384898d0439b895cce189","observation_id":"d6e6d716-bb7c-44dc-9b1b-860c560dc3a5","resolution":{"observed_at":"2026-05-20T05:13:03.755282Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.17312/citation-record","integrity":"/paper/2403.17312/integrity","json":"/paper/2403.17312/citation-record.json","paper":"/paper/2403.17312"},"outbound":[],"paper":{"arxiv_id":"2403.17312","last_updated":"2024-03-26T01:46:34Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-08T22:15:15.963337Z","submitted_at":"2024-03-26T01:46:34Z","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2403.17312."}