{"as_of":"2026-08-09T09:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0dad2e4dc830e17d72d6ead3f2f6ed7e03442ed5c7058943bc334ee01a2f8b38","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":"2026-08-06T13:57:15.821815Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-10T01:36:44.144655Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.03917","last_updated":"2024-05-07T00:25:20Z","snapshot_observed_at":"2026-07-06T18:10:45.376531Z","submitted_at":"2024-05-07T00:25:20Z","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","version":1},"cited_work":{"arxiv_id":"2405.03917","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.03917","snapshot_observed_at":"2026-07-10T01:36:44.144655Z","title":"Kv cache is 1 bit per channel: Efficient large language model inference with coupled quantization","venue":"cs.LG","work_id":"0930f4ab-881c-4719-8e81-9389286a4532","year":2024},"citing_paper":{"arxiv_id":"2504.19874","last_updated":"2025-04-28T15:05:35Z","snapshot_observed_at":"2026-08-01T14:10:27.172555Z","submitted_at":"2025-04-28T15:05:35Z","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-20T08:09:22.226608Z"},"links":{"cited_paper":"/paper/2405.03917","citing_paper":"/paper/2504.19874"},"observation_digest":"sha256:30649dfc6ad177b27cb1f3f1024e213c05a2c1a37b8cb5bd2e32a68d4314eb2b","observation_id":"0c04dabc-3b5d-43dc-a42e-79054b65ac2a","resolution":{"observed_at":"2026-05-20T08:09:22.411208Z","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":"2405.03917","last_updated":"2024-05-07T00:25:20Z","snapshot_observed_at":"2026-07-06T18:10:45.376531Z","submitted_at":"2024-05-07T00:25:20Z","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.03917","snapshot_observed_at":"2026-08-06T13:57:15.821815Z","title":"Kv cache is 1 bit per channel: Efficient large language model inference with coupled quantization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.19906","last_updated":"2025-08-04T08:19:26Z","snapshot_observed_at":"2026-08-08T09:20:56.167689Z","submitted_at":"2025-07-26T10:34:53Z","title":"CaliDrop: KV Cache Compression with Calibration","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T13:57:15.821815Z"},"links":{"cited_paper":"/paper/2405.03917","citing_paper":"/paper/2507.19906"},"observation_digest":"sha256:75b175bd3d126bb89c34c15196c494ebfcbdd46b383b6eaf6390efe38f990ef0","observation_id":"0aef9934-a407-4c49-8162-428eb3976373","resolution":{"observed_at":"2026-08-06T13:57:15.821815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03917","last_updated":"2024-05-07T00:25:20Z","snapshot_observed_at":"2026-07-06T18:10:45.376531Z","submitted_at":"2024-05-07T00:25:20Z","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","version":1},"cited_work":{"arxiv_id":"2405.03917","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.03917","snapshot_observed_at":"2026-07-10T01:36:44.144655Z","title":"Kv cache is 1 bit per channel: Efficient large language model inference with coupled quantization","venue":"cs.LG","work_id":"0930f4ab-881c-4719-8e81-9389286a4532","year":2024},"citing_paper":{"arxiv_id":"2607.08032","last_updated":"2026-07-09T01:15:03Z","snapshot_observed_at":"2026-08-02T16:38:21.894642Z","submitted_at":"2026-07-09T01:15:03Z","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","version":1},"reference_index":148,"source":"pdf_text","source_observed_at":"2026-07-10T01:26:59.421158Z"},"links":{"cited_paper":"/paper/2405.03917","citing_paper":"/paper/2607.08032"},"observation_digest":"sha256:ebc63b845be081c77b54a767bbf51decf60b43595af7d9ffb1d3fc1302a60e4b","observation_id":"5150f09a-df9f-40a6-a18e-a57a59854d2c","resolution":{"observed_at":"2026-07-10T01:36:44.146556Z","resolver_source":"local_arxiv","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/2405.03917/citation-record","integrity":"/paper/2405.03917/integrity","json":"/paper/2405.03917/citation-record.json","paper":"/paper/2405.03917"},"outbound":[],"paper":{"arxiv_id":"2405.03917","last_updated":"2024-05-07T00:25:20Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:10:45.376531Z","submitted_at":"2024-05-07T00:25:20Z","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization"},"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:2405.03917."}