{"as_of":"2026-08-10T15:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:578024f5c0893d56b4cf5f1f3cec7e841b733fcf9cfb5a08a28535c17b15acfd","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":"2026-08-10T06:31:04.303077+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":"2026-08-10T14:59:48.254511Z","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":"2026-08-05T13:15:07.471782Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.11819","last_updated":"2024-10-24T05:53:18Z","snapshot_observed_at":"2026-08-06T23:39:43.807591Z","submitted_at":"2024-02-19T04:19:36Z","title":"Head-wise Shareable Attention for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11819","snapshot_observed_at":"2026-08-10T14:59:48.254511Z","title":"arXiv preprint arXiv:2402.11819","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14713","last_updated":"2025-01-31T17:38:07Z","snapshot_observed_at":"2026-08-10T15:15:05.490321Z","submitted_at":"2025-01-24T18:46:37Z","title":"FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T14:59:48.254511Z"},"links":{"cited_paper":"/paper/2402.11819","citing_paper":"/paper/2501.14713"},"observation_digest":"sha256:ad4a7d4f9f73a9845f96b1aefa4ef5eb4e58bdc3b90f8393d333a5e5226250b7","observation_id":"9d050b94-7530-448f-85c4-29d3b92b4509","resolution":{"observed_at":"2026-08-10T14:59:48.254511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11819","last_updated":"2024-10-24T05:53:18Z","snapshot_observed_at":"2026-08-06T23:39:43.807591Z","submitted_at":"2024-02-19T04:19:36Z","title":"Head-wise Shareable Attention for Large Language Models","version":3},"cited_work":{"arxiv_id":"2402.11819","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.11819","snapshot_observed_at":"2026-08-05T13:15:07.471782Z","title":"Head-wise Shareable Attention for Large Language Models","venue":"cs.CL","work_id":"e2dab638-503d-4a8a-9772-00207ae6cc92","year":2024},"citing_paper":{"arxiv_id":"2509.00925","last_updated":"2025-08-31T16:21:21Z","snapshot_observed_at":"2026-08-09T03:34:12.846656Z","submitted_at":"2025-08-31T16:21:21Z","title":"DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-05T13:15:07.077043Z"},"links":{"cited_paper":"/paper/2402.11819","citing_paper":"/paper/2509.00925"},"observation_digest":"sha256:8911d6f67bba6467d2994d0e0d910965b8dea67e1f825be9fc277d8775605d36","observation_id":"28bde315-1f31-48ed-8b91-c5a66c87cd91","resolution":{"observed_at":"2026-08-05T13:15:07.547386Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.11819/citation-record","integrity":"/paper/2402.11819/integrity","json":"/paper/2402.11819/citation-record.json","paper":"/paper/2402.11819"},"outbound":[],"paper":{"arxiv_id":"2402.11819","last_updated":"2024-10-24T05:53:18Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-06T23:39:43.807591Z","submitted_at":"2024-02-19T04:19:36Z","title":"Head-wise Shareable Attention 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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.11819."}