{"as_of":"2026-08-07T19:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d5c2265377ef715dd5d83930a15425c7a46efd13a2593d0a75b118203fb0e0bc","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":"2026-08-07T06:34:17.273281+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":"2026-07-02T15:14:36.946247Z","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":"2026-07-02T15:17:07.182288Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.04260","last_updated":"2022-02-03T21:26:25Z","snapshot_observed_at":"2026-07-06T11:55:57.117755Z","submitted_at":"2021-10-08T17:15:47Z","title":"Taming Sparsely Activated Transformer with Stochastic Experts","version":3},"cited_work":{"arxiv_id":"2110.04260","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.04260","snapshot_observed_at":"2026-07-02T15:17:07.182288Z","title":"arXiv preprint arXiv:2110.04260 , year=","venue":null,"work_id":"f85ba524-6177-423a-aba7-288d0b57ac47","year":2021},"citing_paper":{"arxiv_id":"2309.14509","last_updated":"2023-10-04T16:51:13Z","snapshot_observed_at":"2026-08-04T19:27:31.715261Z","submitted_at":"2023-09-25T20:15:57Z","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","version":2},"reference_index":167,"source":"arxiv_source","source_observed_at":"2026-05-13T01:07:22.166595Z"},"links":{"cited_paper":"/paper/2110.04260","citing_paper":"/paper/2309.14509"},"observation_digest":"sha256:d490604a1bfd5624d4f00d46357db9c1ddd22673cd879984e117fe4d2ef94cf7","observation_id":"202a855d-5903-44e1-bd12-8d1df84630b8","resolution":{"observed_at":"2026-05-13T01:07:22.292061Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04260","last_updated":"2022-02-03T21:26:25Z","snapshot_observed_at":"2026-07-06T11:55:57.117755Z","submitted_at":"2021-10-08T17:15:47Z","title":"Taming Sparsely Activated Transformer with Stochastic Experts","version":3},"cited_work":{"arxiv_id":"2110.04260","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.04260","snapshot_observed_at":"2026-07-02T15:17:07.182288Z","title":"arXiv preprint arXiv:2110.04260 , year=","venue":null,"work_id":"f85ba524-6177-423a-aba7-288d0b57ac47","year":2021},"citing_paper":{"arxiv_id":"2607.00371","last_updated":"2026-07-01T03:11:21Z","snapshot_observed_at":"2026-08-02T15:32:07.000409Z","submitted_at":"2026-07-01T03:11:21Z","title":"MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-07-02T15:14:36.946247Z"},"links":{"cited_paper":"/paper/2110.04260","citing_paper":"/paper/2607.00371"},"observation_digest":"sha256:897f9567515d80b3edcfefd94e13c8d076324d285e71a0c9792c77f3e76bc69c","observation_id":"543a92b1-cf1d-4faf-8ffe-6e152c431736","resolution":{"observed_at":"2026-07-02T15:17:07.183793Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.04260/citation-record","integrity":"/paper/2110.04260/integrity","json":"/paper/2110.04260/citation-record.json","paper":"/paper/2110.04260"},"outbound":[],"paper":{"arxiv_id":"2110.04260","last_updated":"2022-02-03T21:26:25Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T11:55:57.117755Z","submitted_at":"2021-10-08T17:15:47Z","title":"Taming Sparsely Activated Transformer with Stochastic Experts"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2110.04260."}