{"as_of":"2026-08-12T16:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b262cc17a37de6f76e7fdccf15ee37ae3ba6acbe34882cfb2e7a14c8125a2848","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T11:29:30.975986Z","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":"2026-06-30T13:14:40.891846Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.07306","last_updated":"2021-09-15T14:04:16Z","snapshot_observed_at":"2026-07-06T11:47:57.026683Z","submitted_at":"2021-09-15T14:04:16Z","title":"Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.07306","snapshot_observed_at":"2026-08-11T11:29:30.975986Z","title":"Allocating large vocabulary capacity for cross- lingual language model pre-training,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.15431","last_updated":"2024-12-19T22:29:58Z","snapshot_observed_at":"2026-08-11T11:24:25.202462Z","submitted_at":"2024-12-19T22:29:58Z","title":"Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T11:29:30.975986Z"},"links":{"cited_paper":"/paper/2109.07306","citing_paper":"/paper/2412.15431"},"observation_digest":"sha256:35826e9d93fd639a5381979f48c468d38c6d308b7d5a3cbafe1d517260858349","observation_id":"9cbe1ae1-dfa8-4638-8386-90e8ba6a1f01","resolution":{"observed_at":"2026-08-11T11:29:30.975986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.07306","last_updated":"2021-09-15T14:04:16Z","snapshot_observed_at":"2026-07-06T11:47:57.026683Z","submitted_at":"2021-09-15T14:04:16Z","title":"Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training","version":1},"cited_work":{"arxiv_id":"2109.07306","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.07306","snapshot_observed_at":"2026-06-30T13:14:40.891846Z","title":null,"venue":null,"work_id":"aeb29777-d1ef-4d94-8431-8bbe0f4f2aff","year":null},"citing_paper":{"arxiv_id":"2605.24718","last_updated":"2026-05-23T20:13:44Z","snapshot_observed_at":"2026-08-07T15:18:00.875763Z","submitted_at":"2026-05-23T20:13:44Z","title":"The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-30T13:08:33.172423Z"},"links":{"cited_paper":"/paper/2109.07306","citing_paper":"/paper/2605.24718"},"observation_digest":"sha256:fd6be43efad4e157ffe92529b36d4cf029581ebe6e8e6a40bc469704449e72f7","observation_id":"0f2f0700-0036-400f-a43a-97f333a91fe6","resolution":{"observed_at":"2026-06-30T13:14:40.893204Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2109.07306/citation-record","integrity":"/paper/2109.07306/integrity","json":"/paper/2109.07306/citation-record.json","paper":"/paper/2109.07306"},"outbound":[],"paper":{"arxiv_id":"2109.07306","last_updated":"2021-09-15T14:04:16Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T11:47:57.026683Z","submitted_at":"2021-09-15T14:04:16Z","title":"Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2109.07306."}