{"as_of":"2026-08-16T14:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c0d3e6e703fe032f5d866493c936f0899cd710e96fa95f2ff150a04b0b4e5694","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":"2026-08-16T06:30:59.297886+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":"2026-08-16T11:32:06.046705Z","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":"2026-06-29T07:53:14.338009Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.12560","last_updated":"2025-02-21T14:41:19Z","snapshot_observed_at":"2026-08-16T12:57:27.460553Z","submitted_at":"2025-02-18T05:54:56Z","title":"How does a Language-Specific Tokenizer affect LLMs?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.12560","snapshot_observed_at":"2026-08-16T11:32:06.046705Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.15431","last_updated":"2025-04-21T20:54:44Z","snapshot_observed_at":"2026-08-16T11:24:41.443927Z","submitted_at":"2025-04-21T20:54:44Z","title":"Trillion 7B Technical Report","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-16T11:32:06.046705Z"},"links":{"cited_paper":"/paper/2502.12560","citing_paper":"/paper/2504.15431"},"observation_digest":"sha256:40c247e8d30f0ee716685ae2ddfbab9bde364ad0311039be0b3188060f6bd9ac","observation_id":"42f24c84-d62d-452c-9fab-c9378463a0f9","resolution":{"observed_at":"2026-08-16T11:32:06.046705Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.12560","last_updated":"2025-02-21T14:41:19Z","snapshot_observed_at":"2026-08-16T12:57:27.460553Z","submitted_at":"2025-02-18T05:54:56Z","title":"How does a Language-Specific Tokenizer affect LLMs?","version":2},"cited_work":{"arxiv_id":"2502.12560","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.12560","snapshot_observed_at":"2026-06-29T07:53:14.338009Z","title":"How does a language-specific tokenizer affect llms?https://arxiv.org/abs/2502.12560, 2025","venue":null,"work_id":"e22f7dda-5e12-46e7-877a-9508832f2b4a","year":2025},"citing_paper":{"arxiv_id":"2605.29992","last_updated":"2026-05-28T14:24:50Z","snapshot_observed_at":"2026-08-13T15:13:34.040288Z","submitted_at":"2026-05-28T14:24:50Z","title":"Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T07:34:06.221069Z"},"links":{"cited_paper":"/paper/2502.12560","citing_paper":"/paper/2605.29992"},"observation_digest":"sha256:b35b563fe8594f2db9cf394bb5536e4f39873243fc27e6b23c8b3f925dd2a84d","observation_id":"0a04b2bf-c077-449a-912d-61b5e9a2e501","resolution":{"observed_at":"2026-06-29T07:53:14.339419Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.12560/citation-record","integrity":"/paper/2502.12560/integrity","json":"/paper/2502.12560/citation-record.json","paper":"/paper/2502.12560"},"outbound":[],"paper":{"arxiv_id":"2502.12560","last_updated":"2025-02-21T14:41:19Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T12:57:27.460553Z","submitted_at":"2025-02-18T05:54:56Z","title":"How does a Language-Specific Tokenizer affect LLMs?"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2502.12560."}