{"as_of":"2026-08-18T02:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:13d2cb3a3b2cac32e6b109827027c9eb3bdc1d73621a2dfb07e99b04358a73cd","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":"2026-08-17T06:30:58.91139+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":"2026-08-12T15:29:49.179745Z","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":"2026-05-19T09:53:02.103894Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.04599","last_updated":"2024-09-06T20:12:34Z","snapshot_observed_at":"2026-08-17T14:35:34.611073Z","submitted_at":"2024-09-06T20:12:34Z","title":"BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.04599","snapshot_observed_at":"2026-08-12T15:29:49.179745Z","title":"Yamshchikov","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.14198","last_updated":"2024-11-21T15:06:51Z","snapshot_observed_at":"2026-08-12T15:23:33.437414Z","submitted_at":"2024-11-21T15:06:51Z","title":"Why do language models perform worse for morphologically complex languages?","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T15:29:49.179745Z"},"links":{"cited_paper":"/paper/2409.04599","citing_paper":"/paper/2411.14198"},"observation_digest":"sha256:e87bf0f47495667ad22fa2995a853aa5726a67ffff1f5e7dfd740c5acaf59d19","observation_id":"4568cb6f-3349-4041-ad63-a16c98614005","resolution":{"observed_at":"2026-08-12T15:29:49.179745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.04599","last_updated":"2024-09-06T20:12:34Z","snapshot_observed_at":"2026-08-17T14:35:34.611073Z","submitted_at":"2024-09-06T20:12:34Z","title":"BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training","version":1},"cited_work":{"arxiv_id":"2409.04599","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.04599","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Chizhov, C","venue":null,"work_id":"4e69ea76-efe0-46f2-a337-405c715bb1c5","year":2024},"citing_paper":{"arxiv_id":"2506.14123","last_updated":"2026-05-07T07:43:36Z","snapshot_observed_at":"2026-08-11T17:02:54.244928Z","submitted_at":"2025-06-17T02:37:04Z","title":"Sampling from Your Language Model One Byte at a Time","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-19T09:52:20.923710Z"},"links":{"cited_paper":"/paper/2409.04599","citing_paper":"/paper/2506.14123"},"observation_digest":"sha256:2b04660564be259fd75e2a3a8cb7a9f300015c8e62db82a6b09f0d011be6bca8","observation_id":"16ebc47e-0de3-438d-a5ab-d77cd14779a0","resolution":{"observed_at":"2026-05-19T09:53:02.106060Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.04599/citation-record","integrity":"/paper/2409.04599/integrity","json":"/paper/2409.04599/citation-record.json","paper":"/paper/2409.04599"},"outbound":[],"paper":{"arxiv_id":"2409.04599","last_updated":"2024-09-06T20:12:34Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-17T14:35:34.611073Z","submitted_at":"2024-09-06T20:12:34Z","title":"BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer 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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2409.04599."}