{"as_of":"2026-08-05T14:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9ec0b07eb4e46f1b8c90730f6117d1ffa984235dc5dc7c970d077597cbbc0e3c","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T16:53:25.556222Z","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":"2026-07-04T04:39:34.656602Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.06926","last_updated":"2025-05-01T18:15:36Z","snapshot_observed_at":"2026-07-06T20:04:10.656197Z","submitted_at":"2024-12-09T19:11:54Z","title":"When Every Token Counts: Optimal Segmentation for Low-Resource Language Models","version":5},"cited_work":{"arxiv_id":"2412.06926","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.06926","snapshot_observed_at":"2026-07-04T04:39:34.656602Z","title":null,"venue":null,"work_id":"2f32031e-b01e-407f-802c-1faabd0dbe82","year":2024},"citing_paper":{"arxiv_id":"2606.20993","last_updated":"2026-06-18T23:50:54Z","snapshot_observed_at":"2026-08-05T09:19:18.829577Z","submitted_at":"2026-06-18T23:50:54Z","title":"Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-06-26T16:53:25.556222Z"},"links":{"cited_paper":"/paper/2412.06926","citing_paper":"/paper/2606.20993"},"observation_digest":"sha256:e6a45511829cc8f58541f247044c76982ef6164401b17d615c320f6eb4acddaf","observation_id":"7adebcde-5119-423a-a6da-c2bca8560b34","resolution":{"observed_at":"2026-07-04T04:39:34.657942Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.06926/citation-record","integrity":"/paper/2412.06926/integrity","json":"/paper/2412.06926/citation-record.json","paper":"/paper/2412.06926"},"outbound":[],"paper":{"arxiv_id":"2412.06926","last_updated":"2025-05-01T18:15:36Z","latest_version":5,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:04:10.656197Z","submitted_at":"2024-12-09T19:11:54Z","title":"When Every Token Counts: Optimal Segmentation for Low-Resource 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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2412.06926."}