{"as_of":"2026-08-06T20:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c727d73e123f0589e89d77d705c5c38f08b094476c85168d1d1b6c633b591f5f","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T05:09:55.843624Z","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":"2026-07-02T04:26:35.426380Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.06874","last_updated":"2022-05-18T17:42:09Z","snapshot_observed_at":"2026-07-06T10:49:06.028323Z","submitted_at":"2021-03-11T18:57:44Z","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","version":4},"cited_work":{"arxiv_id":"2103.06874","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.06874","snapshot_observed_at":"2026-07-02T04:26:35.426380Z","title":"Clark, Dan Garrette, Iulia Turc, and John Wieting","venue":null,"work_id":"ecbf65f3-edf5-4a8e-8731-96945d023582","year":2022},"citing_paper":{"arxiv_id":"2605.24718","last_updated":"2026-05-23T20:13:44Z","snapshot_observed_at":"2026-07-06T23:34:47.734159Z","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":15,"source":"pdf_text","source_observed_at":"2026-06-30T13:08:33.172423Z"},"links":{"cited_paper":"/paper/2103.06874","citing_paper":"/paper/2605.24718"},"observation_digest":"sha256:c08e275d4fcdd12a9ff3d3e0ca6c7f232225fcfd17ba9feecbaf1144dae29b54","observation_id":"58e54eab-ae6b-4ec8-8a04-3c52695c66ce","resolution":{"observed_at":"2026-06-30T13:14:40.895765Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.06874","last_updated":"2022-05-18T17:42:09Z","snapshot_observed_at":"2026-07-06T10:49:06.028323Z","submitted_at":"2021-03-11T18:57:44Z","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","version":4},"cited_work":{"arxiv_id":"2103.06874","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.06874","snapshot_observed_at":"2026-07-02T04:26:35.426380Z","title":"Clark, Dan Garrette, Iulia Turc, and John Wieting","venue":null,"work_id":"ecbf65f3-edf5-4a8e-8731-96945d023582","year":2022},"citing_paper":{"arxiv_id":"2606.04171","last_updated":"2026-06-02T19:35:44Z","snapshot_observed_at":"2026-08-04T16:20:12.336807Z","submitted_at":"2026-06-02T19:35:44Z","title":"MimeLens: Position-Agnostic Content-Type Detection for Binary Fragments","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T09:13:26.501298Z"},"links":{"cited_paper":"/paper/2103.06874","citing_paper":"/paper/2606.04171"},"observation_digest":"sha256:c7cf902aea7057e017e4905f7d2e5b8a4dd0c8f1b36c52e87e8ddff41a9fc63e","observation_id":"2500a1ad-1472-411b-a8c8-b44872db5a01","resolution":{"observed_at":"2026-07-02T04:26:35.428082Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.06874","last_updated":"2022-05-18T17:42:09Z","snapshot_observed_at":"2026-07-06T10:49:06.028323Z","submitted_at":"2021-03-11T18:57:44Z","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.06874","snapshot_observed_at":"2026-08-01T05:09:55.843624Z","title":"Clark, Dan Garrette, Iulia Turc, and John Wieting","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22334","last_updated":"2026-07-24T14:12:54Z","snapshot_observed_at":"2026-08-06T13:13:09.326315Z","submitted_at":"2026-07-24T14:12:54Z","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T05:09:55.843624Z"},"links":{"cited_paper":"/paper/2103.06874","citing_paper":"/paper/2607.22334"},"observation_digest":"sha256:b182e5bf7bb4ff972a8be348f3b31ea370f580e934d90ab47fd63a505bd828ce","observation_id":"b0df1043-0977-4429-9a4c-38758d5fdf71","resolution":{"observed_at":"2026-08-01T05:09:55.843624Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2103.06874/citation-record","integrity":"/paper/2103.06874/integrity","json":"/paper/2103.06874/citation-record.json","paper":"/paper/2103.06874"},"outbound":[],"paper":{"arxiv_id":"2103.06874","last_updated":"2022-05-18T17:42:09Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T10:49:06.028323Z","submitted_at":"2021-03-11T18:57:44Z","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2103.06874."}