{"as_of":"2026-08-10T02:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:61345579d77105ad9fac7d22186769b9b9d9b1ac9581be86b635328043db6e1b","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T17:49:21.415485Z","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":"2026-05-10T21:35:18.968699Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.14571","last_updated":"2020-10-29T15:18:35Z","snapshot_observed_at":"2026-07-06T10:09:10.434213Z","submitted_at":"2020-10-27T19:29:17Z","title":"Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus","version":2},"cited_work":{"arxiv_id":"2010.14571","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.14571","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2010.14571 , year=","venue":null,"work_id":"c0de79c9-0b31-477c-8608-0bc6a87ef7fe","year":2010},"citing_paper":{"arxiv_id":"2101.00027","last_updated":"2020-12-31T19:00:10Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-12-31T19:00:10Z","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","version":1},"reference_index":183,"source":"arxiv_source","source_observed_at":"2026-05-10T21:35:18.513342Z"},"links":{"cited_paper":"/paper/2010.14571","citing_paper":"/paper/2101.00027"},"observation_digest":"sha256:e9bf92733097c2737a7422bbfe4aa5a773a631091a46fa7c7fc3f8ca5cb61757","observation_id":"f8c047b2-572a-4a9c-ae39-1717fc9e3468","resolution":{"observed_at":"2026-05-10T21:35:18.977071Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.14571","last_updated":"2020-10-29T15:18:35Z","snapshot_observed_at":"2026-07-06T10:09:10.434213Z","submitted_at":"2020-10-27T19:29:17Z","title":"Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.14571","snapshot_observed_at":"2026-08-08T17:49:21.415485Z","title":"Language id in the wild: Unexpected challenges on the path to a thousand- language web text corpus,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.05841","last_updated":"2025-02-09T10:25:42Z","snapshot_observed_at":"2026-08-09T19:10:37.865545Z","submitted_at":"2025-02-09T10:25:42Z","title":"On the use of Performer and Agent Attention for Spoken Language Identification","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T17:49:21.415485Z"},"links":{"cited_paper":"/paper/2010.14571","citing_paper":"/paper/2502.05841"},"observation_digest":"sha256:9ed008562863ea25814e7bebecb53f07d28db5e899cf77ba046ed24b98fada4d","observation_id":"7deb1654-d7d6-47c8-8675-ee9a757864f7","resolution":{"observed_at":"2026-08-08T17:49:21.415485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2010.14571/citation-record","integrity":"/paper/2010.14571/integrity","json":"/paper/2010.14571/citation-record.json","paper":"/paper/2010.14571"},"outbound":[],"paper":{"arxiv_id":"2010.14571","last_updated":"2020-10-29T15:18:35Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T10:09:10.434213Z","submitted_at":"2020-10-27T19:29:17Z","title":"Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2010.14571."}