{"as_of":"2026-08-19T10:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3856aa1d939e1df3278058b278cf75274eb93e715b1ed095922b2f30a15ef6e3","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":"2026-08-19T06:32:44.657259+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":"2026-08-12T16:27:34.441542Z","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":"2026-05-23T16:38:11.254812Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.09855","last_updated":"2024-07-13T11:29:20Z","snapshot_observed_at":"2026-08-19T10:08:22.020448Z","submitted_at":"2024-07-13T11:29:20Z","title":"Building pre-train LLM Dataset for the INDIC Languages: a case study on Hindi","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09855","snapshot_observed_at":"2026-08-12T16:27:34.441542Z","title":"Building pre-train llm dataset for the indic languages: a case study on hindi","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13453","last_updated":"2024-11-20T16:59:41Z","snapshot_observed_at":"2026-08-14T09:39:08.444218Z","submitted_at":"2024-11-20T16:59:41Z","title":"LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T16:27:34.441542Z"},"links":{"cited_paper":"/paper/2407.09855","citing_paper":"/paper/2411.13453"},"observation_digest":"sha256:01bd3445a2dd096ccf5e7d3863a6998ee90162fad6461cd146d335d3a6f004a1","observation_id":"6b17f21f-fde3-4d86-a882-e1642f5193a9","resolution":{"observed_at":"2026-08-12T16:27:34.441542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09855","last_updated":"2024-07-13T11:29:20Z","snapshot_observed_at":"2026-08-19T10:08:22.020448Z","submitted_at":"2024-07-13T11:29:20Z","title":"Building pre-train LLM Dataset for the INDIC Languages: a case study on Hindi","version":1},"cited_work":{"arxiv_id":"2407.09855","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.09855","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2407.09855 (2024)","venue":null,"work_id":"1bafd274-c40d-4393-9c3c-a49c9c0b088d","year":2024},"citing_paper":{"arxiv_id":"2412.04497","last_updated":"2026-04-17T14:43:11Z","snapshot_observed_at":"2026-08-03T01:36:22.644152Z","submitted_at":"2024-11-30T00:10:56Z","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","version":5},"reference_index":108,"source":"pdf_text","source_observed_at":"2026-05-23T16:36:02.895613Z"},"links":{"cited_paper":"/paper/2407.09855","citing_paper":"/paper/2412.04497"},"observation_digest":"sha256:2daf07963b5ae5d5184b0dc756b6f0af6b24132b286d48585919dfa6aa936e87","observation_id":"a3b715f1-8d2c-4631-a33e-5370e94de024","resolution":{"observed_at":"2026-05-23T16:38:11.257542Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.09855/citation-record","integrity":"/paper/2407.09855/integrity","json":"/paper/2407.09855/citation-record.json","paper":"/paper/2407.09855"},"outbound":[],"paper":{"arxiv_id":"2407.09855","last_updated":"2024-07-13T11:29:20Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T10:08:22.020448Z","submitted_at":"2024-07-13T11:29:20Z","title":"Building pre-train LLM Dataset for the INDIC Languages: a case study on Hindi"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.09855."}