{"as_of":"2026-08-07T22:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0e0011744b366575dcddb9b663af1b91433c1961df1a7b61f485c32c5f3b6da8","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T23:52:04.356379Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T20:21:58.077404Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.13347","last_updated":"2025-06-23T02:24:30Z","snapshot_observed_at":"2026-08-07T18:06:57.924988Z","submitted_at":"2025-02-19T00:31:43Z","title":"Craw4LLM: Efficient Web Crawling for LLM Pretraining","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13347","snapshot_observed_at":"2026-08-06T23:52:04.356379Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16146","last_updated":"2025-07-02T12:34:15Z","snapshot_observed_at":"2026-08-06T23:42:03.645258Z","submitted_at":"2025-06-19T08:59:21Z","title":"Neural Prioritisation for Web Crawling","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T23:52:04.356379Z"},"links":{"cited_paper":"/paper/2502.13347","citing_paper":"/paper/2506.16146"},"observation_digest":"sha256:a021505cbe44640157371b943050390e37f00063e6e7b6407ff51dfe2709121b","observation_id":"38c050eb-4bdb-41d2-a502-36bcd8f466a6","resolution":{"observed_at":"2026-08-06T23:52:04.356379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13347","last_updated":"2025-06-23T02:24:30Z","snapshot_observed_at":"2026-08-07T18:06:57.924988Z","submitted_at":"2025-02-19T00:31:43Z","title":"Craw4LLM: Efficient Web Crawling for LLM Pretraining","version":3},"cited_work":{"arxiv_id":"2502.13347","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.13347","snapshot_observed_at":"2026-08-06T20:21:58.077404Z","title":"Craw4LLM: Efficient Web Crawling for LLM Pretraining","venue":"cs.CL","work_id":"e2a92c2e-d8f9-4ae1-ad30-b198545d0081","year":2025},"citing_paper":{"arxiv_id":"2507.03253","last_updated":"2025-07-08T18:15:09Z","snapshot_observed_at":"2026-08-07T10:43:54.316543Z","submitted_at":"2025-07-04T02:19:58Z","title":"RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-06T20:21:56.432140Z"},"links":{"cited_paper":"/paper/2502.13347","citing_paper":"/paper/2507.03253"},"observation_digest":"sha256:79ae31c82b1df27e1e597dbfd3ba768a152be7b38d2c3cef9320f6381229c93a","observation_id":"591e6031-5101-4b14-9a15-3885759666b3","resolution":{"observed_at":"2026-08-06T20:21:58.169963Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.13347/citation-record","integrity":"/paper/2502.13347/integrity","json":"/paper/2502.13347/citation-record.json","paper":"/paper/2502.13347"},"outbound":[],"paper":{"arxiv_id":"2502.13347","last_updated":"2025-06-23T02:24:30Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T18:06:57.924988Z","submitted_at":"2025-02-19T00:31:43Z","title":"Craw4LLM: Efficient Web Crawling for LLM Pretraining"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2502.13347."}