{"as_of":"2026-08-08T15:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:324af451903fb982fd1500bdc1f471e08680ad0ed7adbfa092ae4302410a1210","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T18:33:11.466884Z","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":"2026-08-07T15:43:04.992448Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.06408","last_updated":"2024-06-20T18:21:49Z","snapshot_observed_at":"2026-07-06T17:14:41.030939Z","submitted_at":"2024-01-12T07:10:10Z","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.06408","snapshot_observed_at":"2026-08-07T18:33:11.466884Z","title":"naacl-long.179/","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10341","last_updated":"2025-07-16T07:09:29Z","snapshot_observed_at":"2026-08-07T18:25:04.873435Z","submitted_at":"2025-02-14T18:02:37Z","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","version":3},"reference_index":179,"source":"pdf_text","source_observed_at":"2026-08-07T18:33:11.466884Z"},"links":{"cited_paper":"/paper/2401.06408","citing_paper":"/paper/2502.10341"},"observation_digest":"sha256:5b850f5883aeaac1fdc61ef6d57003dc9e2c150ab73eb58693aecee638001db8","observation_id":"4e066cac-8b79-4282-bf34-8fda2146aeb4","resolution":{"observed_at":"2026-08-07T18:33:11.466884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06408","last_updated":"2024-06-20T18:21:49Z","snapshot_observed_at":"2026-07-06T17:14:41.030939Z","submitted_at":"2024-01-12T07:10:10Z","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","version":3},"cited_work":{"arxiv_id":"2401.06408","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.06408","snapshot_observed_at":"2026-08-07T15:43:04.992448Z","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","venue":"cs.CL","work_id":"fee61869-2d67-463f-af3b-513e75727b07","year":2024},"citing_paper":{"arxiv_id":"2505.14070","last_updated":"2025-05-31T03:47:36Z","snapshot_observed_at":"2026-08-07T23:55:16.149811Z","submitted_at":"2025-05-20T08:21:37Z","title":"Enhancing LLMs via High-Knowledge Data Selection","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T15:43:02.460556Z"},"links":{"cited_paper":"/paper/2401.06408","citing_paper":"/paper/2505.14070"},"observation_digest":"sha256:594ce5b1ddcf14429ec71faeb5c53846dd14e0fe137d54b9349e22afc957ca97","observation_id":"6e26391d-6f50-4aec-9764-d2f88b2a4bde","resolution":{"observed_at":"2026-08-07T15:43:05.080971Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.06408/citation-record","integrity":"/paper/2401.06408/integrity","json":"/paper/2401.06408/citation-record.json","paper":"/paper/2401.06408"},"outbound":[],"paper":{"arxiv_id":"2401.06408","last_updated":"2024-06-20T18:21:49Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T17:14:41.030939Z","submitted_at":"2024-01-12T07:10:10Z","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2401.06408."}