{"as_of":"2026-08-09T19:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cd030b23b40df85e35bc1de547c1ee065a94ad45e382c1ba8c1e13b742104852","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":"2026-08-06T11:59:52.201021Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":7,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.14389","last_updated":"2023-05-26T13:46:47Z","snapshot_observed_at":"2026-08-05T00:03:29.142007Z","submitted_at":"2022-09-28T19:28:43Z","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","version":2},"cited_work":{"arxiv_id":"2209.14389","doi":"10.48550/arxiv.2209.14389","metadata_source":"arxiv_reference","pith_arxiv_id":"2209.14389","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"and Lipton, Zachary C","venue":"arXiv (Cornell University)","work_id":"fb282b11-91cd-41e0-9293-bd454cc667c2","year":2022},"citing_paper":{"arxiv_id":"2211.09085","last_updated":"2022-11-16T18:06:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-16T18:06:33Z","title":"Galactica: A Large Language Model for Science","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-05-13T05:53:21.810346Z"},"links":{"cited_paper":"/paper/2209.14389","citing_paper":"/paper/2211.09085"},"observation_digest":"sha256:c81d978f548f751bf717a4fcf68cef5e7d9585041cb73cb96720953090b8b35c","observation_id":"a6de482b-e074-467a-9a48-eb626d3fd90c","resolution":{"observed_at":"2026-05-13T05:53:22.068963Z","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":"2209.14389","last_updated":"2023-05-26T13:46:47Z","snapshot_observed_at":"2026-08-05T00:03:29.142007Z","submitted_at":"2022-09-28T19:28:43Z","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.14389","snapshot_observed_at":"2026-08-06T11:59:52.201021Z","title":"Downstream datasets make surprisingly good pretraining corpora.arXiv preprint arXiv:2209.14389,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22250","last_updated":"2025-07-29T21:56:45Z","snapshot_observed_at":"2026-08-06T11:59:51.689888Z","submitted_at":"2025-07-29T21:56:45Z","title":"Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T11:59:52.201021Z"},"links":{"cited_paper":"/paper/2209.14389","citing_paper":"/paper/2507.22250"},"observation_digest":"sha256:775f1ba68e975d4d15d8980e4c333a3af94a03d0845910780db2ff4da660442a","observation_id":"5ddd77f2-d528-43cb-b4dc-f5824a7ed1da","resolution":{"observed_at":"2026-08-06T11:59:52.201021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2209.14389/citation-record","integrity":"/paper/2209.14389/integrity","json":"/paper/2209.14389/citation-record.json","paper":"/paper/2209.14389"},"outbound":[],"paper":{"arxiv_id":"2209.14389","last_updated":"2023-05-26T13:46:47Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T00:03:29.142007Z","submitted_at":"2022-09-28T19:28:43Z","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2209.14389."}