{"as_of":"2026-08-08T17:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:08698e1775a4629a369acf0b908c54820652b842e2047941e831fa0b24dd916c","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:35:43.210706Z","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":"2026-08-06T11:59:52.329177Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.06380","last_updated":"2024-10-19T16:51:38Z","snapshot_observed_at":"2026-07-06T18:43:22.614883Z","submitted_at":"2024-07-08T20:47:58Z","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06380","snapshot_observed_at":"2026-08-07T12:35:43.210706Z","title":"Data, data everywhere: A guide for pretraining dataset construction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24844","last_updated":"2025-05-30T17:43:10Z","snapshot_observed_at":"2026-08-07T12:10:14.729914Z","submitted_at":"2025-05-30T17:43:10Z","title":"Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:43.210706Z"},"links":{"cited_paper":"/paper/2407.06380","citing_paper":"/paper/2505.24844"},"observation_digest":"sha256:2363bb3040d5465f7fae7fbaf0b32ffe0c45ffa2fa29b309321fe4d885bed560","observation_id":"e6ac58fd-dcf0-4aa1-a52c-a87c69a632a3","resolution":{"observed_at":"2026-08-07T12:35:43.210706Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06380","last_updated":"2024-10-19T16:51:38Z","snapshot_observed_at":"2026-07-06T18:43:22.614883Z","submitted_at":"2024-07-08T20:47:58Z","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06380","snapshot_observed_at":"2026-08-07T10:52:06.138326Z","title":"Data, data everywhere: A guide for pretraining dataset construction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04180","last_updated":"2025-06-04T17:27:42Z","snapshot_observed_at":"2026-08-08T16:23:05.849553Z","submitted_at":"2025-06-04T17:27:42Z","title":"SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.138326Z"},"links":{"cited_paper":"/paper/2407.06380","citing_paper":"/paper/2506.04180"},"observation_digest":"sha256:f55d3dcb761ade18d843e809fd9abf1849587565e6d70738c1dfce09ff69ada4","observation_id":"e313c10c-3cad-41c3-9df1-3feb00e7b7c6","resolution":{"observed_at":"2026-08-07T10:52:06.138326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06380","last_updated":"2024-10-19T16:51:38Z","snapshot_observed_at":"2026-07-06T18:43:22.614883Z","submitted_at":"2024-07-08T20:47:58Z","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","version":2},"cited_work":{"arxiv_id":"2407.06380","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.06380","snapshot_observed_at":"2026-08-06T11:59:52.329177Z","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","venue":"cs.CL","work_id":"ccdfcc03-3d99-4321-8b4e-8ee7fe0e95e0","year":2024},"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":25,"source":"pdf_text","source_observed_at":"2026-08-06T11:59:52.223959Z"},"links":{"cited_paper":"/paper/2407.06380","citing_paper":"/paper/2507.22250"},"observation_digest":"sha256:7cee3251ea8ca0c82bf5bdae9035ab3d67b783d18a78885a1ffc24277cca500b","observation_id":"0e3c9fc1-d6c2-4106-9c37-4bac7b08cd4a","resolution":{"observed_at":"2026-08-06T11:59:52.334238Z","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/2407.06380/citation-record","integrity":"/paper/2407.06380/integrity","json":"/paper/2407.06380/citation-record.json","paper":"/paper/2407.06380"},"outbound":[],"paper":{"arxiv_id":"2407.06380","last_updated":"2024-10-19T16:51:38Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:43:22.614883Z","submitted_at":"2024-07-08T20:47:58Z","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction"},"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 3 inbound Pith citation observations for arXiv:2407.06380."}