{"as_of":"2026-08-10T23:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d6428af1553c32612b94741358a5603c06665ae464fda3d914acb1242fcc842b","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":"2026-08-10T06:31:04.303077+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":"2026-08-08T18:25:09.285880Z","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":"2026-05-11T21:01:13.212332Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.07630","last_updated":"2024-07-10T13:09:23Z","snapshot_observed_at":"2026-08-10T14:47:42.317250Z","submitted_at":"2024-07-10T13:09:23Z","title":"A Review of the Challenges with Massive Web-mined Corpora Used in Large Language Models Pre-Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07630","snapshot_observed_at":"2026-08-08T18:25:09.285880Z","title":"and Po \\'s wiata, R","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.15745","last_updated":"2025-02-08T20:37:21Z","snapshot_observed_at":"2026-08-10T11:07:26.239905Z","submitted_at":"2025-02-08T20:37:21Z","title":"On the Effectiveness of Large Language Models in Automating Categorization of Scientific Texts","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-08T18:25:09.285880Z"},"links":{"cited_paper":"/paper/2407.07630","citing_paper":"/paper/2502.15745"},"observation_digest":"sha256:df82c837489922ca6f7693c343368609db6abf92789e4c71d89d23fa02a4a619","observation_id":"54b00524-b34d-4d69-adca-cee62e4d51be","resolution":{"observed_at":"2026-08-08T18:25:09.285880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07630","last_updated":"2024-07-10T13:09:23Z","snapshot_observed_at":"2026-08-10T14:47:42.317250Z","submitted_at":"2024-07-10T13:09:23Z","title":"A Review of the Challenges with Massive Web-mined Corpora Used in Large Language Models Pre-Training","version":1},"cited_work":{"arxiv_id":"2407.07630","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.07630","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2407.07630 (2024)","venue":null,"work_id":"1f9ae005-7e0f-4c8b-b659-177ec25956f8","year":2024},"citing_paper":{"arxiv_id":"2604.23430","last_updated":"2026-04-25T19:52:21Z","snapshot_observed_at":"2026-07-06T23:09:38.799345Z","submitted_at":"2026-04-25T19:52:21Z","title":"Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-08T07:18:25.902898Z"},"links":{"cited_paper":"/paper/2407.07630","citing_paper":"/paper/2604.23430"},"observation_digest":"sha256:de55f88e5958bc926a8cc8d96fe681cbd530177379f652a5ef6bd27dd30b72e7","observation_id":"d03046c7-e487-4a43-bbcf-751fd20dece2","resolution":{"observed_at":"2026-05-11T21:01:13.222759Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.07630/citation-record","integrity":"/paper/2407.07630/integrity","json":"/paper/2407.07630/citation-record.json","paper":"/paper/2407.07630"},"outbound":[],"paper":{"arxiv_id":"2407.07630","last_updated":"2024-07-10T13:09:23Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-10T14:47:42.317250Z","submitted_at":"2024-07-10T13:09:23Z","title":"A Review of the Challenges with Massive Web-mined Corpora Used in Large Language Models Pre-Training"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.07630."}