{"as_of":"2026-08-23T17:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e7565653189553dd38ed5a946a76e71ef4d1584d3cb3f66b0334ac38a25c4ad3","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":"2026-08-23T06:30:58.430688+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":"2026-08-07T10:29:42.995274Z","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":"2026-08-06T05:07:19.148601Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.08365","last_updated":"2025-01-14T17:18:05Z","snapshot_observed_at":"2026-08-10T20:27:53.314845Z","submitted_at":"2025-01-14T17:18:05Z","title":"Towards Best Practices for Open Datasets for LLM Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.08365","snapshot_observed_at":"2026-08-07T10:29:42.995274Z","title":"Towards best practices for open datasets for llm training, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.05209","last_updated":"2025-06-05T16:21:30Z","snapshot_observed_at":"2026-08-09T07:25:20.673180Z","submitted_at":"2025-06-05T16:21:30Z","title":"The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:29:42.995274Z"},"links":{"cited_paper":"/paper/2501.08365","citing_paper":"/paper/2506.05209"},"observation_digest":"sha256:97d3d6d83562c0c94d9de1136a7a0e168994a0182423222bec4a1252056a548d","observation_id":"86dffc5c-5492-464f-bd44-09638560d0cc","resolution":{"observed_at":"2026-08-07T10:29:42.995274Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.08365","last_updated":"2025-01-14T17:18:05Z","snapshot_observed_at":"2026-08-10T20:27:53.314845Z","submitted_at":"2025-01-14T17:18:05Z","title":"Towards Best Practices for Open Datasets for LLM Training","version":1},"cited_work":{"arxiv_id":"2501.08365","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.08365","snapshot_observed_at":"2026-08-06T05:07:19.148601Z","title":"Towards Best Practices for Open Datasets for LLM Training","venue":"cs.CY","work_id":"825bf4d2-a0eb-4af1-99bd-82fb26645aa5","year":2025},"citing_paper":{"arxiv_id":"2508.02271","last_updated":"2025-08-05T09:27:09Z","snapshot_observed_at":"2026-08-06T05:07:17.504090Z","submitted_at":"2025-08-04T10:30:42Z","title":"Dynaword: From One-shot to Continuously Developed Datasets","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:18.501404Z"},"links":{"cited_paper":"/paper/2501.08365","citing_paper":"/paper/2508.02271"},"observation_digest":"sha256:4d31f8f7ff80999bb7c71324f8b6a31628f7e548bdc58a4267487bf9dfa1d862","observation_id":"ea31e5ce-e551-465a-8f48-d972f22adf33","resolution":{"observed_at":"2026-08-06T05:07:19.223043Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.08365/citation-record","integrity":"/paper/2501.08365/integrity","json":"/paper/2501.08365/citation-record.json","paper":"/paper/2501.08365"},"outbound":[],"paper":{"arxiv_id":"2501.08365","last_updated":"2025-01-14T17:18:05Z","latest_version":1,"primary_category":"cs.CY","snapshot_observed_at":"2026-08-10T20:27:53.314845Z","submitted_at":"2025-01-14T17:18:05Z","title":"Towards Best Practices for Open Datasets for LLM 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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2501.08365."}