{"as_of":"2026-08-17T03:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a43efaa846ef4de0c3c3d73081e383849010ae6255f7c1b4c66d1679348c40ab","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":"2026-08-16T06:30:59.297886+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":"2026-08-16T11:24:12.221598Z","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":"2026-08-15T23:25:00.862060Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.22587","last_updated":"2024-11-18T18:42:44Z","snapshot_observed_at":"2026-08-16T17:51:25.715262Z","submitted_at":"2024-10-29T23:00:05Z","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.22587","snapshot_observed_at":"2026-08-16T11:24:12.221598Z","title":"Toxicity of the commons: Curat- ing open-source pre-training data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.15585","last_updated":"2025-06-09T02:36:20Z","snapshot_observed_at":"2026-08-16T13:11:23.928524Z","submitted_at":"2025-04-22T05:02:49Z","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","version":4},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-16T11:24:12.221598Z"},"links":{"cited_paper":"/paper/2410.22587","citing_paper":"/paper/2504.15585"},"observation_digest":"sha256:edc453aae7f3ff454379aa5da2bad95a765f45b441fbf0c55732d3c366c92107","observation_id":"a8d9c28f-3253-4175-8577-e72be51fdd57","resolution":{"observed_at":"2026-08-16T11:24:12.221598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.22587","last_updated":"2024-11-18T18:42:44Z","snapshot_observed_at":"2026-08-16T17:51:25.715262Z","submitted_at":"2024-10-29T23:00:05Z","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data","version":2},"cited_work":{"arxiv_id":"2410.22587","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.22587","snapshot_observed_at":"2026-08-15T23:25:00.862060Z","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data","venue":"cs.CL","work_id":"2d4f0950-ec1c-4c18-9ad5-f61387b5f022","year":2024},"citing_paper":{"arxiv_id":"2505.04741","last_updated":"2025-05-07T19:17:49Z","snapshot_observed_at":"2026-08-16T02:22:19.600858Z","submitted_at":"2025-05-07T19:17:49Z","title":"When Bad Data Leads to Good Models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T23:25:00.107667Z"},"links":{"cited_paper":"/paper/2410.22587","citing_paper":"/paper/2505.04741"},"observation_digest":"sha256:b8e20fb1e9a1fbaa4ac29353f816e7036082c2ce2edd41363d3b6e5448e74bff","observation_id":"2100cedd-d90d-4a1f-b140-cbeec05e5e12","resolution":{"observed_at":"2026-08-15T23:25:00.868858Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.22587/citation-record","integrity":"/paper/2410.22587/integrity","json":"/paper/2410.22587/citation-record.json","paper":"/paper/2410.22587"},"outbound":[],"paper":{"arxiv_id":"2410.22587","last_updated":"2024-11-18T18:42:44Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T17:51:25.715262Z","submitted_at":"2024-10-29T23:00:05Z","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2410.22587."}