{"as_of":"2026-08-08T20:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:263407cba5e4689cf69e58b386fe07607cb1c319500554a8d7232ab244eb6664","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":"2026-08-05T23:13:05.224677Z","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":"2026-07-02T12:26:57.033442Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.02009","last_updated":"2025-08-12T19:41:44Z","snapshot_observed_at":"2026-08-07T15:56:40.434770Z","submitted_at":"2025-05-04T06:37:20Z","title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.02009","snapshot_observed_at":"2026-08-05T23:13:05.224677Z","title":"arXiv preprint arXiv:2505.02009 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.05775","last_updated":"2026-07-27T20:50:40Z","snapshot_observed_at":"2026-08-05T23:12:57.691936Z","submitted_at":"2025-08-07T18:42:16Z","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","version":3},"reference_index":212,"source":"arxiv_source","source_observed_at":"2026-08-05T23:13:05.224677Z"},"links":{"cited_paper":"/paper/2505.02009","citing_paper":"/paper/2508.05775"},"observation_digest":"sha256:bff1f2464a16662d9f756dac94582ee68650ff8fe2860403bd372efecae6f7aa","observation_id":"803bed5d-fdd5-462f-86f8-adeff192f10d","resolution":{"observed_at":"2026-08-05T23:13:05.224677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02009","last_updated":"2025-08-12T19:41:44Z","snapshot_observed_at":"2026-08-07T15:56:40.434770Z","submitted_at":"2025-05-04T06:37:20Z","title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.02009","snapshot_observed_at":"2026-08-05T14:57:12.878381Z","title":"Towards safer pretraining: Analyzing and filtering harmful content in webscale datasets for responsible llms, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.20766","last_updated":"2025-08-28T13:22:33Z","snapshot_observed_at":"2026-08-07T12:38:42.068471Z","submitted_at":"2025-08-28T13:22:33Z","title":"Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-05T14:57:12.878381Z"},"links":{"cited_paper":"/paper/2505.02009","citing_paper":"/paper/2508.20766"},"observation_digest":"sha256:b254877e037f3ffd2343c011e9d9b3f486d645daaa2449ecd013859ec8e90762","observation_id":"bb034246-6af4-4a59-b1e4-b960e64aae42","resolution":{"observed_at":"2026-08-05T14:57:12.878381Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02009","last_updated":"2025-08-12T19:41:44Z","snapshot_observed_at":"2026-08-07T15:56:40.434770Z","submitted_at":"2025-05-04T06:37:20Z","title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs","version":3},"cited_work":{"arxiv_id":"2505.02009","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.02009","snapshot_observed_at":"2026-07-02T12:26:57.033442Z","title":"United Nations","venue":null,"work_id":"9fc74b77-761a-46c6-9861-5d8ae35fe2d6","year":1982},"citing_paper":{"arxiv_id":"2606.05936","last_updated":"2026-06-04T09:38:55Z","snapshot_observed_at":"2026-07-06T23:45:51.910263Z","submitted_at":"2026-06-04T09:38:55Z","title":"Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-28T02:06:31.341519Z"},"links":{"cited_paper":"/paper/2505.02009","citing_paper":"/paper/2606.05936"},"observation_digest":"sha256:8973da80353dd19254b0ca64d637b86be2ba2565a85e499628d9224514e51864","observation_id":"ea22ca27-f0da-4ec6-8833-486a85e51208","resolution":{"observed_at":"2026-07-02T12:26:57.034737Z","resolver_source":"arxiv_id","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/2505.02009/citation-record","integrity":"/paper/2505.02009/integrity","json":"/paper/2505.02009/citation-record.json","paper":"/paper/2505.02009"},"outbound":[],"paper":{"arxiv_id":"2505.02009","last_updated":"2025-08-12T19:41:44Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T15:56:40.434770Z","submitted_at":"2025-05-04T06:37:20Z","title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs"},"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:2505.02009."}