{"as_of":"2026-08-07T04:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d7dee9f0d885d209ee1669ba2d31ee9a210037b65c2f42112ab07ea918420173","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":"2026-08-06T06:34:29.942622+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":"2026-08-06T18:51:27.438057Z","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":"2026-07-04T04:19:34.990786Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.15453","last_updated":"2025-01-28T06:35:32Z","snapshot_observed_at":"2026-07-06T20:26:17.112340Z","submitted_at":"2025-01-26T08:49:46Z","title":"Data-adaptive Safety Rules for Training Reward Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15453","snapshot_observed_at":"2026-08-06T18:51:27.438057Z","title":"Data-adaptive safety rules for training reward models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07375","last_updated":"2025-07-10T01:56:56Z","snapshot_observed_at":"2026-08-06T18:40:15.446120Z","submitted_at":"2025-07-10T01:56:56Z","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:51:27.438057Z"},"links":{"cited_paper":"/paper/2501.15453","citing_paper":"/paper/2507.07375"},"observation_digest":"sha256:8e328897ed42265a5ea3bccb9c35df3a7fea2da6d6e344f5dacc97828d0bef8f","observation_id":"69708228-e735-41ca-9311-dc586d66fc1f","resolution":{"observed_at":"2026-08-06T18:51:27.438057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15453","last_updated":"2025-01-28T06:35:32Z","snapshot_observed_at":"2026-07-06T20:26:17.112340Z","submitted_at":"2025-01-26T08:49:46Z","title":"Data-adaptive Safety Rules for Training Reward Models","version":2},"cited_work":{"arxiv_id":"2501.15453","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.15453","snapshot_observed_at":"2026-07-04T04:19:34.990786Z","title":"Data-adaptive safety rules for training reward models.arXiv preprint arXiv:2501.15453, 2025","venue":null,"work_id":"a73a4d27-82a0-4831-a332-a48361bea78c","year":2025},"citing_paper":{"arxiv_id":"2606.20363","last_updated":"2026-06-18T15:25:42Z","snapshot_observed_at":"2026-07-06T23:55:29.991442Z","submitted_at":"2026-06-18T15:25:42Z","title":"Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-26T17:02:30.696295Z"},"links":{"cited_paper":"/paper/2501.15453","citing_paper":"/paper/2606.20363"},"observation_digest":"sha256:ee7816a8986788c8f8a0336ecab7cab7e61f44066203509e3e7af3a6274db2a1","observation_id":"26cf5ff7-62cf-458f-8a51-58f0d698fee8","resolution":{"observed_at":"2026-07-04T04:19:34.992897Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.15453/citation-record","integrity":"/paper/2501.15453/integrity","json":"/paper/2501.15453/citation-record.json","paper":"/paper/2501.15453"},"outbound":[],"paper":{"arxiv_id":"2501.15453","last_updated":"2025-01-28T06:35:32Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:26:17.112340Z","submitted_at":"2025-01-26T08:49:46Z","title":"Data-adaptive Safety Rules for Training Reward Models"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2501.15453."}