{"as_of":"2026-08-08T08:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:272ceb9419fe0eef688966d7aa48fc2bf0d1e7f15602b6daa5c43f24fb72cdff","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T18:43:58.486504Z","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":"2026-05-22T13:41:36.721453Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.11393","last_updated":"2025-05-26T03:52:24Z","snapshot_observed_at":"2026-08-07T18:13:52.873494Z","submitted_at":"2025-02-17T03:24:02Z","title":"HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning","version":2},"cited_work":{"arxiv_id":"2502.11393","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.11393","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hellaswag-pro: A large-scale bilingual benchmark for evaluating the robustness of llms in commonsense reasoning","venue":null,"work_id":"d7b04f4c-76b6-43e7-8515-249a6bc5f6b5","year":2025},"citing_paper":{"arxiv_id":"2505.17123","last_updated":"2026-05-21T12:25:44Z","snapshot_observed_at":"2026-08-03T06:01:46.333933Z","submitted_at":"2025-05-21T17:59:12Z","title":"MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-22T13:37:49.475416Z"},"links":{"cited_paper":"/paper/2502.11393","citing_paper":"/paper/2505.17123"},"observation_digest":"sha256:70d7c552e2bf55f65a3c226f3fece670c41a8b6c5ea7aa7e4ee84a4f1185f773","observation_id":"d041a5cf-2076-47c1-88dd-0b99bdee0745","resolution":{"observed_at":"2026-05-22T13:41:36.724097Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11393","last_updated":"2025-05-26T03:52:24Z","snapshot_observed_at":"2026-08-07T18:13:52.873494Z","submitted_at":"2025-02-17T03:24:02Z","title":"HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11393","snapshot_observed_at":"2026-08-06T18:43:58.486504Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07498","last_updated":"2025-07-14T07:10:51Z","snapshot_observed_at":"2026-08-07T08:42:01.003260Z","submitted_at":"2025-07-10T07:34:05Z","title":"Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T18:43:58.486504Z"},"links":{"cited_paper":"/paper/2502.11393","citing_paper":"/paper/2507.07498"},"observation_digest":"sha256:819e31cd64cf1f302ec765ff47bd4d8ad81d382d0de02d03d3a26e4675987895","observation_id":"abe9e047-01dc-4272-a012-e5869a9c0d20","resolution":{"observed_at":"2026-08-06T18:43:58.486504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.11393/citation-record","integrity":"/paper/2502.11393/integrity","json":"/paper/2502.11393/citation-record.json","paper":"/paper/2502.11393"},"outbound":[],"paper":{"arxiv_id":"2502.11393","last_updated":"2025-05-26T03:52:24Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T18:13:52.873494Z","submitted_at":"2025-02-17T03:24:02Z","title":"HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning"},"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 2 inbound Pith citation observations for arXiv:2502.11393."}