{"as_of":"2026-08-07T09:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f26ccfb3b278b025a23112d7d92606b5f8fa9327c7d0808f6f86df616c6349ab","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T04:33:11.149875Z","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":"2026-06-29T09:13:16.615236Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.06643","last_updated":"2026-07-06T05:56:24Z","snapshot_observed_at":"2026-08-07T05:14:45.965038Z","submitted_at":"2025-03-09T14:41:18Z","title":"Is Your Benchmark Still Useful? Dynamic Benchmarking for Code Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06643","snapshot_observed_at":"2026-08-07T04:33:11.149875Z","title":"Is your benchmark (still) useful? dynamic benchmarking for code language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.10481","last_updated":"2025-06-12T08:33:38Z","snapshot_observed_at":"2026-08-07T05:19:15.942866Z","submitted_at":"2025-06-12T08:33:38Z","title":"OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T04:33:11.149875Z"},"links":{"cited_paper":"/paper/2503.06643","citing_paper":"/paper/2506.10481"},"observation_digest":"sha256:264823f7220d38be29f62de297a72b81ede71111435a7c172132d4ccf1c995a7","observation_id":"d710289c-aca7-4203-b897-827a8eb75b65","resolution":{"observed_at":"2026-08-07T04:33:11.149875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06643","last_updated":"2026-07-06T05:56:24Z","snapshot_observed_at":"2026-08-07T05:14:45.965038Z","submitted_at":"2025-03-09T14:41:18Z","title":"Is Your Benchmark Still Useful? Dynamic Benchmarking for Code Language Models","version":2},"cited_work":{"arxiv_id":"2503.06643","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.06643","snapshot_observed_at":"2026-07-07T02:19:37.552446Z","title":"Is your benchmark (still) useful? dynamic benchmarking for code language models","venue":null,"work_id":"c31f9e56-912e-426c-bb27-99fc984d0b8a","year":2018},"citing_paper":{"arxiv_id":"2605.10448","last_updated":"2026-05-11T12:20:15Z","snapshot_observed_at":"2026-08-06T20:03:57.191605Z","submitted_at":"2026-05-11T12:20:15Z","title":"Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-12T05:05:55.592359Z"},"links":{"cited_paper":"/paper/2503.06643","citing_paper":"/paper/2605.10448"},"observation_digest":"sha256:7948ea94be9b87243191fa6531e0a2d0a7b375f65c9c85f554a6a29a3151f0e4","observation_id":"c8ea4181-b363-423a-8ace-3bf2fa8d95ae","resolution":{"observed_at":"2026-07-07T02:19:37.552446Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06643","last_updated":"2026-07-06T05:56:24Z","snapshot_observed_at":"2026-08-07T05:14:45.965038Z","submitted_at":"2025-03-09T14:41:18Z","title":"Is Your Benchmark Still Useful? Dynamic Benchmarking for Code Language Models","version":2},"cited_work":{"arxiv_id":"2503.06643","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.06643","snapshot_observed_at":"2026-07-07T02:19:37.552446Z","title":"Is your benchmark (still) useful? dynamic benchmarking for code language models","venue":null,"work_id":"c31f9e56-912e-426c-bb27-99fc984d0b8a","year":2018},"citing_paper":{"arxiv_id":"2605.29490","last_updated":"2026-05-28T07:17:53Z","snapshot_observed_at":"2026-07-06T23:38:56.014434Z","submitted_at":"2026-05-28T07:17:53Z","title":"CODEFUSE-DEBENCH: An Empirical Study on Readability, Recompilability, and Functionality","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T06:54:29.067978Z"},"links":{"cited_paper":"/paper/2503.06643","citing_paper":"/paper/2605.29490"},"observation_digest":"sha256:2df52b4a567b01696ecd0b3e3512c1f069c367ae3a86bb210ac13d9ac3aece73","observation_id":"bc6cecde-7a1f-4db1-b3b7-c918acfd794e","resolution":{"observed_at":"2026-07-07T02:19:37.552446Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.06643/citation-record","integrity":"/paper/2503.06643/integrity","json":"/paper/2503.06643/citation-record.json","paper":"/paper/2503.06643"},"outbound":[],"paper":{"arxiv_id":"2503.06643","last_updated":"2026-07-06T05:56:24Z","latest_version":2,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-07T05:14:45.965038Z","submitted_at":"2025-03-09T14:41:18Z","title":"Is Your Benchmark Still Useful? Dynamic Benchmarking for Code Language 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.06643."}