{"as_of":"2026-08-12T14:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:83bc2c64baf1e8f900f59fa81099df8df636789ecbe0808d68bdd551d3b3e0db","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T11:39:33.593222Z","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":"2026-05-11T08:11:01.476796Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.01940","last_updated":"2024-03-11T08:07:28Z","snapshot_observed_at":"2026-08-11T16:25:04.412349Z","submitted_at":"2023-09-05T04:12:01Z","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01940","snapshot_observed_at":"2026-08-12T11:39:33.593222Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.18019","last_updated":"2024-11-27T03:25:44Z","snapshot_observed_at":"2026-08-12T11:33:56.360513Z","submitted_at":"2024-11-27T03:25:44Z","title":"A Real-World Benchmark for Evaluating Fine-Grained Issue Solving Capabilities of Large Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T11:39:33.593222Z"},"links":{"cited_paper":"/paper/2309.01940","citing_paper":"/paper/2411.18019"},"observation_digest":"sha256:f8ed2ebcefc3406ee29ab7a974493110c7a31a622525f02f5ff5212f18377f10","observation_id":"3c90e457-6e5d-4901-8970-c3ae95b5f194","resolution":{"observed_at":"2026-08-12T11:39:33.593222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01940","last_updated":"2024-03-11T08:07:28Z","snapshot_observed_at":"2026-08-11T16:25:04.412349Z","submitted_at":"2023-09-05T04:12:01Z","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01940","snapshot_observed_at":"2026-08-11T11:57:50.839876Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.14764","last_updated":"2024-12-19T11:48:01Z","snapshot_observed_at":"2026-08-11T11:54:04.254836Z","submitted_at":"2024-12-19T11:48:01Z","title":"CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T11:57:50.839876Z"},"links":{"cited_paper":"/paper/2309.01940","citing_paper":"/paper/2412.14764"},"observation_digest":"sha256:deb1b244a6231b11b25660b30614ba0ec224c683d2ec1cc4db22678d16cd7ee8","observation_id":"df35725c-aa15-4d7e-ac19-056c51f776d2","resolution":{"observed_at":"2026-08-11T11:57:50.839876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01940","last_updated":"2024-03-11T08:07:28Z","snapshot_observed_at":"2026-08-11T16:25:04.412349Z","submitted_at":"2023-09-05T04:12:01Z","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","version":4},"cited_work":{"arxiv_id":"2309.01940","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.01940","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"8f3a8b32-9dec-4e9b-a2f5-88eb85215c28","year":2023},"citing_paper":{"arxiv_id":"2604.09515","last_updated":"2026-04-10T17:37:26Z","snapshot_observed_at":"2026-08-11T12:32:54.988890Z","submitted_at":"2026-04-10T17:37:26Z","title":"When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T16:48:11.705307Z"},"links":{"cited_paper":"/paper/2309.01940","citing_paper":"/paper/2604.09515"},"observation_digest":"sha256:b30deaf4a59addcf5da0582fe73741147e7e6baf143987c6abad93a0fc5a01a0","observation_id":"94023f46-9ce0-4b0e-904a-da3a8571bb66","resolution":{"observed_at":"2026-05-11T08:11:01.480908Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01940","last_updated":"2024-03-11T08:07:28Z","snapshot_observed_at":"2026-08-11T16:25:04.412349Z","submitted_at":"2023-09-05T04:12:01Z","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01940","snapshot_observed_at":"2026-08-01T00:57:34.602703Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25996","last_updated":"2026-07-28T17:12:41Z","snapshot_observed_at":"2026-08-08T13:45:03.380671Z","submitted_at":"2026-07-28T17:12:41Z","title":"RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T00:57:34.602703Z"},"links":{"cited_paper":"/paper/2309.01940","citing_paper":"/paper/2607.25996"},"observation_digest":"sha256:b8a4f5ead0a1104a41a69c3d5096547af16f80f0c69845e17a5b4e1cd7ae4532","observation_id":"d543636c-1331-4ead-9ffc-c916029304c9","resolution":{"observed_at":"2026-08-01T00:57:34.602703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.01940/citation-record","integrity":"/paper/2309.01940/integrity","json":"/paper/2309.01940/citation-record.json","paper":"/paper/2309.01940"},"outbound":[],"paper":{"arxiv_id":"2309.01940","last_updated":"2024-03-11T08:07:28Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-11T16:25:04.412349Z","submitted_at":"2023-09-05T04:12:01Z","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large 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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2309.01940."}