{"as_of":"2026-08-07T23:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:485d3a5cbeec20d66bdea0687d31b12851dc99b9491a4810a8d916ff27aadd40","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":"2026-08-07T06:34:17.273281+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":"2026-06-27T09:30:47.726480Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":6,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.12806","last_updated":"2023-12-20T07:01:49Z","snapshot_observed_at":"2026-08-05T10:00:04.639857Z","submitted_at":"2023-12-20T07:01:49Z","title":"MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models","version":1},"cited_work":{"arxiv_id":"2312.12806","doi":"10.48550/arxiv.2312.12806","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.12806","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Medbench: A large-scale chinese benchmark for evaluating medical large language models","venue":"arXiv (Cornell University)","work_id":"69c6b3f6-49db-4815-963a-20ea4eae386a","year":2023},"citing_paper":{"arxiv_id":"2605.08094","last_updated":"2026-04-09T18:00:47Z","snapshot_observed_at":"2026-08-02T05:04:09.143025Z","submitted_at":"2026-04-09T18:00:47Z","title":"MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-12T01:22:15.608348Z"},"links":{"cited_paper":"/paper/2312.12806","citing_paper":"/paper/2605.08094"},"observation_digest":"sha256:39738c85805d778d9941666c34edde458b04ab3b1f9bfec5c432deb4402e0990","observation_id":"bcefcfe2-4e36-403e-b210-d28e371dab99","resolution":{"observed_at":"2026-05-12T08:01:31.724700Z","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":"2312.12806","last_updated":"2023-12-20T07:01:49Z","snapshot_observed_at":"2026-08-05T10:00:04.639857Z","submitted_at":"2023-12-20T07:01:49Z","title":"MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models","version":1},"cited_work":{"arxiv_id":"2312.12806","doi":"10.48550/arxiv.2312.12806","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.12806","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Medbench: A large-scale chinese benchmark for evaluating medical large language models","venue":"arXiv (Cornell University)","work_id":"69c6b3f6-49db-4815-963a-20ea4eae386a","year":2023},"citing_paper":{"arxiv_id":"2606.12291","last_updated":"2026-06-10T16:27:26Z","snapshot_observed_at":"2026-08-02T15:04:58.080617Z","submitted_at":"2026-06-10T16:27:26Z","title":"Measuring Epistemic Resilience of LLMs Under Misleading Medical Context","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T09:30:47.726480Z"},"links":{"cited_paper":"/paper/2312.12806","citing_paper":"/paper/2606.12291"},"observation_digest":"sha256:230cf825c35b88c7822fba5e946f2b3918f57e977b05fd80bc93f00e1329709f","observation_id":"7e605dd6-e4a8-4331-bce0-cb9334308c6b","resolution":{"observed_at":"2026-06-27T09:40:47.726832Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2312.12806/citation-record","integrity":"/paper/2312.12806/integrity","json":"/paper/2312.12806/citation-record.json","paper":"/paper/2312.12806"},"outbound":[],"paper":{"arxiv_id":"2312.12806","last_updated":"2023-12-20T07:01:49Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T10:00:04.639857Z","submitted_at":"2023-12-20T07:01:49Z","title":"MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical 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":"2026-08-07T06:34:17.273281+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 2 inbound Pith citation observations for arXiv:2312.12806."}