{"as_of":"2026-08-21T01:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:af5da10d2ef8a9f2bce3059cb2d8f423fcf2275359b1a5c2ffd4dd6a2fe99cf0","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":"2026-08-20T06:33:59.587034+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":"2026-08-09T17:36:27.872732Z","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":"2026-05-09T07:21:27.067546Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.10893","last_updated":"2024-05-17T16:31:56Z","snapshot_observed_at":"2026-08-19T04:48:10.794088Z","submitted_at":"2024-05-17T16:31:56Z","title":"COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.10893","snapshot_observed_at":"2026-08-09T17:36:27.872732Z","title":"CoRR abs/2405.10893 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00832","last_updated":"2025-02-02T16:05:23Z","snapshot_observed_at":"2026-08-14T23:29:48.333652Z","submitted_at":"2025-02-02T16:05:23Z","title":"Generalization of Medical Large Language Models through Cross-Domain Weak Supervision","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:27.872732Z"},"links":{"cited_paper":"/paper/2405.10893","citing_paper":"/paper/2502.00832"},"observation_digest":"sha256:581c039d93b2cb3ee7cd1a7db6f011d3f908f3ab4e75c18c903e51fcdb57965c","observation_id":"50ea6496-4eb9-4dfa-a56d-f33e4950d64b","resolution":{"observed_at":"2026-08-09T17:36:27.872732Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.10893","last_updated":"2024-05-17T16:31:56Z","snapshot_observed_at":"2026-08-19T04:48:10.794088Z","submitted_at":"2024-05-17T16:31:56Z","title":"COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.10893","snapshot_observed_at":"2026-08-07T13:52:02.866405Z","title":"Cognet-md, an evalua- tion framework and dataset for large language model benchmarks in the medical domain.arXiv preprint arXiv:2405.10893, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20824","last_updated":"2025-05-27T07:34:40Z","snapshot_observed_at":"2026-08-20T21:58:45.241527Z","submitted_at":"2025-05-27T07:34:40Z","title":"MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:52:02.866405Z"},"links":{"cited_paper":"/paper/2405.10893","citing_paper":"/paper/2505.20824"},"observation_digest":"sha256:7db46a6f5673bc6ad0bcd5c77ddef3bae5924a9d25a4da84754c3edc420e493c","observation_id":"229e6e05-7eda-4759-bf37-52fa55c5cef5","resolution":{"observed_at":"2026-08-07T13:52:02.866405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.10893","last_updated":"2024-05-17T16:31:56Z","snapshot_observed_at":"2026-08-19T04:48:10.794088Z","submitted_at":"2024-05-17T16:31:56Z","title":"COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain","version":1},"cited_work":{"arxiv_id":"2405.10893","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.10893","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"In Proceedings of the 2024 Con- ference on Empirical Methods in Natural Language Processing, pages 8428–8438, Miami, Florida, USA","venue":null,"work_id":"e96e0686-4a5d-4242-97fd-ab988c77106f","year":2024},"citing_paper":{"arxiv_id":"2508.04325","last_updated":"2026-04-29T05:46:18Z","snapshot_observed_at":"2026-08-02T07:50:38.917887Z","submitted_at":"2025-08-06T11:11:40Z","title":"Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-19T00:40:34.440305Z"},"links":{"cited_paper":"/paper/2405.10893","citing_paper":"/paper/2508.04325"},"observation_digest":"sha256:af0810fa11fcf32a1335b4c692c9a81129bb22d8269e9b13f1441ddc5c938f59","observation_id":"c475641c-7c69-4ecf-aa9a-02a0b10a969f","resolution":{"observed_at":"2026-05-09T07:21:27.071940Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.10893/citation-record","integrity":"/paper/2405.10893/integrity","json":"/paper/2405.10893/citation-record.json","paper":"/paper/2405.10893"},"outbound":[],"paper":{"arxiv_id":"2405.10893","last_updated":"2024-05-17T16:31:56Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T04:48:10.794088Z","submitted_at":"2024-05-17T16:31:56Z","title":"COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2405.10893."}