{"as_of":"2026-08-08T13:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:516817aadf6da2d6306a1956d549560bf6c90681a786b020506302d806f42e62","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":"2026-08-07T12:44:14.888885Z","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":"2026-05-20T00:02:53.778437Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.16966","last_updated":"2024-06-05T20:14:15Z","snapshot_observed_at":"2026-07-06T18:05:46.922400Z","submitted_at":"2024-04-25T18:35:54Z","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16966","snapshot_observed_at":"2026-08-07T12:44:14.888885Z","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00072","last_updated":"2025-05-29T17:13:26Z","snapshot_observed_at":"2026-08-07T12:38:03.915535Z","submitted_at":"2025-05-29T17:13:26Z","title":"Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:44:14.888885Z"},"links":{"cited_paper":"/paper/2404.16966","citing_paper":"/paper/2506.00072"},"observation_digest":"sha256:66916c0a8060a75a378ddf7a94653bacc7cc5a897663ddf932cb13ea159a4afa","observation_id":"6a9a8eb7-fd15-4794-8c89-37a8138a8f3d","resolution":{"observed_at":"2026-08-07T12:44:14.888885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16966","last_updated":"2024-06-05T20:14:15Z","snapshot_observed_at":"2026-07-06T18:05:46.922400Z","submitted_at":"2024-04-25T18:35:54Z","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","version":2},"cited_work":{"arxiv_id":"2404.16966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.16966","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Examining the ro- bustness of llm evaluation to the distributional assumptions of benchmarks","venue":null,"work_id":"79645759-cac9-4766-a8fe-0c5c22a7e569","year":2024},"citing_paper":{"arxiv_id":"2605.17288","last_updated":"2026-05-17T06:59:43Z","snapshot_observed_at":"2026-08-02T11:50:03.814042Z","submitted_at":"2026-05-17T06:59:43Z","title":"When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-19T23:58:53.524203Z"},"links":{"cited_paper":"/paper/2404.16966","citing_paper":"/paper/2605.17288"},"observation_digest":"sha256:84970b350dfb65e8378f903465b14f1c2f073e0ab3487dd3df35a9ad818f4ddf","observation_id":"be0c793d-d4cf-44be-ba69-87652326a680","resolution":{"observed_at":"2026-05-20T00:02:53.781874Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2404.16966/citation-record","integrity":"/paper/2404.16966/integrity","json":"/paper/2404.16966/citation-record.json","paper":"/paper/2404.16966"},"outbound":[],"paper":{"arxiv_id":"2404.16966","last_updated":"2024-06-05T20:14:15Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:05:46.922400Z","submitted_at":"2024-04-25T18:35:54Z","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks"},"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:2404.16966."}