{"as_of":"2026-08-06T12:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3f1478a1ad58f507878dbf235e14cc718913be6a1d1b6bab1c4a87c1821e7979","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":"2026-08-06T06:34:29.942622+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":"2026-06-29T21:47:17.894881Z","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":"2026-07-02T02:36:27.452622Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.05761","last_updated":"2025-03-25T07:12:10Z","snapshot_observed_at":"2026-08-05T22:24:58.466585Z","submitted_at":"2024-06-09T12:30:30Z","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","version":2},"cited_work":{"arxiv_id":"2406.05761","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.05761","snapshot_observed_at":"2026-07-02T02:36:27.452622Z","title":"Y., et al","venue":null,"work_id":"ea7cc881-eb36-4c10-ac78-d0f89fe9dd4d","year":2025},"citing_paper":{"arxiv_id":"2509.11206","last_updated":"2026-04-20T05:43:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-09-14T10:24:13Z","title":"Evalet: Evaluating Large Language Models through Functional Fragmentation","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-18T16:57:25.259866Z"},"links":{"cited_paper":"/paper/2406.05761","citing_paper":"/paper/2509.11206"},"observation_digest":"sha256:6547efb5c7cff61955104e01a22eb57ce48c82f375d52a32106a797c0e46301e","observation_id":"7d636483-3ae0-4150-890f-df653d0b1174","resolution":{"observed_at":"2026-05-18T17:01:40.061056Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05761","last_updated":"2025-03-25T07:12:10Z","snapshot_observed_at":"2026-08-05T22:24:58.466585Z","submitted_at":"2024-06-09T12:30:30Z","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","version":2},"cited_work":{"arxiv_id":"2406.05761","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.05761","snapshot_observed_at":"2026-07-02T02:36:27.452622Z","title":"Y., et al","venue":null,"work_id":"ea7cc881-eb36-4c10-ac78-d0f89fe9dd4d","year":2025},"citing_paper":{"arxiv_id":"2605.25603","last_updated":"2026-05-25T08:54:55Z","snapshot_observed_at":"2026-08-03T17:47:49.546009Z","submitted_at":"2026-05-25T08:54:55Z","title":"Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-29T21:47:17.894881Z"},"links":{"cited_paper":"/paper/2406.05761","citing_paper":"/paper/2605.25603"},"observation_digest":"sha256:92903b3659d78990c89b594b3cc050e96fe0beed2cc109488041aff8fc144e56","observation_id":"d9e87539-1a81-450a-b433-0784c542ef95","resolution":{"observed_at":"2026-06-29T21:53:59.562279Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05761","last_updated":"2025-03-25T07:12:10Z","snapshot_observed_at":"2026-08-05T22:24:58.466585Z","submitted_at":"2024-06-09T12:30:30Z","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","version":2},"cited_work":{"arxiv_id":"2406.05761","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.05761","snapshot_observed_at":"2026-07-02T02:36:27.452622Z","title":"Y., et al","venue":null,"work_id":"ea7cc881-eb36-4c10-ac78-d0f89fe9dd4d","year":2025},"citing_paper":{"arxiv_id":"2606.03650","last_updated":"2026-06-04T10:01:47Z","snapshot_observed_at":"2026-08-06T12:17:15.155456Z","submitted_at":"2026-06-02T13:41:43Z","title":"CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T10:46:24.554332Z"},"links":{"cited_paper":"/paper/2406.05761","citing_paper":"/paper/2606.03650"},"observation_digest":"sha256:b1a083cb86b7160ca0cb7b3675e75ce1cf825e2834341589d3dafb653597903e","observation_id":"d42c853c-44aa-4875-99eb-f390e9b72887","resolution":{"observed_at":"2026-07-02T02:36:27.454057Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.05761/citation-record","integrity":"/paper/2406.05761/integrity","json":"/paper/2406.05761/citation-record.json","paper":"/paper/2406.05761"},"outbound":[],"paper":{"arxiv_id":"2406.05761","last_updated":"2025-03-25T07:12:10Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T22:24:58.466585Z","submitted_at":"2024-06-09T12:30:30Z","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with 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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.05761."}