{"as_of":"2026-08-18T18:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b02c47568201224d93607a48983d1fb7d31a4acd7c5b671c28695d3a0532b98e","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":"2026-08-18T06:34:40.430872+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":"2026-08-10T18:00:32.727925Z","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":"2026-05-11T23:08:35.717041Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.10516","last_updated":"2024-07-09T02:56:14Z","snapshot_observed_at":"2026-08-16T13:51:59.694086Z","submitted_at":"2024-05-17T03:50:28Z","title":"Language Models can Evaluate Themselves via Probability Discrepancy","version":2},"cited_work":{"arxiv_id":"2405.10516","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.10516","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"cd4dd677-c52a-4de5-8298-3f71637b1207","year":2024},"citing_paper":{"arxiv_id":"2412.05579","last_updated":"2024-12-10T05:49:12Z","snapshot_observed_at":"2026-08-17T10:18:05.650518Z","submitted_at":"2024-12-07T08:07:24Z","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","version":2},"reference_index":256,"source":"pdf_text","source_observed_at":"2026-05-11T23:08:34.312466Z"},"links":{"cited_paper":"/paper/2405.10516","citing_paper":"/paper/2412.05579"},"observation_digest":"sha256:a40b881d5c857c3692ba903e1ec6e7aeadd09d749105cdb0ceef49fafb250c4b","observation_id":"8223c7fb-c0a3-4d84-b808-58e22e44f00b","resolution":{"observed_at":"2026-05-11T23:08:35.719887Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.10516","last_updated":"2024-07-09T02:56:14Z","snapshot_observed_at":"2026-08-16T13:51:59.694086Z","submitted_at":"2024-05-17T03:50:28Z","title":"Language Models can Evaluate Themselves via Probability Discrepancy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.10516","snapshot_observed_at":"2026-08-10T18:00:32.727925Z","title":"Language models can evaluate themselves via probability discrepancy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.11721","last_updated":"2025-03-08T21:56:29Z","snapshot_observed_at":"2026-08-15T18:28:50.149851Z","submitted_at":"2025-01-20T20:07:18Z","title":"Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T18:00:32.727925Z"},"links":{"cited_paper":"/paper/2405.10516","citing_paper":"/paper/2501.11721"},"observation_digest":"sha256:1db0d8db51785fd9786a9c3020ffa3779a5c58d1e480000d9e89b7095597705f","observation_id":"9cf92435-8d6a-446c-b62c-9041449ef5c9","resolution":{"observed_at":"2026-08-10T18:00:32.727925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.10516/citation-record","integrity":"/paper/2405.10516/integrity","json":"/paper/2405.10516/citation-record.json","paper":"/paper/2405.10516"},"outbound":[],"paper":{"arxiv_id":"2405.10516","last_updated":"2024-07-09T02:56:14Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T13:51:59.694086Z","submitted_at":"2024-05-17T03:50:28Z","title":"Language Models can Evaluate Themselves via Probability Discrepancy"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2405.10516."}