{"as_of":"2026-08-08T04:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:45c97c7e0588fa0d8abaa6ef820f94ce0cec356de80ff2c305c23a171efec18c","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T14:44:09.381842Z","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":"2026-05-23T17:35:43.963141Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.11044","last_updated":"2025-02-07T21:56:40Z","snapshot_observed_at":"2026-07-06T18:31:49.437336Z","submitted_at":"2024-06-16T19:02:31Z","title":"Evaluating the Performance of Large Language Models via Debates","version":2},"cited_work":{"arxiv_id":"2406.11044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.11044","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"14ef0989-596c-4811-9ce2-38f71a3e380d","year":2024},"citing_paper":{"arxiv_id":"2411.15594","last_updated":"2025-10-19T10:32:43Z","snapshot_observed_at":"2026-08-02T10:23:50.881300Z","submitted_at":"2024-11-23T16:03:35Z","title":"A Survey on LLM-as-a-Judge","version":6},"reference_index":109,"source":"pdf_text","source_observed_at":"2026-05-23T17:33:13.394338Z"},"links":{"cited_paper":"/paper/2406.11044","citing_paper":"/paper/2411.15594"},"observation_digest":"sha256:76ae919ebbcf3ecb9f172892bebb4b4d88b9ae3f7034817c5a2a769f9b13620a","observation_id":"d7b7f57a-d576-432d-833c-6f084ab4d494","resolution":{"observed_at":"2026-05-23T17:35:43.966005Z","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":"2406.11044","last_updated":"2025-02-07T21:56:40Z","snapshot_observed_at":"2026-07-06T18:31:49.437336Z","submitted_at":"2024-06-16T19:02:31Z","title":"Evaluating the Performance of Large Language Models via Debates","version":2},"cited_work":{"arxiv_id":"2406.11044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.11044","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"14ef0989-596c-4811-9ce2-38f71a3e380d","year":2024},"citing_paper":{"arxiv_id":"2412.05579","last_updated":"2024-12-10T05:49:12Z","snapshot_observed_at":"2026-07-31T01:42:39.468673Z","submitted_at":"2024-12-07T08:07:24Z","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","version":2},"reference_index":163,"source":"pdf_text","source_observed_at":"2026-05-11T23:08:34.312466Z"},"links":{"cited_paper":"/paper/2406.11044","citing_paper":"/paper/2412.05579"},"observation_digest":"sha256:450bc3a6f6c164059c1182fc4228627c57d05c1b8ad619c87b900d712f7f2489","observation_id":"4920742b-8605-4fce-b84a-a72a01b7563d","resolution":{"observed_at":"2026-05-11T23:08:37.429892Z","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":"2406.11044","last_updated":"2025-02-07T21:56:40Z","snapshot_observed_at":"2026-07-06T18:31:49.437336Z","submitted_at":"2024-06-16T19:02:31Z","title":"Evaluating the Performance of Large Language Models via Debates","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11044","snapshot_observed_at":"2026-08-06T14:44:09.381842Z","title":"Evaluating the performance of large language models via debates","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17747","last_updated":"2025-08-08T01:56:30Z","snapshot_observed_at":"2026-08-06T14:37:08.284816Z","submitted_at":"2025-07-23T17:58:14Z","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-06T14:44:09.381842Z"},"links":{"cited_paper":"/paper/2406.11044","citing_paper":"/paper/2507.17747"},"observation_digest":"sha256:ca71cb96ff4d8eb0554f392c62f460d3546df2b9a87b2e4998c8c80f1ba1d4e8","observation_id":"e966dac2-cd50-4d15-baaa-94f3454d0b18","resolution":{"observed_at":"2026-08-06T14:44:09.381842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.11044/citation-record","integrity":"/paper/2406.11044/integrity","json":"/paper/2406.11044/citation-record.json","paper":"/paper/2406.11044"},"outbound":[],"paper":{"arxiv_id":"2406.11044","last_updated":"2025-02-07T21:56:40Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:31:49.437336Z","submitted_at":"2024-06-16T19:02:31Z","title":"Evaluating the Performance of Large Language Models via Debates"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.11044."}