{"as_of":"2026-08-15T19:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3f8384bcf08d7ba922f6159f3c23e8969c6e1c2597838d453f00e5445e983b66","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T14:12:47.304643Z","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":"2026-05-11T23:08:37.144039Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.19740","last_updated":"2025-01-18T03:27:45Z","snapshot_observed_at":"2026-08-15T17:16:11.897352Z","submitted_at":"2023-10-30T17:04:35Z","title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19740","snapshot_observed_at":"2026-08-12T14:12:47.304643Z","title":"Collaborative evaluation: Exploring the synergy of large language models and humans for open-ended generation evaluation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15560","last_updated":"2024-11-26T09:25:22Z","snapshot_observed_at":"2026-08-13T15:23:41.008148Z","submitted_at":"2024-11-23T13:34:50Z","title":"Do LLMs Agree on the Creativity Evaluation of Alternative Uses?","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T14:12:47.304643Z"},"links":{"cited_paper":"/paper/2310.19740","citing_paper":"/paper/2411.15560"},"observation_digest":"sha256:bd761e6c48c7c79eea5545b69cf5d30ce2784d636b63cffe0d2f2d612a190607","observation_id":"638d01f5-8136-4085-8d0e-74f6584c07c6","resolution":{"observed_at":"2026-08-12T14:12:47.304643Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.19740","last_updated":"2025-01-18T03:27:45Z","snapshot_observed_at":"2026-08-15T17:16:11.897352Z","submitted_at":"2023-10-30T17:04:35Z","title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks","version":2},"cited_work":{"arxiv_id":"2310.19740","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.19740","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"770b872e-d710-40b9-92a6-48a65678d85c","year":2023},"citing_paper":{"arxiv_id":"2412.05579","last_updated":"2024-12-10T05:49:12Z","snapshot_observed_at":"2026-08-11T23:22:45.789386Z","submitted_at":"2024-12-07T08:07:24Z","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","version":2},"reference_index":136,"source":"pdf_text","source_observed_at":"2026-05-11T23:08:34.312466Z"},"links":{"cited_paper":"/paper/2310.19740","citing_paper":"/paper/2412.05579"},"observation_digest":"sha256:beedefd284497bb4f9375c0f1fcc9a21caa62aabdbdb4bfdc3082090d701f057","observation_id":"6f170774-89e9-4bea-b4da-74d6022d32e8","resolution":{"observed_at":"2026-05-11T23:08:37.147953Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.19740","last_updated":"2025-01-18T03:27:45Z","snapshot_observed_at":"2026-08-15T17:16:11.897352Z","submitted_at":"2023-10-30T17:04:35Z","title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19740","snapshot_observed_at":"2026-08-11T18:35:56.283907Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.09645","last_updated":"2025-08-20T18:39:27Z","snapshot_observed_at":"2026-08-15T07:30:31.246400Z","submitted_at":"2024-12-10T18:52:39Z","title":"Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T18:35:56.283907Z"},"links":{"cited_paper":"/paper/2310.19740","citing_paper":"/paper/2412.09645"},"observation_digest":"sha256:6b0e1fdf3434c3c347184821053976a039d1fa9afe17427739813408c863a923","observation_id":"68a54e23-6b77-4cbc-adc2-4295a2e2f1eb","resolution":{"observed_at":"2026-08-11T18:35:56.283907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.19740","last_updated":"2025-01-18T03:27:45Z","snapshot_observed_at":"2026-08-15T17:16:11.897352Z","submitted_at":"2023-10-30T17:04:35Z","title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19740","snapshot_observed_at":"2026-08-10T14:51:43.478395Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14956","last_updated":"2025-05-31T01:44:04Z","snapshot_observed_at":"2026-08-13T17:22:22.632514Z","submitted_at":"2025-01-24T22:44:22Z","title":"ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generation","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T14:51:43.478395Z"},"links":{"cited_paper":"/paper/2310.19740","citing_paper":"/paper/2501.14956"},"observation_digest":"sha256:b6cf9dff50000d8038ca24d480a0b12b5e52c8d0fad2c2290f6ab22c14dfb202","observation_id":"a661602b-b421-4e15-bf42-8abe0032a569","resolution":{"observed_at":"2026-08-10T14:51:43.478395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2310.19740/citation-record","integrity":"/paper/2310.19740/integrity","json":"/paper/2310.19740/citation-record.json","paper":"/paper/2310.19740"},"outbound":[],"paper":{"arxiv_id":"2310.19740","last_updated":"2025-01-18T03:27:45Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T17:16:11.897352Z","submitted_at":"2023-10-30T17:04:35Z","title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2310.19740."}