{"as_of":"2026-08-18T14:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:16691d34802148bf0146be2c19d14f48ac0e652e2e9b1b0b475c2494746afa0e","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T04:32:03.403644Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-12T04:32:03.630275Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.10770","last_updated":"2024-10-02T09:18:47Z","snapshot_observed_at":"2026-08-18T04:12:01.498568Z","submitted_at":"2024-02-16T15:48:33Z","title":"How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?","version":4},"cited_work":{"arxiv_id":"2402.10770","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.10770","snapshot_observed_at":"2026-08-12T04:32:03.630275Z","title":"How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?","venue":"cs.CL","work_id":"9ce154e7-ddf8-47a1-905b-8e66c17d242c","year":2024},"citing_paper":{"arxiv_id":"2412.01333","last_updated":"2024-12-02T09:56:18Z","snapshot_observed_at":"2026-08-13T14:04:07.660512Z","submitted_at":"2024-12-02T09:56:18Z","title":"Can Large Language Models Serve as Evaluators for Code Summarization?","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T04:32:03.403644Z"},"links":{"cited_paper":"/paper/2402.10770","citing_paper":"/paper/2412.01333"},"observation_digest":"sha256:01ffd18ad9a7c4369b00e296fa4ede70e328b615fca66b69d65457d0cf4e570e","observation_id":"ab4ed19b-f959-4989-8ddc-62fd7bb645e8","resolution":{"observed_at":"2026-08-12T04:32:03.636635Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2402.10770/citation-record","integrity":"/paper/2402.10770/integrity","json":"/paper/2402.10770/citation-record.json","paper":"/paper/2402.10770"},"outbound":[],"paper":{"arxiv_id":"2402.10770","last_updated":"2024-10-02T09:18:47Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-18T04:12:01.498568Z","submitted_at":"2024-02-16T15:48:33Z","title":"How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?"},"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 1 inbound Pith citation observation for arXiv:2402.10770."}