{"as_of":"2026-08-05T00:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2833c9355970d34c6a833513ab3e3bfc61da449ecaf3a19a2c01ed68a141cf4","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":"2026-08-04T06:34:03.388597+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":"2026-08-04T12:44:14.390327Z","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":"2026-07-04T19:50:10.207239Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.12055","last_updated":"2024-06-28T14:53:35Z","snapshot_observed_at":"2026-07-06T17:32:10.828230Z","submitted_at":"2024-02-19T11:19:02Z","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?","version":2},"cited_work":{"arxiv_id":"2402.12055","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.12055","snapshot_observed_at":"2026-07-04T19:50:10.207239Z","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria? ArXiv, abs/2402.12055","venue":null,"work_id":"fc365d4a-7942-4ac2-8152-629c4871264b","year":2024},"citing_paper":{"arxiv_id":"2405.14782","last_updated":"2026-05-31T00:04:33Z","snapshot_observed_at":"2026-08-02T05:44:43.939336Z","submitted_at":"2024-05-23T16:50:49Z","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","version":2},"reference_index":285,"source":"arxiv_source","source_observed_at":"2026-05-16T18:44:49.519995Z"},"links":{"cited_paper":"/paper/2402.12055","citing_paper":"/paper/2405.14782"},"observation_digest":"sha256:d61d7295fbc881fb7345f3adc7d13b04172d3f11b8de017584fe94e59c1d38ae","observation_id":"1e9f2742-8743-4cf5-bd34-8b97542a5f8a","resolution":{"observed_at":"2026-05-16T18:44:49.888530Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12055","last_updated":"2024-06-28T14:53:35Z","snapshot_observed_at":"2026-07-06T17:32:10.828230Z","submitted_at":"2024-02-19T11:19:02Z","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12055","snapshot_observed_at":"2026-08-04T12:44:14.390327Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.06242","last_updated":"2025-10-03T08:37:33Z","snapshot_observed_at":"2026-08-04T12:44:10.596654Z","submitted_at":"2025-10-03T08:37:33Z","title":"Transparent Reference-free Automated Evaluation of Open-Ended User Survey Responses","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T12:44:14.390327Z"},"links":{"cited_paper":"/paper/2402.12055","citing_paper":"/paper/2510.06242"},"observation_digest":"sha256:1b9c52ee315897117ee8780c750b8f0fef6f1e6bb8e3c96e237e6cc845cd453d","observation_id":"b51cf4c6-0b5f-4b74-a137-e2b02eb8fd13","resolution":{"observed_at":"2026-08-04T12:44:14.390327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12055","last_updated":"2024-06-28T14:53:35Z","snapshot_observed_at":"2026-07-06T17:32:10.828230Z","submitted_at":"2024-02-19T11:19:02Z","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?","version":2},"cited_work":{"arxiv_id":"2402.12055","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.12055","snapshot_observed_at":"2026-07-04T19:50:10.207239Z","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria? ArXiv, abs/2402.12055","venue":null,"work_id":"fc365d4a-7942-4ac2-8152-629c4871264b","year":2024},"citing_paper":{"arxiv_id":"2606.25445","last_updated":"2026-06-24T06:15:24Z","snapshot_observed_at":"2026-07-06T23:59:52.373272Z","submitted_at":"2026-06-24T06:15:24Z","title":"C3-Bench: A Context-Aware Change Captioning Benchmark","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-25T21:02:52.529391Z"},"links":{"cited_paper":"/paper/2402.12055","citing_paper":"/paper/2606.25445"},"observation_digest":"sha256:d34ba42fbfa7fdd798ff890742d7b927081efd2cf4ce83c9886fb542e916414e","observation_id":"f26412c7-65eb-4789-95b6-a0771491f71a","resolution":{"observed_at":"2026-07-04T19:50:10.209082Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.12055/citation-record","integrity":"/paper/2402.12055/integrity","json":"/paper/2402.12055/citation-record.json","paper":"/paper/2402.12055"},"outbound":[],"paper":{"arxiv_id":"2402.12055","last_updated":"2024-06-28T14:53:35Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T17:32:10.828230Z","submitted_at":"2024-02-19T11:19:02Z","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.12055."}