{"as_of":"2026-08-09T21:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d5fd4f00c7d43765012c071587c05dd12ae0827fca3be205ef94ad4acfae16f6","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T15:06:54.866504Z","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":"2026-05-18T11:01:17.105752Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2009.13888","last_updated":"2021-03-03T06:22:32Z","snapshot_observed_at":"2026-07-06T09:59:44.649578Z","submitted_at":"2020-09-29T09:25:31Z","title":"Utility is in the Eye of the User: A Critique of NLP Leaderboards","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.13888","snapshot_observed_at":"2026-08-08T15:06:54.866504Z","title":"Utility is in the Eye of the User : A Critique of NLP Leaderboards , March 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.06559","last_updated":"2025-05-25T23:36:47Z","snapshot_observed_at":"2026-08-08T23:28:10.897343Z","submitted_at":"2025-02-10T15:25:06Z","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-08T15:06:54.866504Z"},"links":{"cited_paper":"/paper/2009.13888","citing_paper":"/paper/2502.06559"},"observation_digest":"sha256:a270484f502fd9b46d7926b017561aa808e7fb42dbf8befee6e82080f0fa5f51","observation_id":"0017ebb3-a924-48e8-80d4-3ef1c890c58b","resolution":{"observed_at":"2026-08-08T15:06:54.866504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.13888","last_updated":"2021-03-03T06:22:32Z","snapshot_observed_at":"2026-07-06T09:59:44.649578Z","submitted_at":"2020-09-29T09:25:31Z","title":"Utility is in the Eye of the User: A Critique of NLP Leaderboards","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.13888","snapshot_observed_at":"2026-08-07T04:06:29.022554Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.11604","last_updated":"2025-06-27T10:12:42Z","snapshot_observed_at":"2026-08-09T05:29:09.288699Z","submitted_at":"2025-06-13T09:20:41Z","title":"VLM@school -- Evaluation of AI image understanding on German middle school knowledge","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:06:29.022554Z"},"links":{"cited_paper":"/paper/2009.13888","citing_paper":"/paper/2506.11604"},"observation_digest":"sha256:66c9e4a797d1101c6f82d54eafa46710123bf2c05267adca0bfb8a6b0beaf8c5","observation_id":"0c314a30-c5e5-447a-ab89-49843e9caecd","resolution":{"observed_at":"2026-08-07T04:06:29.022554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.13888","last_updated":"2021-03-03T06:22:32Z","snapshot_observed_at":"2026-07-06T09:59:44.649578Z","submitted_at":"2020-09-29T09:25:31Z","title":"Utility is in the Eye of the User: A Critique of NLP Leaderboards","version":4},"cited_work":{"arxiv_id":"2009.13888","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2009.13888","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"18c2b53d-88a4-4254-8db5-f01bc8871b47","year":2021},"citing_paper":{"arxiv_id":"2511.05501","last_updated":"2026-04-28T16:06:15Z","snapshot_observed_at":"2026-07-06T22:35:13.699594Z","submitted_at":"2025-09-30T21:36:23Z","title":"Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-18T10:59:16.139525Z"},"links":{"cited_paper":"/paper/2009.13888","citing_paper":"/paper/2511.05501"},"observation_digest":"sha256:921d4bc57455a6afe9a63035de6642481e3149384a8de12741b0032e187fbd91","observation_id":"bfee44e5-92ad-4a1e-a4af-f10d0df48641","resolution":{"observed_at":"2026-05-18T11:01:17.109691Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.13888","last_updated":"2021-03-03T06:22:32Z","snapshot_observed_at":"2026-07-06T09:59:44.649578Z","submitted_at":"2020-09-29T09:25:31Z","title":"Utility is in the Eye of the User: A Critique of NLP Leaderboards","version":4},"cited_work":{"arxiv_id":"2009.13888","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2009.13888","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"18c2b53d-88a4-4254-8db5-f01bc8871b47","year":2021},"citing_paper":{"arxiv_id":"2605.14164","last_updated":"2026-05-13T22:39:10Z","snapshot_observed_at":"2026-07-06T23:25:39.415637Z","submitted_at":"2026-05-13T22:39:10Z","title":"Unsteady Metrics and Benchmarking Cultures of AI Model Builders","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-15T04:54:26.888562Z"},"links":{"cited_paper":"/paper/2009.13888","citing_paper":"/paper/2605.14164"},"observation_digest":"sha256:140341e5f6cc5c9b4a73db9f968d6dc4822730e04b8de8b9259ae4f1c73e48f9","observation_id":"72a29015-d3a7-4b0e-b559-60bc8b13ba09","resolution":{"observed_at":"2026-05-15T04:55:03.345398Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2009.13888/citation-record","integrity":"/paper/2009.13888/integrity","json":"/paper/2009.13888/citation-record.json","paper":"/paper/2009.13888"},"outbound":[],"paper":{"arxiv_id":"2009.13888","last_updated":"2021-03-03T06:22:32Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T09:59:44.649578Z","submitted_at":"2020-09-29T09:25:31Z","title":"Utility is in the Eye of the User: A Critique of NLP Leaderboards"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2009.13888."}