{"as_of":"2026-08-17T07:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a277962184d20fcf9980837b6a336b312522d3130e04f170f2d65f2215ef78fb","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":"2026-08-17T06:30:58.91139+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":"2026-08-07T13:40:24.455373Z","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":"2026-05-21T22:00:41.495691Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.00840","last_updated":"2021-06-01T22:33:53Z","snapshot_observed_at":"2026-08-16T18:20:25.028859Z","submitted_at":"2021-06-01T22:33:53Z","title":"Comparing Test Sets with Item Response Theory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.00840","snapshot_observed_at":"2026-08-07T13:40:24.455373Z","title":"Comparing test sets with item response theory","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21389","last_updated":"2025-05-27T16:17:15Z","snapshot_observed_at":"2026-08-15T07:49:04.403413Z","submitted_at":"2025-05-27T16:17:15Z","title":"AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T13:40:24.455373Z"},"links":{"cited_paper":"/paper/2106.00840","citing_paper":"/paper/2505.21389"},"observation_digest":"sha256:9e64c3b4cc2832485bd03060dd562cae8ff3d9ff255bf3ae2f2d2b41b16b2f10","observation_id":"343cb7bb-915e-49a8-9ab6-0fe700ab8fd4","resolution":{"observed_at":"2026-08-07T13:40:24.455373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.00840","last_updated":"2021-06-01T22:33:53Z","snapshot_observed_at":"2026-08-16T18:20:25.028859Z","submitted_at":"2021-06-01T22:33:53Z","title":"Comparing Test Sets with Item Response Theory","version":1},"cited_work":{"arxiv_id":"2106.00840","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.00840","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Comparing test sets with item response theory","venue":null,"work_id":"167c8a7d-b4b0-4849-a6f6-c007e65564fa","year":2021},"citing_paper":{"arxiv_id":"2509.19590","last_updated":"2026-05-16T01:07:51Z","snapshot_observed_at":"2026-08-16T22:43:15.745999Z","submitted_at":"2025-09-23T21:29:04Z","title":"Position: AI Evaluations Should be Grounded on a Theory of Capability","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-05-21T21:57:55.834632Z"},"links":{"cited_paper":"/paper/2106.00840","citing_paper":"/paper/2509.19590"},"observation_digest":"sha256:9aab31c4f2ce41f4bf12ea28051f32ed5290c64f109dc709d356ea2b961b8916","observation_id":"537cf1e3-2aa2-46a5-b60b-6bcf23db09b7","resolution":{"observed_at":"2026-05-21T22:00:41.497970Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.00840","last_updated":"2021-06-01T22:33:53Z","snapshot_observed_at":"2026-08-16T18:20:25.028859Z","submitted_at":"2021-06-01T22:33:53Z","title":"Comparing Test Sets with Item Response Theory","version":1},"cited_work":{"arxiv_id":"2106.00840","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.00840","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Comparing test sets with item response theory","venue":null,"work_id":"167c8a7d-b4b0-4849-a6f6-c007e65564fa","year":2021},"citing_paper":{"arxiv_id":"2605.18663","last_updated":"2026-05-18T17:09:50Z","snapshot_observed_at":"2026-08-16T14:51:17.741960Z","submitted_at":"2026-05-18T17:09:50Z","title":"GIM: Evaluating models via tasks that integrate multiple cognitive domains","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-20T10:25:35.620798Z"},"links":{"cited_paper":"/paper/2106.00840","citing_paper":"/paper/2605.18663"},"observation_digest":"sha256:a2604dec8e89bfcd35eed7660f537a6c7bdd8cd3cd0888e33fe42dafa3b0aac4","observation_id":"e04f4ff7-5667-4d7a-8c7d-0c665156f737","resolution":{"observed_at":"2026-05-20T10:28:12.137136Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.00840/citation-record","integrity":"/paper/2106.00840/integrity","json":"/paper/2106.00840/citation-record.json","paper":"/paper/2106.00840"},"outbound":[],"paper":{"arxiv_id":"2106.00840","last_updated":"2021-06-01T22:33:53Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T18:20:25.028859Z","submitted_at":"2021-06-01T22:33:53Z","title":"Comparing Test Sets with Item Response Theory"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2106.00840."}