{"as_of":"2026-08-10T07:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e6991c59c929edff27e3bedf36c34345dc5f4a5fd7e0ee6dc0eb12597abde230","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T23:06:04.855888Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.15210","last_updated":"2025-05-29T23:35:10Z","snapshot_observed_at":"2026-08-07T17:59:53.519594Z","submitted_at":"2025-02-21T04:53:11Z","title":"PairBench: Are Vision-Language Models Reliable at Comparing What They See?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15210","snapshot_observed_at":"2026-08-03T23:06:04.855888Z","title":"Pairbench: Are vision-language models reliable at comparing what they see?, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.07332","last_updated":"2026-06-09T21:30:32Z","snapshot_observed_at":"2026-08-09T15:43:09.649238Z","submitted_at":"2025-11-10T17:35:21Z","title":"Grounding Computer Use Agents on Human Demonstrations","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-03T23:06:04.855888Z"},"links":{"cited_paper":"/paper/2502.15210","citing_paper":"/paper/2511.07332"},"observation_digest":"sha256:48ffc3e7ba5067152a7d8baf9b51369b0651e2481df5bc6609452dbff43efd75","observation_id":"7a6a37c1-697a-44e6-a321-fbc5b1846e61","resolution":{"observed_at":"2026-08-03T23:06:04.855888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.15210","last_updated":"2025-05-29T23:35:10Z","snapshot_observed_at":"2026-08-07T17:59:53.519594Z","submitted_at":"2025-02-21T04:53:11Z","title":"PairBench: Are Vision-Language Models Reliable at Comparing What They See?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15210","snapshot_observed_at":"2026-08-03T00:53:52.745687Z","title":"arXiv preprint arXiv:2502.15210 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28645","last_updated":"2026-05-29T05:48:19Z","snapshot_observed_at":"2026-08-05T23:11:22.264645Z","submitted_at":"2026-05-29T05:48:19Z","title":"Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-03T00:53:52.745687Z"},"links":{"cited_paper":"/paper/2502.15210","citing_paper":"/paper/2607.28645"},"observation_digest":"sha256:62bf217a938ef384d69c37288927a49b52d1acaa3e301791c799bce19fb76ee4","observation_id":"decd1210-eb75-4a3e-8600-7079d7ed62ab","resolution":{"observed_at":"2026-08-03T00:53:52.745687Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.15210/citation-record","integrity":"/paper/2502.15210/integrity","json":"/paper/2502.15210/citation-record.json","paper":"/paper/2502.15210"},"outbound":[],"paper":{"arxiv_id":"2502.15210","last_updated":"2025-05-29T23:35:10Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T17:59:53.519594Z","submitted_at":"2025-02-21T04:53:11Z","title":"PairBench: Are Vision-Language Models Reliable at Comparing What They See?"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2502.15210."}