{"as_of":"2026-08-10T14:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b4719bac37dd8063495de840ca0b642651d9b13f5d8fd7409a15a9f84428dfa9","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":"2026-08-10T06:31:04.303077+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":"2026-08-05T16:31:57.838708Z","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":"2026-08-05T16:31:58.191472Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.16934","last_updated":"2024-05-27T08:26:58Z","snapshot_observed_at":"2026-08-10T03:54:06.079351Z","submitted_at":"2024-05-27T08:26:58Z","title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","version":1},"cited_work":{"arxiv_id":"2405.16934","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.16934","snapshot_observed_at":"2026-08-05T16:31:58.191472Z","title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","venue":"cs.CV","work_id":"b270f40c-d517-417c-8e38-199f8c9f714b","year":2024},"citing_paper":{"arxiv_id":"2508.18421","last_updated":"2025-08-25T19:11:03Z","snapshot_observed_at":"2026-08-09T12:25:22.726555Z","submitted_at":"2025-08-25T19:11:03Z","title":"Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T16:31:57.838708Z"},"links":{"cited_paper":"/paper/2405.16934","citing_paper":"/paper/2508.18421"},"observation_digest":"sha256:41d9ef334d5334e2874898868d3173242e5a80c7f6a1c16a227f39872cf4e09f","observation_id":"8ff6e04e-4994-44bd-af45-61de65be504b","resolution":{"observed_at":"2026-08-05T16:31:58.194545Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.16934/citation-record","integrity":"/paper/2405.16934/integrity","json":"/paper/2405.16934/citation-record.json","paper":"/paper/2405.16934"},"outbound":[],"paper":{"arxiv_id":"2405.16934","last_updated":"2024-05-27T08:26:58Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T03:54:06.079351Z","submitted_at":"2024-05-27T08:26:58Z","title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR"},"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 1 inbound Pith citation observation for arXiv:2405.16934."}