{"as_of":"2026-08-09T20:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:37841eec040ad9754d160828411015180a0fa7cea054a0ea856eae66aad4d72e","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":"2026-08-09T06:31:02.800959+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":"2026-07-14T16:20:19.874172Z","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":"2404.19128","last_updated":"2024-04-29T22:06:17Z","snapshot_observed_at":"2026-08-04T02:46:39.581200Z","submitted_at":"2024-04-29T22:06:17Z","title":"Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19128","snapshot_observed_at":"2026-07-11T16:32:55.757864Z","title":"arXiv preprint arXiv:2404.19128 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04605","last_updated":"2026-07-13T07:13:49Z","snapshot_observed_at":"2026-08-04T23:09:53.876810Z","submitted_at":"2026-07-06T02:19:11Z","title":"Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-07-11T16:32:55.757864Z"},"links":{"cited_paper":"/paper/2404.19128","citing_paper":"/paper/2607.04605"},"observation_digest":"sha256:70e86bc985df699c834d21eacf44ec8b9599221c03b646bb6d1e1248e9975340","observation_id":"7af040c9-0487-4b28-87e5-0854081b4c33","resolution":{"observed_at":"2026-07-11T16:32:55.757864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19128","last_updated":"2024-04-29T22:06:17Z","snapshot_observed_at":"2026-08-04T02:46:39.581200Z","submitted_at":"2024-04-29T22:06:17Z","title":"Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19128","snapshot_observed_at":"2026-07-14T16:20:19.874172Z","title":"arXiv preprint arXiv:2404.19128 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04605","last_updated":"2026-07-13T07:13:49Z","snapshot_observed_at":"2026-08-04T23:09:53.876810Z","submitted_at":"2026-07-06T02:19:11Z","title":"Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-07-14T16:20:19.874172Z"},"links":{"cited_paper":"/paper/2404.19128","citing_paper":"/paper/2607.04605"},"observation_digest":"sha256:88985918e8e15318b4e66576066f47516e98f4bdbf3bbd45477de18c27552a2f","observation_id":"d6f69e71-bdc3-4e4c-be96-b8a33365b224","resolution":{"observed_at":"2026-07-14T16:20:19.874172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2404.19128/citation-record","integrity":"/paper/2404.19128/integrity","json":"/paper/2404.19128/citation-record.json","paper":"/paper/2404.19128"},"outbound":[],"paper":{"arxiv_id":"2404.19128","last_updated":"2024-04-29T22:06:17Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T02:46:39.581200Z","submitted_at":"2024-04-29T22:06:17Z","title":"Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM"},"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 2 inbound Pith citation observations for arXiv:2404.19128."}