{"as_of":"2026-08-08T16:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e3d1ef4a9cdb932f9eb1ac165ece318c709c1206890549ce5bdefa0158b445bc","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T05:21:34.967677Z","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":"2026-05-11T10:31:03.770874Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.15021","last_updated":"2024-03-01T01:52:58Z","snapshot_observed_at":"2026-08-07T12:09:14.156070Z","submitted_at":"2024-02-22T23:42:25Z","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15021","snapshot_observed_at":"2026-08-07T05:21:34.967677Z","title":"Clove: Encoding compositional lan- guage in contrastive vision-language models.arXiv preprint arXiv:2402.15021, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08227","last_updated":"2025-06-09T20:53:43Z","snapshot_observed_at":"2026-08-07T05:14:41.333172Z","submitted_at":"2025-06-09T20:53:43Z","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:34.967677Z"},"links":{"cited_paper":"/paper/2402.15021","citing_paper":"/paper/2506.08227"},"observation_digest":"sha256:b28029322d872ad3f68cbd57d7615fe3c4dd2774c031f392daa2108c8c2163da","observation_id":"8c9aacce-3096-449c-9206-cc24b38c8c1f","resolution":{"observed_at":"2026-08-07T05:21:34.967677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15021","last_updated":"2024-03-01T01:52:58Z","snapshot_observed_at":"2026-08-07T12:09:14.156070Z","submitted_at":"2024-02-22T23:42:25Z","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","version":2},"cited_work":{"arxiv_id":"2402.15021","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.15021","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Clove: Encoding compositional language in contrastive vision-language models","venue":null,"work_id":"b0ccf7cb-4578-4792-b61c-9b6256bdd836","year":2024},"citing_paper":{"arxiv_id":"2604.12335","last_updated":"2026-04-14T06:17:35Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T06:17:35Z","title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T15:26:55.369840Z"},"links":{"cited_paper":"/paper/2402.15021","citing_paper":"/paper/2604.12335"},"observation_digest":"sha256:ec19a4439349140265b350fb0926d18fb0b647d8ee0f9934bac750f1b16fe8cc","observation_id":"f2907c80-ff48-4e60-8b08-4853fb5f356f","resolution":{"observed_at":"2026-05-11T10:31:03.782182Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.15021/citation-record","integrity":"/paper/2402.15021/integrity","json":"/paper/2402.15021/citation-record.json","paper":"/paper/2402.15021"},"outbound":[],"paper":{"arxiv_id":"2402.15021","last_updated":"2024-03-01T01:52:58Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T12:09:14.156070Z","submitted_at":"2024-02-22T23:42:25Z","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.15021."}