{"as_of":"2026-08-20T13:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a24fa85beb5226ae9f9a991894a040032563f09b178fc47bb8590314d933052b","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":"2026-08-20T06:33:59.587034+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":"2026-05-18T15:30:29.933558Z","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":"2026-05-18T15:31:33.253539Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.18091","last_updated":"2024-02-28T06:24:39Z","snapshot_observed_at":"2026-08-16T14:14:39.683790Z","submitted_at":"2024-02-28T06:24:39Z","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning","version":1},"cited_work":{"arxiv_id":"2402.18091","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.18091","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Polos: Multimodal Metric Learning from Human Feed- back for Image Captioning, Feb","venue":null,"work_id":"03089214-10ed-429d-87f1-9f996bb881e6","year":2024},"citing_paper":{"arxiv_id":"2509.16538","last_updated":"2026-04-19T03:58:34Z","snapshot_observed_at":"2026-08-13T00:07:57.935058Z","submitted_at":"2025-09-20T05:04:41Z","title":"VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-18T15:30:29.933558Z"},"links":{"cited_paper":"/paper/2402.18091","citing_paper":"/paper/2509.16538"},"observation_digest":"sha256:c70ae5447c1c761ae3be62f2e42e9d42f89ba83bbf7f307f0b633685fd6141a1","observation_id":"77336794-b841-4b7e-ae96-1d57ca2ff7b3","resolution":{"observed_at":"2026-05-18T15:31:33.256865Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.18091/citation-record","integrity":"/paper/2402.18091/integrity","json":"/paper/2402.18091/citation-record.json","paper":"/paper/2402.18091"},"outbound":[],"paper":{"arxiv_id":"2402.18091","last_updated":"2024-02-28T06:24:39Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T14:14:39.683790Z","submitted_at":"2024-02-28T06:24:39Z","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2402.18091."}