{"as_of":"2026-08-13T12:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f32805c7a556e5bd3835874d5b724f68e635e46a087b760d02135f701d3ccbaa","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T12:10:17.475874Z","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":"2026-08-11T18:11:56.394541Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.13273","last_updated":"2023-05-08T02:29:28Z","snapshot_observed_at":"2026-08-13T11:55:00.778757Z","submitted_at":"2023-04-26T04:06:20Z","title":"From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping","version":3},"cited_work":{"arxiv_id":"2304.13273","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.13273","snapshot_observed_at":"2026-08-11T18:11:56.394541Z","title":"From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping","venue":"cs.CV","work_id":"8d47cfb4-7bf4-444c-8dec-8da8bd684a91","year":2023},"citing_paper":{"arxiv_id":"2412.08158","last_updated":"2024-12-11T07:29:04Z","snapshot_observed_at":"2026-08-12T07:36:23.412895Z","submitted_at":"2024-12-11T07:29:04Z","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T18:11:54.531612Z"},"links":{"cited_paper":"/paper/2304.13273","citing_paper":"/paper/2412.08158"},"observation_digest":"sha256:a7e6339043a90cf62b00571065b39de947f3539fa3b5bd6cb4f8af230f953556","observation_id":"5564bba4-21b8-4a19-9800-9fd834cb580c","resolution":{"observed_at":"2026-08-11T18:11:56.400451Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.13273","last_updated":"2023-05-08T02:29:28Z","snapshot_observed_at":"2026-08-13T11:55:00.778757Z","submitted_at":"2023-04-26T04:06:20Z","title":"From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.13273","snapshot_observed_at":"2026-08-12T12:10:17.475874Z","title":"From association to genera- tion: Text-only captioning by unsupervised cross-modal mapping,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11013","last_updated":"2026-08-11T14:57:44Z","snapshot_observed_at":"2026-08-13T12:24:28.533875Z","submitted_at":"2026-08-11T14:57:44Z","title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T12:10:17.475874Z"},"links":{"cited_paper":"/paper/2304.13273","citing_paper":"/paper/2608.11013"},"observation_digest":"sha256:dca16136a0b668ea1814171d1311ef8b09b121b72771a574aedbe8f6beaf0cb7","observation_id":"45b26696-9dfd-472a-bc6e-f1d27156b202","resolution":{"observed_at":"2026-08-12T12:10:17.475874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2304.13273/citation-record","integrity":"/paper/2304.13273/integrity","json":"/paper/2304.13273/citation-record.json","paper":"/paper/2304.13273"},"outbound":[],"paper":{"arxiv_id":"2304.13273","last_updated":"2023-05-08T02:29:28Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T11:55:00.778757Z","submitted_at":"2023-04-26T04:06:20Z","title":"From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2304.13273."}