{"as_of":"2026-08-16T14:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aa393b806697d66105074007f4fbe0ea12cc7c413e741ee715ef8c5aba66ae5f","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T13:06:07.651422Z","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":"2026-05-10T23:35:50.621785Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2012.02339","last_updated":"2021-11-10T23:52:50Z","snapshot_observed_at":"2026-08-15T06:17:46.057837Z","submitted_at":"2020-12-04T00:05:02Z","title":"Understanding Guided Image Captioning Performance across Domains","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.02339","snapshot_observed_at":"2026-08-12T13:06:07.651422Z","title":"Ng, Bo Pang, Piyush Sharma, and Radu Soricut","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.16508","last_updated":"2025-05-01T03:41:42Z","snapshot_observed_at":"2026-08-15T21:31:08.434189Z","submitted_at":"2024-11-25T15:44:42Z","title":"All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T13:06:07.651422Z"},"links":{"cited_paper":"/paper/2012.02339","citing_paper":"/paper/2411.16508"},"observation_digest":"sha256:f11481ed0b126b4cfc9994c2a03aa726759ae0341ed90c1352ce811de770592e","observation_id":"aa944d7c-7702-41aa-8289-2b8a0f0b1f38","resolution":{"observed_at":"2026-08-12T13:06:07.651422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.02339","last_updated":"2021-11-10T23:52:50Z","snapshot_observed_at":"2026-08-15T06:17:46.057837Z","submitted_at":"2020-12-04T00:05:02Z","title":"Understanding Guided Image Captioning Performance across Domains","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.02339","snapshot_observed_at":"2026-08-11T23:16:56.089065Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.02641","last_updated":"2024-12-03T18:13:37Z","snapshot_observed_at":"2026-08-14T20:45:11.791950Z","submitted_at":"2024-12-03T18:13:37Z","title":"SEMANTIC SEE-THROUGH GOGGLES: Wearing Linguistic Virtual Reality in (Artificial) Intelligence","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T23:16:56.089065Z"},"links":{"cited_paper":"/paper/2012.02339","citing_paper":"/paper/2412.02641"},"observation_digest":"sha256:d3b59d0faab954edcaa0829f749d971fc9eb3398d4ca57ad6d90a69f0d5fafc7","observation_id":"dd34e8e4-85b6-49b5-8d76-1e10c9a0520e","resolution":{"observed_at":"2026-08-11T23:16:56.089065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.02339","last_updated":"2021-11-10T23:52:50Z","snapshot_observed_at":"2026-08-15T06:17:46.057837Z","submitted_at":"2020-12-04T00:05:02Z","title":"Understanding Guided Image Captioning Performance across Domains","version":3},"cited_work":{"arxiv_id":"2012.02339","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2012.02339","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ng, Bo Pang, Piyush Sharma, and Radu Soricut","venue":null,"work_id":"d2a68207-7b80-4659-b631-ab6277674754","year":2012},"citing_paper":{"arxiv_id":"2604.04579","last_updated":"2026-04-07T05:30:10Z","snapshot_observed_at":"2026-07-06T22:53:33.177713Z","submitted_at":"2026-04-06T10:25:16Z","title":"Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-10T19:01:18.334371Z"},"links":{"cited_paper":"/paper/2012.02339","citing_paper":"/paper/2604.04579"},"observation_digest":"sha256:09da476f7ea5fa4e59f8aa5782d8b76f35e4873794e45bfffa66bb4edf787189","observation_id":"a840ad37-5379-4322-9854-2e11a7a00bb6","resolution":{"observed_at":"2026-05-10T23:35:50.623993Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2012.02339/citation-record","integrity":"/paper/2012.02339/integrity","json":"/paper/2012.02339/citation-record.json","paper":"/paper/2012.02339"},"outbound":[],"paper":{"arxiv_id":"2012.02339","last_updated":"2021-11-10T23:52:50Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T06:17:46.057837Z","submitted_at":"2020-12-04T00:05:02Z","title":"Understanding Guided Image Captioning Performance across Domains"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2012.02339."}