{"as_of":"2026-08-14T01:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:762e187707083e185c469facf476a622ab017c25320a269724c751c8c7198cb5","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":"2026-08-13T06:32:02.005865+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":"2026-08-11T14:06:27.674532Z","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":"2026-07-03T05:47:41.832072Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2111.14447","last_updated":"2022-03-31T14:53:47Z","snapshot_observed_at":"2026-08-13T21:29:47.751790Z","submitted_at":"2021-11-29T11:01:49Z","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","version":2},"cited_work":{"arxiv_id":"2111.14447","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2111.14447","snapshot_observed_at":"2026-07-03T05:47:41.832072Z","title":"Tewel, Y","venue":null,"work_id":"fdf4253c-83f9-4aef-902c-3c36369b0afd","year":2022},"citing_paper":{"arxiv_id":"2204.00598","last_updated":"2022-05-27T17:52:50Z","snapshot_observed_at":"2026-08-13T04:37:51.649726Z","submitted_at":"2022-04-01T17:43:13Z","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-16T09:50:00.546571Z"},"links":{"cited_paper":"/paper/2111.14447","citing_paper":"/paper/2204.00598"},"observation_digest":"sha256:b66868e02f108d5a17f1169ca5102835dd95dba152d9601a0c89e8beb6bec72d","observation_id":"97f643e6-a4fa-4b07-b1db-3ba60364e490","resolution":{"observed_at":"2026-05-16T09:50:00.646798Z","resolver_source":"arxiv_id","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":"2111.14447","last_updated":"2022-03-31T14:53:47Z","snapshot_observed_at":"2026-08-13T21:29:47.751790Z","submitted_at":"2021-11-29T11:01:49Z","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.14447","snapshot_observed_at":"2026-08-11T14:06:27.674532Z","title":"Zero-shot image-to-text generation for visual-semantic arith- metic","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.12463","last_updated":"2025-04-05T16:33:40Z","snapshot_observed_at":"2026-08-12T04:32:17.344669Z","submitted_at":"2024-12-17T01:52:12Z","title":"Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:27.674532Z"},"links":{"cited_paper":"/paper/2111.14447","citing_paper":"/paper/2412.12463"},"observation_digest":"sha256:060874f696c52bfca1f9b42fbb847802c28b010e9531e54399db1c757e65b6fe","observation_id":"dc7708a7-bb29-4863-a26d-95a076377979","resolution":{"observed_at":"2026-08-11T14:06:27.674532Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.14447","last_updated":"2022-03-31T14:53:47Z","snapshot_observed_at":"2026-08-13T21:29:47.751790Z","submitted_at":"2021-11-29T11:01:49Z","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","version":2},"cited_work":{"arxiv_id":"2111.14447","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2111.14447","snapshot_observed_at":"2026-07-03T05:47:41.832072Z","title":"Tewel, Y","venue":null,"work_id":"fdf4253c-83f9-4aef-902c-3c36369b0afd","year":2022},"citing_paper":{"arxiv_id":"2606.11074","last_updated":"2026-06-10T03:48:53Z","snapshot_observed_at":"2026-08-12T08:49:59.183581Z","submitted_at":"2026-06-09T16:34:37Z","title":"Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models","version":2},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-06-27T13:04:14.886733Z"},"links":{"cited_paper":"/paper/2111.14447","citing_paper":"/paper/2606.11074"},"observation_digest":"sha256:c9b675fb7170e6a09acfb6fc3817ec2ded42450f89c5134e8504f263b5c77eca","observation_id":"7578f220-aa30-4a6c-995a-aa370e180d1b","resolution":{"observed_at":"2026-07-03T05:47:41.833701Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2111.14447/citation-record","integrity":"/paper/2111.14447/integrity","json":"/paper/2111.14447/citation-record.json","paper":"/paper/2111.14447"},"outbound":[],"paper":{"arxiv_id":"2111.14447","last_updated":"2022-03-31T14:53:47Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T21:29:47.751790Z","submitted_at":"2021-11-29T11:01:49Z","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic"},"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 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2111.14447."}