{"as_of":"2026-08-15T21:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:660c894743a48bfbbd938aa452eaab53f9d5f4cd5280360f299201b292aa7df8","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":"2026-08-15T06:32:42.880941+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":"2026-08-12T05:34:47.124307Z","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":"2026-05-11T05:56:11.298575Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.04702","last_updated":"2022-04-14T16:11:12Z","snapshot_observed_at":"2026-08-15T17:35:19.701917Z","submitted_at":"2021-01-12T19:16:51Z","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","version":5},"cited_work":{"arxiv_id":"2101.04702","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.04702","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Y ., Baldridge, J., Lee, H., and Yang, Y","venue":null,"work_id":"051a956f-5d09-4c9f-9e35-57e685a6946f","year":2021},"citing_paper":{"arxiv_id":"2112.10741","last_updated":"2022-03-08T18:18:49Z","snapshot_observed_at":"2026-08-07T12:21:17.790675Z","submitted_at":"2021-12-20T18:42:55Z","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-11T05:56:10.970591Z"},"links":{"cited_paper":"/paper/2101.04702","citing_paper":"/paper/2112.10741"},"observation_digest":"sha256:341fdcccb02bfd6dbe61ddfbe6a0eaee52d10eaf9a4e1beac347480860b3fa64","observation_id":"30a3fc05-1447-447f-abe4-abaf0ae12d1b","resolution":{"observed_at":"2026-05-11T05:56:11.305595Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.04702","last_updated":"2022-04-14T16:11:12Z","snapshot_observed_at":"2026-08-15T17:35:19.701917Z","submitted_at":"2021-01-12T19:16:51Z","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","version":5},"cited_work":{"arxiv_id":"2101.04702","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.04702","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Y ., Baldridge, J., Lee, H., and Yang, Y","venue":null,"work_id":"051a956f-5d09-4c9f-9e35-57e685a6946f","year":2021},"citing_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-08-15T12:50:58.405488Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-10T16:55:57.612364Z"},"links":{"cited_paper":"/paper/2101.04702","citing_paper":"/paper/2204.06125"},"observation_digest":"sha256:e7c3895f803288808a1d943aba1a54171a4789742e47f1ab9465148f550566e0","observation_id":"8d24112d-fd04-433a-b47e-43176958422b","resolution":{"observed_at":"2026-05-10T16:55:57.777378Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.04702","last_updated":"2022-04-14T16:11:12Z","snapshot_observed_at":"2026-08-15T17:35:19.701917Z","submitted_at":"2021-01-12T19:16:51Z","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.04702","snapshot_observed_at":"2026-08-12T05:34:47.124307Z","title":"Cross-modal contrastive learning for text-to-image generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00373","last_updated":"2024-11-30T06:45:13Z","snapshot_observed_at":"2026-08-14T01:22:15.534970Z","submitted_at":"2024-11-30T06:45:13Z","title":"Approximate Fiber Product: A Preliminary Algebraic-Geometric Perspective on Multimodal Embedding Alignment","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T05:34:47.124307Z"},"links":{"cited_paper":"/paper/2101.04702","citing_paper":"/paper/2412.00373"},"observation_digest":"sha256:db393b0f5591ef0e99baa3cd4fa394438fa5c9868113b59dafe3688bd8748b9b","observation_id":"cfb59902-4345-426a-a4df-0ace90b9d2fb","resolution":{"observed_at":"2026-08-12T05:34:47.124307Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2101.04702/citation-record","integrity":"/paper/2101.04702/integrity","json":"/paper/2101.04702/citation-record.json","paper":"/paper/2101.04702"},"outbound":[],"paper":{"arxiv_id":"2101.04702","last_updated":"2022-04-14T16:11:12Z","latest_version":5,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T17:35:19.701917Z","submitted_at":"2021-01-12T19:16:51Z","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2101.04702."}