{"as_of":"2026-08-05T04:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:476be3081a8a56986096fd2f9bb36ae2cc8d279558a1bdd7959ec5a6e0b863d6","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":"2026-08-04T06:34:03.388597+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":"2026-06-26T05:03:15.044146Z","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":"2026-07-04T13:39:50.767139Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.01913","last_updated":"2021-03-03T16:41:01Z","snapshot_observed_at":"2026-08-04T11:19:49.325661Z","submitted_at":"2021-03-02T18:13:54Z","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","version":2},"cited_work":{"arxiv_id":"2103.01913","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.01913","snapshot_observed_at":"2026-07-04T13:39:50.767139Z","title":"WIT: wikipedia-based image text dataset for multimodal multilingual machine learning","venue":null,"work_id":"094317fd-e143-4446-8761-9c366f1182b9","year":2021},"citing_paper":{"arxiv_id":"2303.15343","last_updated":"2023-09-27T12:05:41Z","snapshot_observed_at":"2026-07-06T15:08:30.190912Z","submitted_at":"2023-03-27T15:53:01Z","title":"Sigmoid Loss for Language Image Pre-Training","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-16T13:05:36.460932Z"},"links":{"cited_paper":"/paper/2103.01913","citing_paper":"/paper/2303.15343"},"observation_digest":"sha256:23b7f7f358592fe47ecc943602f1f4f9a9a631d2c62eba90a9c3e85396d02cdf","observation_id":"19d97322-a6a2-4e77-a914-2cd1e5d21699","resolution":{"observed_at":"2026-05-16T13:05:36.559014Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.01913","last_updated":"2021-03-03T16:41:01Z","snapshot_observed_at":"2026-08-04T11:19:49.325661Z","submitted_at":"2021-03-02T18:13:54Z","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","version":2},"cited_work":{"arxiv_id":"2103.01913","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.01913","snapshot_observed_at":"2026-07-04T13:39:50.767139Z","title":"WIT: wikipedia-based image text dataset for multimodal multilingual machine learning","venue":null,"work_id":"094317fd-e143-4446-8761-9c366f1182b9","year":2021},"citing_paper":{"arxiv_id":"2606.26794","last_updated":"2026-06-25T09:27:54Z","snapshot_observed_at":"2026-08-03T16:40:37.506200Z","submitted_at":"2026-06-25T09:27:54Z","title":"ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-06-26T05:03:15.044146Z"},"links":{"cited_paper":"/paper/2103.01913","citing_paper":"/paper/2606.26794"},"observation_digest":"sha256:6aab206147ec20d90d43d6b3dc4eca4826b102c0629e4045554c6fab2a488f26","observation_id":"0f035a0c-dd9e-4a42-9e26-7c81387272fc","resolution":{"observed_at":"2026-07-04T13:39:50.768586Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2103.01913/citation-record","integrity":"/paper/2103.01913/integrity","json":"/paper/2103.01913/citation-record.json","paper":"/paper/2103.01913"},"outbound":[],"paper":{"arxiv_id":"2103.01913","last_updated":"2021-03-03T16:41:01Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T11:19:49.325661Z","submitted_at":"2021-03-02T18:13:54Z","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2103.01913."}