{"as_of":"2026-08-08T16:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:53b376ed07955f30dfa086a84b45108a2b3399134f857e9156f4a7146a007064","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T12:08:21.963849Z","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":"2026-05-18T13:02:37.452099Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2012.05107","last_updated":"2020-11-24T22:13:21Z","snapshot_observed_at":"2026-08-08T14:16:35.675685Z","submitted_at":"2020-11-24T22:13:21Z","title":"Towards Zero-shot Cross-lingual Image Retrieval","version":1},"cited_work":{"arxiv_id":"2012.05107","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2012.05107","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards zero- shot cross-lingual image retrieval","venue":null,"work_id":"dceda28c-2ba0-4fd3-b121-ead8d5f338ab","year":2020},"citing_paper":{"arxiv_id":"2312.14238","last_updated":"2024-01-15T15:23:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-21T18:59:31Z","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-13T22:46:09.693156Z"},"links":{"cited_paper":"/paper/2012.05107","citing_paper":"/paper/2312.14238"},"observation_digest":"sha256:4a9eaac2640c1dd8a4659d3f453530d8e0f2a7824f7c70039cc05be1a599d42b","observation_id":"e0431afd-2a13-4136-b6d4-c98f0eaf5486","resolution":{"observed_at":"2026-05-13T22:46:09.768595Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.05107","last_updated":"2020-11-24T22:13:21Z","snapshot_observed_at":"2026-08-08T14:16:35.675685Z","submitted_at":"2020-11-24T22:13:21Z","title":"Towards Zero-shot Cross-lingual Image Retrieval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.05107","snapshot_observed_at":"2026-08-06T12:08:21.963849Z","title":"Towards zero-shot cross-lingual image retrieval.arXiv preprint arXiv:2012.05107 ,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.22062","last_updated":"2025-08-01T06:40:13Z","snapshot_observed_at":"2026-08-06T12:08:20.848892Z","submitted_at":"2025-07-29T17:59:58Z","title":"Meta CLIP 2: A Worldwide Scaling Recipe","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T12:08:21.963849Z"},"links":{"cited_paper":"/paper/2012.05107","citing_paper":"/paper/2507.22062"},"observation_digest":"sha256:7bdd92f83afa4e6e64606d8c09d96f060e6bd51f33bede9031659b27a73a699b","observation_id":"1d034e13-e2da-40ca-b488-e82fea865f11","resolution":{"observed_at":"2026-08-06T12:08:21.963849Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.05107","last_updated":"2020-11-24T22:13:21Z","snapshot_observed_at":"2026-08-08T14:16:35.675685Z","submitted_at":"2020-11-24T22:13:21Z","title":"Towards Zero-shot Cross-lingual Image Retrieval","version":1},"cited_work":{"arxiv_id":"2012.05107","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2012.05107","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards zero- shot cross-lingual image retrieval","venue":null,"work_id":"dceda28c-2ba0-4fd3-b121-ead8d5f338ab","year":2020},"citing_paper":{"arxiv_id":"2509.22123","last_updated":"2026-05-13T12:28:55Z","snapshot_observed_at":"2026-08-08T13:18:54.000166Z","submitted_at":"2025-09-26T09:46:13Z","title":"Multilingual Vision-Language Models, A Survey","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-18T13:02:08.000814Z"},"links":{"cited_paper":"/paper/2012.05107","citing_paper":"/paper/2509.22123"},"observation_digest":"sha256:aabac20dc4670e0578fa6e3a5c072217c80437ca4511c6b8e89deefdd0835a7d","observation_id":"26ebb691-4066-4788-ad32-f2b6f622fcbe","resolution":{"observed_at":"2026-05-18T13:02:37.455608Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2012.05107/citation-record","integrity":"/paper/2012.05107/integrity","json":"/paper/2012.05107/citation-record.json","paper":"/paper/2012.05107"},"outbound":[],"paper":{"arxiv_id":"2012.05107","last_updated":"2020-11-24T22:13:21Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-08T14:16:35.675685Z","submitted_at":"2020-11-24T22:13:21Z","title":"Towards Zero-shot Cross-lingual Image Retrieval"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2012.05107."}