{"as_of":"2026-08-14T22:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0ae97f1ce1c63f9b319f0fa22542d0b4ed3f68750e3aca9712412eade2469da3","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T13:07:21.427660Z","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":"2026-08-14T11:10:43.185867Z","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:ac16c4218cd79b3f3cbfaddfdf079bf298f6c0be76a993939fc25eef41518b66","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 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.05107","last_updated":"2020-11-24T22:13:21Z","snapshot_observed_at":"2026-08-14T11:10:43.185867Z","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":"2026-08-11T13:07:21.427660Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13510","last_updated":"2024-12-18T05:19:09Z","snapshot_observed_at":"2026-08-12T09:57:58.122520Z","submitted_at":"2024-12-18T05:19:09Z","title":"Dynamic Adapter with Semantics Disentangling for Cross-lingual Cross-modal Retrieval","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T13:07:21.427660Z"},"links":{"cited_paper":"/paper/2012.05107","citing_paper":"/paper/2412.13510"},"observation_digest":"sha256:21e063cb99fbc9c5a640d3190bef2463e15e57e7f3061396cc1520a4eb11f1ad","observation_id":"0546c2b5-77ad-4226-9803-9a5c80394f5d","resolution":{"observed_at":"2026-08-11T13:07:21.427660Z","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":"2026-08-14T11:10:43.185867Z","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":"2026-08-10T12:44:14.015550Z","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":"sha256:3342a9c7a6ae53335a3aa1b54ee53864055d2303499bb9c0199808cc5def0c8c","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":"2026-08-14T11:10:43.185867Z","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:e503212f87302e9c97ca4fa70b686fbfbd22eeb5334099e7ae0f6d9fa966f4a8","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 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-14T11:10:43.185867Z","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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2012.05107."}