{"as_of":"2026-08-04T20:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a9ab4edc6cba1261c7487112ad1287bbca36f87c1235230e6f6708015166f4b0","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":"2026-08-01T04:30:10.813808Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-10T06:15:00.866473Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.16334","last_updated":"2024-12-20T20:46:48Z","snapshot_observed_at":"2026-08-03T11:55:28.120069Z","submitted_at":"2024-12-20T20:46:48Z","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","version":1},"cited_work":{"arxiv_id":"2412.16334","doi":"10.48550/arxiv.2412.16334","metadata_source":"pith","pith_arxiv_id":"2412.16334","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","venue":"cs.CV","work_id":"829001ff-3641-4fca-94a9-e8da5d64360e","year":2024},"citing_paper":{"arxiv_id":"2607.06305","last_updated":"2026-07-07T14:08:18Z","snapshot_observed_at":"2026-08-03T14:50:25.902308Z","submitted_at":"2026-07-07T14:08:18Z","title":"Exploring Image-Text Alignment for Radio Galaxy Morphologies","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-07-08T10:27:27.065695Z"},"links":{"cited_paper":"/paper/2412.16334","citing_paper":"/paper/2607.06305"},"observation_digest":"sha256:6a25f78e164bb626f47af932c874e26ee42c9c61dafeca6ba820e4a6f62695d4","observation_id":"c4526e6b-98f0-4507-91d9-81bb50fae72a","resolution":{"observed_at":"2026-07-08T10:34:50.511447Z","resolver_source":"local_arxiv","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":"2026-07-10T23:49:07.025883+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-10T23:49:07.025883+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16334","last_updated":"2024-12-20T20:46:48Z","snapshot_observed_at":"2026-08-03T11:55:28.120069Z","submitted_at":"2024-12-20T20:46:48Z","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16334","snapshot_observed_at":"2026-08-01T04:30:10.813808Z","title":"arXiv preprint arXiv:2412.16334 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22531","last_updated":"2026-07-24T17:59:39Z","snapshot_observed_at":"2026-08-01T04:29:41.388158Z","submitted_at":"2026-07-24T17:59:39Z","title":"Twins: Learn to Predict Unified Representations with Focal Loss","version":1},"reference_index":270,"source":"arxiv_source","source_observed_at":"2026-08-01T04:30:10.813808Z"},"links":{"cited_paper":"/paper/2412.16334","citing_paper":"/paper/2607.22531"},"observation_digest":"sha256:36482c5a84391aa148d1e72b21279f74693405e5f860d7ecd61a6abaf46e1ba9","observation_id":"8db6e0e0-3571-4f51-97ae-7d0fb429adbb","resolution":{"observed_at":"2026-08-01T04:30:10.813808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.16334/citation-record","integrity":"/paper/2412.16334/integrity","json":"/paper/2412.16334/citation-record.json","paper":"/paper/2412.16334"},"outbound":[],"paper":{"arxiv_id":"2412.16334","last_updated":"2024-12-20T20:46:48Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T11:55:28.120069Z","submitted_at":"2024-12-20T20:46:48Z","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment"},"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 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2412.16334."}