{"as_of":"2026-08-04T11:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2ec6c52b6a215aa2521f198aec8529f35f84982e0d6b2867a4942405fac8b8bd","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":"2026-08-04T06:34:03.388597+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":"2026-08-01T21:12:04.844747Z","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":"2026-07-02T02:16:26.476658Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.07204","last_updated":"2024-04-10T17:59:45Z","snapshot_observed_at":"2026-07-06T17:58:25.894552Z","submitted_at":"2024-04-10T17:59:45Z","title":"BRAVE: Broadening the visual encoding of vision-language models","version":1},"cited_work":{"arxiv_id":"2404.07204","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07204","snapshot_observed_at":"2026-07-02T02:16:26.476658Z","title":"BRA VE: Broadening the visual encoding of vision-language models","venue":null,"work_id":"74cb7089-8df1-45a0-aedf-316dfd66318c","year":2024},"citing_paper":{"arxiv_id":"2412.03555","last_updated":"2024-12-04T18:50:42Z","snapshot_observed_at":"2026-07-06T20:01:45.826971Z","submitted_at":"2024-12-04T18:50:42Z","title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-15T09:15:07.523565Z"},"links":{"cited_paper":"/paper/2404.07204","citing_paper":"/paper/2412.03555"},"observation_digest":"sha256:8db1cb0d344889d4eabe86c8fd126ae898d72bfbf600f6c2f42053c1de4dab95","observation_id":"793f627f-7938-45aa-9020-81c0af7cad9f","resolution":{"observed_at":"2026-05-15T09:15:07.598735Z","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":"2404.07204","last_updated":"2024-04-10T17:59:45Z","snapshot_observed_at":"2026-07-06T17:58:25.894552Z","submitted_at":"2024-04-10T17:59:45Z","title":"BRAVE: Broadening the visual encoding of vision-language models","version":1},"cited_work":{"arxiv_id":"2404.07204","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07204","snapshot_observed_at":"2026-07-02T02:16:26.476658Z","title":"BRA VE: Broadening the visual encoding of vision-language models","venue":null,"work_id":"74cb7089-8df1-45a0-aedf-316dfd66318c","year":2024},"citing_paper":{"arxiv_id":"2606.03879","last_updated":"2026-06-02T16:46:42Z","snapshot_observed_at":"2026-07-06T23:44:05.167767Z","submitted_at":"2026-06-02T16:46:42Z","title":"Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T11:08:36.451147Z"},"links":{"cited_paper":"/paper/2404.07204","citing_paper":"/paper/2606.03879"},"observation_digest":"sha256:d0a7459f439d232d46f4fed665333b4a0dadff473fd3b0723cf8a572f4ec8e92","observation_id":"bd6221a3-afeb-45c4-8f76-2b12957543ce","resolution":{"observed_at":"2026-07-02T02:16:26.478330Z","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":"2404.07204","last_updated":"2024-04-10T17:59:45Z","snapshot_observed_at":"2026-07-06T17:58:25.894552Z","submitted_at":"2024-04-10T17:59:45Z","title":"BRAVE: Broadening the visual encoding of vision-language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07204","snapshot_observed_at":"2026-08-01T21:12:04.844747Z","title":"BRAVE: Broadening the visual encoding of vision-language models.arXiv preprint arXiv:2404.07204, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16165","last_updated":"2026-07-17T17:46:23Z","snapshot_observed_at":"2026-08-03T09:32:27.223381Z","submitted_at":"2026-07-17T17:46:23Z","title":"An Exam for Active Observers","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T21:12:04.844747Z"},"links":{"cited_paper":"/paper/2404.07204","citing_paper":"/paper/2607.16165"},"observation_digest":"sha256:d34ea77b86ee848c6672a68a47b3fc26eaf814a93d305e4e1f9fe7ac7b6b2a83","observation_id":"e4c19394-d85b-40ee-be29-e51c05c7d730","resolution":{"observed_at":"2026-08-01T21:12:04.844747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2404.07204/citation-record","integrity":"/paper/2404.07204/integrity","json":"/paper/2404.07204/citation-record.json","paper":"/paper/2404.07204"},"outbound":[],"paper":{"arxiv_id":"2404.07204","last_updated":"2024-04-10T17:59:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:58:25.894552Z","submitted_at":"2024-04-10T17:59:45Z","title":"BRAVE: Broadening the visual encoding of vision-language models"},"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 3 inbound Pith citation observations for arXiv:2404.07204."}