{"as_of":"2026-08-08T15:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e2f9cb11dda02d960e82d18811caa112c446765c21e51d25df36d51c19bf1db8","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":"2026-08-08T06:32:00.761636+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":"2026-08-08T12:12:30.652561Z","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":"2026-08-06T22:36:50.760616Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.05095","last_updated":"2023-05-08T23:47:07Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T23:47:07Z","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05095","snapshot_observed_at":"2026-08-08T12:12:30.652561Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.07617","last_updated":"2026-05-31T18:45:03Z","snapshot_observed_at":"2026-08-08T12:06:14.483667Z","submitted_at":"2025-02-11T15:05:33Z","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T12:12:30.652561Z"},"links":{"cited_paper":"/paper/2305.05095","citing_paper":"/paper/2502.07617"},"observation_digest":"sha256:1a37675697a818b174f11dc85663b02fc77522c0b93cbe57c6009062fe04eed8","observation_id":"d87dc198-a1f3-4a3c-a618-787ce9507f85","resolution":{"observed_at":"2026-08-08T12:12:30.652561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05095","last_updated":"2023-05-08T23:47:07Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T23:47:07Z","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","version":1},"cited_work":{"arxiv_id":"2305.05095","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.05095","snapshot_observed_at":"2026-08-06T22:36:50.760616Z","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","venue":"cs.CV","work_id":"24b55893-7a0d-4deb-b0c5-29d814aee752","year":2023},"citing_paper":{"arxiv_id":"2506.21233","last_updated":"2025-06-27T12:06:27Z","snapshot_observed_at":"2026-08-07T23:38:02.795569Z","submitted_at":"2025-06-26T13:22:03Z","title":"ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:42.353046Z"},"links":{"cited_paper":"/paper/2305.05095","citing_paper":"/paper/2506.21233"},"observation_digest":"sha256:c43b32c757c46978ce3205730e4105f9e9d0850649f86879e76d8b62eb86a8ee","observation_id":"94387481-f722-4ff7-b6d5-4a4d5bacff81","resolution":{"observed_at":"2026-08-06T22:36:50.840513Z","resolver_source":"local_arxiv","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/2305.05095/citation-record","integrity":"/paper/2305.05095/integrity","json":"/paper/2305.05095/citation-record.json","paper":"/paper/2305.05095"},"outbound":[],"paper":{"arxiv_id":"2305.05095","last_updated":"2023-05-08T23:47:07Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T23:47:07Z","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness"},"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 2 inbound Pith citation observations for arXiv:2305.05095."}