{"as_of":"2026-08-09T22:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d3b381161cbc8e89d9e474febc9450832278667e8f4fc239f1c9aaab61c005b0","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":"2026-08-09T06:31:02.800959+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":"2026-08-05T14:59:19.556141Z","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":"2026-07-08T16:45:07.684747Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.12956","last_updated":"2023-08-24T17:50:21Z","snapshot_observed_at":"2026-08-08T09:10:54.543652Z","submitted_at":"2023-08-24T17:50:21Z","title":"DLIP: Distilling Language-Image Pre-training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12956","snapshot_observed_at":"2026-08-05T14:59:19.556141Z","title":"Dlip: Distilling language-image pre-training.arXiv preprint arXiv:2308.12956 ,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.20691","last_updated":"2025-08-28T11:50:22Z","snapshot_observed_at":"2026-08-06T13:33:55.665527Z","submitted_at":"2025-08-28T11:50:22Z","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-05T14:59:19.556141Z"},"links":{"cited_paper":"/paper/2308.12956","citing_paper":"/paper/2508.20691"},"observation_digest":"sha256:2ff3fb1104b1d8a0a54af50a50fc568bea43261ee9d14dd0bcfbe3359271ccee","observation_id":"4db68fbb-6f5d-4286-a80e-ee3e8ea8dc23","resolution":{"observed_at":"2026-08-05T14:59:19.556141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12956","last_updated":"2023-08-24T17:50:21Z","snapshot_observed_at":"2026-08-08T09:10:54.543652Z","submitted_at":"2023-08-24T17:50:21Z","title":"DLIP: Distilling Language-Image Pre-training","version":1},"cited_work":{"arxiv_id":"2308.12956","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.12956","snapshot_observed_at":"2026-07-08T16:45:07.684747Z","title":"DLIP: Distilling Language-Image Pre-training","venue":"cs.CV","work_id":"24bda0fc-55c4-4ab6-bbc2-a34614894606","year":2023},"citing_paper":{"arxiv_id":"2607.06097","last_updated":"2026-07-07T10:11:35Z","snapshot_observed_at":"2026-08-09T21:18:57.864840Z","submitted_at":"2026-07-07T10:11:35Z","title":"PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-08T16:39:53.448383Z"},"links":{"cited_paper":"/paper/2308.12956","citing_paper":"/paper/2607.06097"},"observation_digest":"sha256:8956ba1a03f88578880cd2089babcbe41377935fa5345c5519fa577d9f85eda3","observation_id":"dc1c7fd1-f2a1-42b7-8d6c-70c35142d45f","resolution":{"observed_at":"2026-07-08T16:45:07.686511Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2308.12956/citation-record","integrity":"/paper/2308.12956/integrity","json":"/paper/2308.12956/citation-record.json","paper":"/paper/2308.12956"},"outbound":[],"paper":{"arxiv_id":"2308.12956","last_updated":"2023-08-24T17:50:21Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T09:10:54.543652Z","submitted_at":"2023-08-24T17:50:21Z","title":"DLIP: Distilling Language-Image Pre-training"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2308.12956."}