{"as_of":"2026-08-09T05:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:90bc8c34b77158bcd9b04e792e3f4a0a196be24ea1618fd88ebe638d60b9ab21","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T05:21:35.075784Z","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":"2026-07-04T13:39:50.766648Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.05210","last_updated":"2024-10-07T17:16:20Z","snapshot_observed_at":"2026-07-06T19:29:09.714725Z","submitted_at":"2024-10-07T17:16:20Z","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05210","snapshot_observed_at":"2026-08-07T05:21:35.075784Z","title":"Preserving multi-modal capabilities of pre- trained vlms for improving vision-linguistic compositional- ity.arXiv preprint arXiv:2410.05210, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08227","last_updated":"2025-06-09T20:53:43Z","snapshot_observed_at":"2026-08-07T05:14:41.333172Z","submitted_at":"2025-06-09T20:53:43Z","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:35.075784Z"},"links":{"cited_paper":"/paper/2410.05210","citing_paper":"/paper/2506.08227"},"observation_digest":"sha256:042614fb786d7ba973dc540af79ac1c4fd705b5c0a9c38a5b4fcddab1828ad4d","observation_id":"75edd83d-e0b1-49ea-a639-88d5cbf2042a","resolution":{"observed_at":"2026-08-07T05:21:35.075784Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05210","last_updated":"2024-10-07T17:16:20Z","snapshot_observed_at":"2026-07-06T19:29:09.714725Z","submitted_at":"2024-10-07T17:16:20Z","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","version":1},"cited_work":{"arxiv_id":"2410.05210","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.05210","snapshot_observed_at":"2026-07-04T13:39:50.766648Z","title":"arXiv preprint arXiv:2410.05210 (2024)","venue":null,"work_id":"63e54452-0246-4258-a6d0-c32a5f3b4ecd","year":2024},"citing_paper":{"arxiv_id":"2606.13288","last_updated":"2026-06-11T12:45:25Z","snapshot_observed_at":"2026-07-06T23:52:04.574604Z","submitted_at":"2026-06-11T12:45:25Z","title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-06-27T07:03:50.311891Z"},"links":{"cited_paper":"/paper/2410.05210","citing_paper":"/paper/2606.13288"},"observation_digest":"sha256:a819f5374e5711141a64a00f6735990550dff2dbb02f47165b9cc748bef006a3","observation_id":"a3a9d948-5ee5-43b8-b7f5-8373b14c58c1","resolution":{"observed_at":"2026-07-03T14:28:31.479611Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05210","last_updated":"2024-10-07T17:16:20Z","snapshot_observed_at":"2026-07-06T19:29:09.714725Z","submitted_at":"2024-10-07T17:16:20Z","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","version":1},"cited_work":{"arxiv_id":"2410.05210","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.05210","snapshot_observed_at":"2026-07-04T13:39:50.766648Z","title":"arXiv preprint arXiv:2410.05210 (2024)","venue":null,"work_id":"63e54452-0246-4258-a6d0-c32a5f3b4ecd","year":2024},"citing_paper":{"arxiv_id":"2606.26794","last_updated":"2026-06-25T09:27:54Z","snapshot_observed_at":"2026-08-03T16:40:37.506200Z","submitted_at":"2026-06-25T09:27:54Z","title":"ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-06-26T05:03:15.044146Z"},"links":{"cited_paper":"/paper/2410.05210","citing_paper":"/paper/2606.26794"},"observation_digest":"sha256:32fe8ec9f97b90963f2013e690ae59d6bb0e7d97248f1cbf854b24412e037c6e","observation_id":"602388bf-c0f6-4cfd-92fc-7bcac1f2d99d","resolution":{"observed_at":"2026-07-04T13:39:50.768106Z","resolver_source":"arxiv_id","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/2410.05210/citation-record","integrity":"/paper/2410.05210/integrity","json":"/paper/2410.05210/citation-record.json","paper":"/paper/2410.05210"},"outbound":[],"paper":{"arxiv_id":"2410.05210","last_updated":"2024-10-07T17:16:20Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:29:09.714725Z","submitted_at":"2024-10-07T17:16:20Z","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2410.05210."}