{"as_of":"2026-08-07T19:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dac4b43133bd2f2ff77949b2773ac509aeb473118c7aad79059a02596e903280","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T05:47:29.878452Z","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":"2026-05-12T09:06:25.019701Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.08173","last_updated":"2024-03-01T04:24:04Z","snapshot_observed_at":"2026-07-06T15:42:18.360486Z","submitted_at":"2023-06-13T23:32:09Z","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08173","snapshot_observed_at":"2026-08-07T05:47:29.878452Z","title":"Safeguard- ing data in multimodal ai: A differentially private approach to clip training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-07T10:37:00.894480Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.878452Z"},"links":{"cited_paper":"/paper/2306.08173","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:24d4000d2818013890275b7a2542fe1bf591d9b09c9dddcb2da3b86002b6b19e","observation_id":"fb32c6a1-87e3-443c-9f3f-38ba4225d358","resolution":{"observed_at":"2026-08-07T05:47:29.878452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08173","last_updated":"2024-03-01T04:24:04Z","snapshot_observed_at":"2026-07-06T15:42:18.360486Z","submitted_at":"2023-06-13T23:32:09Z","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","version":2},"cited_work":{"arxiv_id":"2306.08173","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.08173","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"1065a798-8b75-4898-843b-29161b830c20","year":2023},"citing_paper":{"arxiv_id":"2604.26467","last_updated":"2026-04-29T09:25:06Z","snapshot_observed_at":"2026-07-06T23:12:06.349884Z","submitted_at":"2026-04-29T09:25:06Z","title":"Differentially Private Contrastive Learning via Bounding Group-level Contribution","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-07T13:07:53.564066Z"},"links":{"cited_paper":"/paper/2306.08173","citing_paper":"/paper/2604.26467"},"observation_digest":"sha256:9a5f9eed8a1a4e5026963fedc03551d8231d803cfd58602aad2e323fa548b6fc","observation_id":"7dcb34c0-0ea8-4308-84d6-2953d6c19da1","resolution":{"observed_at":"2026-05-12T09:06:25.022537Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08173","last_updated":"2024-03-01T04:24:04Z","snapshot_observed_at":"2026-07-06T15:42:18.360486Z","submitted_at":"2023-06-13T23:32:09Z","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08173","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2306.08173 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2306.08173","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:5fafef0e4b85ed25e6b68b126f0b82005810ea6b1aba45694256420847e69387","observation_id":"731366d6-6860-4b75-89b7-9713c0cc022b","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2306.08173/citation-record","integrity":"/paper/2306.08173/integrity","json":"/paper/2306.08173/citation-record.json","paper":"/paper/2306.08173"},"outbound":[],"paper":{"arxiv_id":"2306.08173","last_updated":"2024-03-01T04:24:04Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T15:42:18.360486Z","submitted_at":"2023-06-13T23:32:09Z","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2306.08173."}