{"as_of":"2026-08-13T21:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1602c5f160a6524c9af5bfaad34615baefe17cab717b7b88073b2a1cf0fe581c","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":"2026-08-13T06:32:02.005865+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":"2026-08-09T15:36:27.456453Z","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":"2026-08-09T00:50:01.713055Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.03323","last_updated":"2023-07-17T06:03:16Z","snapshot_observed_at":"2026-08-13T12:30:32.631108Z","submitted_at":"2023-03-06T17:48:32Z","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.03323","snapshot_observed_at":"2026-08-09T15:36:27.456453Z","title":"Cleanclip: Mitigating data poisoning attacks in multimodal contrastive learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01385","last_updated":"2025-02-10T08:04:21Z","snapshot_observed_at":"2026-08-11T03:08:08.478754Z","submitted_at":"2025-02-03T14:21:05Z","title":"Detecting Backdoor Samples in Contrastive Language Image Pretraining","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T15:36:27.456453Z"},"links":{"cited_paper":"/paper/2303.03323","citing_paper":"/paper/2502.01385"},"observation_digest":"sha256:51e452dd9bd00cd57f6b9a5ca6f49dd656c40898468ef82c98345f501b675a0f","observation_id":"c77f19a6-172c-434c-9287-e3dca119694a","resolution":{"observed_at":"2026-08-09T15:36:27.456453Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.03323","last_updated":"2023-07-17T06:03:16Z","snapshot_observed_at":"2026-08-13T12:30:32.631108Z","submitted_at":"2023-03-06T17:48:32Z","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","version":3},"cited_work":{"arxiv_id":"2303.03323","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.03323","snapshot_observed_at":"2026-08-09T00:50:01.713055Z","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","venue":"cs.CV","work_id":"cec3f850-84b1-4f5f-a77f-0987c8f659b2","year":2023},"citing_paper":{"arxiv_id":"2502.05224","last_updated":"2025-02-06T04:43:05Z","snapshot_observed_at":"2026-08-13T00:35:04.918294Z","submitted_at":"2025-02-06T04:43:05Z","title":"A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations","version":1},"reference_index":187,"source":"pdf_text","source_observed_at":"2026-08-09T00:50:00.809761Z"},"links":{"cited_paper":"/paper/2303.03323","citing_paper":"/paper/2502.05224"},"observation_digest":"sha256:0127e03b8bc4409ffebfb0006d96cd8dcfd7dda668aae587d717265f31e23c2d","observation_id":"219d7f8a-5ca4-4346-9bf9-2186660cc034","resolution":{"observed_at":"2026-08-09T00:50:01.718005Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2303.03323/citation-record","integrity":"/paper/2303.03323/integrity","json":"/paper/2303.03323/citation-record.json","paper":"/paper/2303.03323"},"outbound":[],"paper":{"arxiv_id":"2303.03323","last_updated":"2023-07-17T06:03:16Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T12:30:32.631108Z","submitted_at":"2023-03-06T17:48:32Z","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2303.03323."}