{"as_of":"2026-08-19T23:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:95b7d289d64bbc8f1b2f9c891ddf40a0f5436978a2fdca64db7701f15ef63e2a","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":"2026-08-19T06:32:44.657259+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":"2026-08-11T17:10:44.311602Z","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":"2026-05-11T10:31:03.978355Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.09233","last_updated":"2024-07-01T17:48:16Z","snapshot_observed_at":"2026-08-19T22:48:29.871005Z","submitted_at":"2023-07-18T13:10:11Z","title":"Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09233","snapshot_observed_at":"2026-08-11T17:10:44.311602Z","title":"Distilling knowledge from text-to-image generative models improves visio-linguistic reasoning in CLIP","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.09353","last_updated":"2025-04-15T10:14:34Z","snapshot_observed_at":"2026-08-16T18:37:28.389117Z","submitted_at":"2024-12-12T15:22:03Z","title":"Causal Graphical Models for Vision-Language Compositional Understanding","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-11T17:10:44.311602Z"},"links":{"cited_paper":"/paper/2307.09233","citing_paper":"/paper/2412.09353"},"observation_digest":"sha256:ddb26e5fc01c299287acd4328e36cb3f8b47ca4e28f70b4b3cde40ca780e6640","observation_id":"9554776b-1b51-4296-adf9-b7e16ac15cdc","resolution":{"observed_at":"2026-08-11T17:10:44.311602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09233","last_updated":"2024-07-01T17:48:16Z","snapshot_observed_at":"2026-08-19T22:48:29.871005Z","submitted_at":"2023-07-18T13:10:11Z","title":"Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP","version":3},"cited_work":{"arxiv_id":"2307.09233","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2307.09233","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Augmenting clip with improved visio-linguistic reasoning.arXiv preprint arXiv:2307.09233, 2(6):10","venue":null,"work_id":"07dd08bb-29c6-4fc2-b5d9-064e4e71d438","year":2023},"citing_paper":{"arxiv_id":"2604.12335","last_updated":"2026-04-14T06:17:35Z","snapshot_observed_at":"2026-08-11T09:39:12.749021Z","submitted_at":"2026-04-14T06:17:35Z","title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T15:26:55.369840Z"},"links":{"cited_paper":"/paper/2307.09233","citing_paper":"/paper/2604.12335"},"observation_digest":"sha256:8fcb9fd7dab96ffb96e6e043664bceb6ed2b9836cd368a59e77468b414088e15","observation_id":"fdaa8184-a6f5-4419-b94e-48b537c541d6","resolution":{"observed_at":"2026-05-11T10:31:03.988982Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2307.09233/citation-record","integrity":"/paper/2307.09233/integrity","json":"/paper/2307.09233/citation-record.json","paper":"/paper/2307.09233"},"outbound":[],"paper":{"arxiv_id":"2307.09233","last_updated":"2024-07-01T17:48:16Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T22:48:29.871005Z","submitted_at":"2023-07-18T13:10:11Z","title":"Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2307.09233."}