{"as_of":"2026-08-13T03:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:75096e425e581b8022a679b01b7473e85c1f11c07757b712e6d1b4373d71ba49","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T23:54:24.047080Z","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":"2026-08-11T14:31:37.347658Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.12652","last_updated":"2025-01-13T21:59:56Z","snapshot_observed_at":"2026-08-13T00:26:16.850953Z","submitted_at":"2024-04-19T06:41:32Z","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.12652","snapshot_observed_at":"2026-08-11T23:54:24.047080Z","title":"Pre- trained vision-language models learn discoverable vi- sual concepts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02104","last_updated":"2024-12-03T02:54:31Z","snapshot_observed_at":"2026-08-12T00:49:07.041510Z","submitted_at":"2024-12-03T02:54:31Z","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","version":1},"reference_index":181,"source":"pdf_text","source_observed_at":"2026-08-11T23:54:24.047080Z"},"links":{"cited_paper":"/paper/2404.12652","citing_paper":"/paper/2412.02104"},"observation_digest":"sha256:967f573080beee6e73fae75481cc27b81f2bdc0e3e496293abbac8a88e7cf335","observation_id":"323b2dae-ef61-4579-b9e3-a62814839ec4","resolution":{"observed_at":"2026-08-11T23:54:24.047080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.12652","last_updated":"2025-01-13T21:59:56Z","snapshot_observed_at":"2026-08-13T00:26:16.850953Z","submitted_at":"2024-04-19T06:41:32Z","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","version":2},"cited_work":{"arxiv_id":"2404.12652","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.12652","snapshot_observed_at":"2026-08-11T14:31:37.347658Z","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","venue":"cs.CV","work_id":"756f029f-ecd4-4025-8949-c300145b9c3f","year":2024},"citing_paper":{"arxiv_id":"2412.11917","last_updated":"2024-12-19T17:57:59Z","snapshot_observed_at":"2026-08-11T22:09:11.510087Z","submitted_at":"2024-12-16T16:01:18Z","title":"Does VLM Classification Benefit from LLM Description Semantics?","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-11T14:31:37.300013Z"},"links":{"cited_paper":"/paper/2404.12652","citing_paper":"/paper/2412.11917"},"observation_digest":"sha256:b9fb7cd6ebbb9dfd09e9a439b04e68fca32cd1dc53831af8e0411e902a435c5f","observation_id":"ee3bc514-de4f-47f6-8c92-17b4ffd9a03c","resolution":{"observed_at":"2026-08-11T14:31:37.354165Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.12652/citation-record","integrity":"/paper/2404.12652/integrity","json":"/paper/2404.12652/citation-record.json","paper":"/paper/2404.12652"},"outbound":[],"paper":{"arxiv_id":"2404.12652","last_updated":"2025-01-13T21:59:56Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T00:26:16.850953Z","submitted_at":"2024-04-19T06:41:32Z","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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:2404.12652."}