{"as_of":"2026-08-15T20:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cae3bbe00c12557002eb75e2f0ef5412619e36642e71a4ae6ba706276dec883f","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":"2026-08-15T06:32:42.880941+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":"2026-08-12T16:56:10.890450Z","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":"2026-08-10T17:26:37.174157Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.12808","last_updated":"2024-08-23T03:02:11Z","snapshot_observed_at":"2026-08-13T12:35:01.532030Z","submitted_at":"2024-08-23T03:02:11Z","title":"VALE: A Multimodal Visual and Language Explanation Framework for Image Classifiers using eXplainable AI and Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.12808","snapshot_observed_at":"2026-08-12T16:56:10.890450Z","title":"Vale: A mul- timodal visual and language explanation framework for im- age classifiers using explainable ai and language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13053","last_updated":"2024-11-20T05:57:00Z","snapshot_observed_at":"2026-08-15T05:37:09.605243Z","submitted_at":"2024-11-20T05:57:00Z","title":"MEGL: Multimodal Explanation-Guided Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T16:56:10.890450Z"},"links":{"cited_paper":"/paper/2408.12808","citing_paper":"/paper/2411.13053"},"observation_digest":"sha256:74c934acf7d47dbb3a2a242a80a3c132478eb99d0d0017275eef77793f5f9caf","observation_id":"c352a93d-f575-4683-8bf0-48133222af74","resolution":{"observed_at":"2026-08-12T16:56:10.890450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12808","last_updated":"2024-08-23T03:02:11Z","snapshot_observed_at":"2026-08-13T12:35:01.532030Z","submitted_at":"2024-08-23T03:02:11Z","title":"VALE: A Multimodal Visual and Language Explanation Framework for Image Classifiers using eXplainable AI and Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.12808","snapshot_observed_at":"2026-08-11T23:54:23.985817Z","title":"Vale: A multimodal visual and language explanation framework for image classifiers using explainable ai and language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02104","last_updated":"2024-12-03T02:54:31Z","snapshot_observed_at":"2026-08-13T18:59:32.206758Z","submitted_at":"2024-12-03T02:54:31Z","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","version":1},"reference_index":170,"source":"pdf_text","source_observed_at":"2026-08-11T23:54:23.985817Z"},"links":{"cited_paper":"/paper/2408.12808","citing_paper":"/paper/2412.02104"},"observation_digest":"sha256:8b168c025d2f075f88747e5188ad8d8943c357004a0bae5961fc306a6be2888b","observation_id":"7d433d4c-69ab-4399-8c65-536b1f3b50ed","resolution":{"observed_at":"2026-08-11T23:54:23.985817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12808","last_updated":"2024-08-23T03:02:11Z","snapshot_observed_at":"2026-08-13T12:35:01.532030Z","submitted_at":"2024-08-23T03:02:11Z","title":"VALE: A Multimodal Visual and Language Explanation Framework for Image Classifiers using eXplainable AI and Language Models","version":1},"cited_work":{"arxiv_id":"2408.12808","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.12808","snapshot_observed_at":"2026-08-10T17:26:37.174157Z","title":"VALE: A Multimodal Visual and Language Explanation Framework for Image Classifiers using eXplainable AI and Language Models","venue":"cs.CV","work_id":"6a68a937-265b-4367-92da-82faf176bf6e","year":2024},"citing_paper":{"arxiv_id":"2501.12203","last_updated":"2025-01-21T15:18:55Z","snapshot_observed_at":"2026-08-15T03:05:08.572691Z","submitted_at":"2025-01-21T15:18:55Z","title":"Explainability for Vision Foundation Models: A Survey","version":1},"reference_index":137,"source":"pdf_text","source_observed_at":"2026-08-10T17:26:35.495822Z"},"links":{"cited_paper":"/paper/2408.12808","citing_paper":"/paper/2501.12203"},"observation_digest":"sha256:b0fd3de3eca0a10c92544156373caf44369eaf15cf633a535de7c4cef53fd97d","observation_id":"e76e3ac4-4e40-439e-aed3-2676d3481ee4","resolution":{"observed_at":"2026-08-10T17:26:37.178614Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2408.12808/citation-record","integrity":"/paper/2408.12808/integrity","json":"/paper/2408.12808/citation-record.json","paper":"/paper/2408.12808"},"outbound":[],"paper":{"arxiv_id":"2408.12808","last_updated":"2024-08-23T03:02:11Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T12:35:01.532030Z","submitted_at":"2024-08-23T03:02:11Z","title":"VALE: A Multimodal Visual and Language Explanation Framework for Image Classifiers using eXplainable AI and Language Models"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2408.12808."}