{"as_of":"2026-08-09T20:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4d2eaf1914e0c0c96b015ca4634921dceb2601c956b33ab071c103a3466f43f3","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T23:35:38.610935Z","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":"2026-05-24T00:53:40.718702Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.11281","last_updated":"2024-06-20T13:12:31Z","snapshot_observed_at":"2026-08-09T17:22:17.388997Z","submitted_at":"2024-02-17T13:41:44Z","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?","version":3},"cited_work":{"arxiv_id":"2402.11281","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11281","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Can large multimodal models uncover deep semantics behind images?","venue":null,"work_id":"ca52148d-2a34-402f-b5dd-3b12d9fa81d5","year":2024},"citing_paper":{"arxiv_id":"2405.19088","last_updated":"2026-04-15T02:26:56Z","snapshot_observed_at":"2026-07-06T18:21:57.091728Z","submitted_at":"2024-05-29T13:51:43Z","title":"Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-24T00:52:52.056076Z"},"links":{"cited_paper":"/paper/2402.11281","citing_paper":"/paper/2405.19088"},"observation_digest":"sha256:7717ce9a65bcdb2878a83fa0445d52bb00747537edd3796f276e1bee2a31b66c","observation_id":"df69a80c-c94d-42ca-9c0d-87e466adcd12","resolution":{"observed_at":"2026-05-24T00:53:40.722581Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11281","last_updated":"2024-06-20T13:12:31Z","snapshot_observed_at":"2026-08-09T17:22:17.388997Z","submitted_at":"2024-02-17T13:41:44Z","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11281","snapshot_observed_at":"2026-08-08T23:35:38.610935Z","title":"Can large multimodal models uncover deep semantics behind images? arXiv preprint arXiv:2402.11281, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04095","last_updated":"2025-02-06T14:12:41Z","snapshot_observed_at":"2026-08-09T16:10:32.021940Z","submitted_at":"2025-02-06T14:12:41Z","title":"LLMs to Support a Domain Specific Knowledge Assistant","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-08T23:35:38.610935Z"},"links":{"cited_paper":"/paper/2402.11281","citing_paper":"/paper/2502.04095"},"observation_digest":"sha256:7a2b1da070b4bbd79b45e3c73bcab69b0d43aeeba55bf4b07f785d25d8da71b0","observation_id":"3cf1532e-7d1b-4d3a-b9ff-a5458a788fed","resolution":{"observed_at":"2026-08-08T23:35:38.610935Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11281","last_updated":"2024-06-20T13:12:31Z","snapshot_observed_at":"2026-08-09T17:22:17.388997Z","submitted_at":"2024-02-17T13:41:44Z","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?","version":3},"cited_work":{"arxiv_id":"2402.11281","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11281","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Can large multimodal models uncover deep semantics behind images?","venue":null,"work_id":"ca52148d-2a34-402f-b5dd-3b12d9fa81d5","year":2024},"citing_paper":{"arxiv_id":"2503.23137","last_updated":"2026-04-15T02:38:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-29T16:08:51Z","title":"When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-22T22:38:35.969273Z"},"links":{"cited_paper":"/paper/2402.11281","citing_paper":"/paper/2503.23137"},"observation_digest":"sha256:9a52c087ab237388978f72964027aa83a8c6e133aa25855d0ec1532cecd7ca3d","observation_id":"40398bae-2e11-45a4-84c2-5920e627be29","resolution":{"observed_at":"2026-05-22T22:42:13.538234Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.11281/citation-record","integrity":"/paper/2402.11281/integrity","json":"/paper/2402.11281/citation-record.json","paper":"/paper/2402.11281"},"outbound":[],"paper":{"arxiv_id":"2402.11281","last_updated":"2024-06-20T13:12:31Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T17:22:17.388997Z","submitted_at":"2024-02-17T13:41:44Z","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.11281."}