{"as_of":"2026-08-09T16:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f516aa778fd8ed58374a875d59125df5175fa36679f19eef5258b7b53326c1a0","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T18:32:29.261710Z","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":"2026-05-20T06:48:05.759954Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.16670","last_updated":"2024-04-25T15:15:36Z","snapshot_observed_at":"2026-08-09T13:14:13.143793Z","submitted_at":"2024-04-25T15:15:36Z","title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16670","snapshot_observed_at":"2026-08-08T18:32:29.261710Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05660","last_updated":"2025-02-08T18:25:31Z","snapshot_observed_at":"2026-08-08T18:25:20.194040Z","submitted_at":"2025-02-08T18:25:31Z","title":"Evaluating Vision-Language Models for Emotion Recognition","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-08T18:32:29.261710Z"},"links":{"cited_paper":"/paper/2404.16670","citing_paper":"/paper/2502.05660"},"observation_digest":"sha256:c2209d6eb887b7e69c44800cf3e9577bd3ff2d350898c4161a22c82d47516bf1","observation_id":"724d50ea-479d-4ab7-9713-0f735e415806","resolution":{"observed_at":"2026-08-08T18:32:29.261710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16670","last_updated":"2024-04-25T15:15:36Z","snapshot_observed_at":"2026-08-09T13:14:13.143793Z","submitted_at":"2024-04-25T15:15:36Z","title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","version":1},"cited_work":{"arxiv_id":"2404.16670","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.16670","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"EmoVIT: Multimodal emotion understanding with vision instruction tuning","venue":null,"work_id":"1c3504e9-5afe-4a5c-bb12-14de42ebc701","year":2024},"citing_paper":{"arxiv_id":"2605.19950","last_updated":"2026-05-19T15:05:00Z","snapshot_observed_at":"2026-07-06T23:30:35.042915Z","submitted_at":"2026-05-19T15:05:00Z","title":"AffectVerse: Emotional World Models for Multimodal Affective Computing","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-20T06:46:33.612905Z"},"links":{"cited_paper":"/paper/2404.16670","citing_paper":"/paper/2605.19950"},"observation_digest":"sha256:094b5b4d1582a8ec284fd1e24dc4efa6375c01640af2e965b38c1a11ddad572b","observation_id":"111afc69-4f54-4501-8e08-e42cc03b7ee7","resolution":{"observed_at":"2026-05-20T06:48:05.761960Z","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/2404.16670/citation-record","integrity":"/paper/2404.16670/integrity","json":"/paper/2404.16670/citation-record.json","paper":"/paper/2404.16670"},"outbound":[],"paper":{"arxiv_id":"2404.16670","last_updated":"2024-04-25T15:15:36Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T13:14:13.143793Z","submitted_at":"2024-04-25T15:15:36Z","title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning"},"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 2 inbound Pith citation observations for arXiv:2404.16670."}