{"as_of":"2026-08-13T20:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:914347389d1e8d41d912f40350f04e61f66dfe82dd61066bc0b71b9301826f66","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T18:32:29.153457Z","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":"2026-05-11T23:26:13.762088Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.08992","last_updated":"2025-01-31T18:53:30Z","snapshot_observed_at":"2026-08-13T00:07:36.788733Z","submitted_at":"2024-05-14T23:24:12Z","title":"Contextual Emotion Recognition using Large Vision Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08992","snapshot_observed_at":"2026-08-08T18:32:29.153457Z","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":"2026-08-10T20:12:25.614328Z","submitted_at":"2025-02-08T18:25:31Z","title":"Evaluating Vision-Language Models for Emotion Recognition","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-08T18:32:29.153457Z"},"links":{"cited_paper":"/paper/2405.08992","citing_paper":"/paper/2502.05660"},"observation_digest":"sha256:83f1b1b377b4aa866f08653b01792aa776aadaea792fdf496a581a0d557b3862","observation_id":"ed3fbeb9-8a5a-428e-999b-2249ff765c03","resolution":{"observed_at":"2026-08-08T18:32:29.153457Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08992","last_updated":"2025-01-31T18:53:30Z","snapshot_observed_at":"2026-08-13T00:07:36.788733Z","submitted_at":"2024-05-14T23:24:12Z","title":"Contextual Emotion Recognition using Large Vision Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08992","snapshot_observed_at":"2026-08-07T12:27:27.873897Z","title":"Contextual emotion recognition using large vision language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24493","last_updated":"2025-05-30T11:45:36Z","snapshot_observed_at":"2026-08-12T05:00:36.919285Z","submitted_at":"2025-05-30T11:45:36Z","title":"MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:27:27.873897Z"},"links":{"cited_paper":"/paper/2405.08992","citing_paper":"/paper/2505.24493"},"observation_digest":"sha256:319b7a1e8d9cddcf8b15d44a06fb40ab1caa1d8a03a7e5ab742047c344dd932f","observation_id":"feafe0e5-f059-4a73-84ab-a7cc6783b03b","resolution":{"observed_at":"2026-08-07T12:27:27.873897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08992","last_updated":"2025-01-31T18:53:30Z","snapshot_observed_at":"2026-08-13T00:07:36.788733Z","submitted_at":"2024-05-14T23:24:12Z","title":"Contextual Emotion Recognition using Large Vision Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08992","snapshot_observed_at":"2026-08-05T11:57:55.297380Z","title":"Contextual emotion recognition using large vision language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.02100","last_updated":"2025-09-08T08:37:27Z","snapshot_observed_at":"2026-08-10T21:35:05.056428Z","submitted_at":"2025-09-02T08:58:32Z","title":"E-THER: A Multimodal Dataset for Empathic AI -- Towards Emotional Mismatch Awareness","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T11:57:55.297380Z"},"links":{"cited_paper":"/paper/2405.08992","citing_paper":"/paper/2509.02100"},"observation_digest":"sha256:5f0c3f032ce65ce440b5e6e05518cef20dbacb9b1307b65da721ba40df020f10","observation_id":"72753f3e-ff0e-498a-aee2-97539264bec1","resolution":{"observed_at":"2026-08-05T11:57:55.297380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08992","last_updated":"2025-01-31T18:53:30Z","snapshot_observed_at":"2026-08-13T00:07:36.788733Z","submitted_at":"2024-05-14T23:24:12Z","title":"Contextual Emotion Recognition using Large Vision Language Models","version":2},"cited_work":{"arxiv_id":"2405.08992","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.08992","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Contextual emo- tion recognition using large vision language models","venue":null,"work_id":"03540583-4154-4595-bbde-05ae4859a04c","year":2024},"citing_paper":{"arxiv_id":"2604.25255","last_updated":"2026-04-28T06:02:23Z","snapshot_observed_at":"2026-07-06T23:11:07.254460Z","submitted_at":"2026-04-28T06:02:23Z","title":"Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-07T17:02:44.776943Z"},"links":{"cited_paper":"/paper/2405.08992","citing_paper":"/paper/2604.25255"},"observation_digest":"sha256:2af1ebb59e01dab9c5c08c42b0b92c8d3c5aa5fec5e25749215d9f26467ab53f","observation_id":"59132eb3-228a-4b9d-8448-210aac2e779f","resolution":{"observed_at":"2026-05-11T23:26:13.773911Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.08992/citation-record","integrity":"/paper/2405.08992/integrity","json":"/paper/2405.08992/citation-record.json","paper":"/paper/2405.08992"},"outbound":[],"paper":{"arxiv_id":"2405.08992","last_updated":"2025-01-31T18:53:30Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T00:07:36.788733Z","submitted_at":"2024-05-14T23:24:12Z","title":"Contextual Emotion Recognition using Large Vision 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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2405.08992."}