{"as_of":"2026-08-10T04:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c929975f428cb6037de4d63b54719f403cc235eef53d6d35ddd47429d3fc1b7e","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":"2026-08-04T13:29:57.017612Z","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":"2026-07-02T12:46:56.624171Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.08269","last_updated":"2025-04-11T05:51:44Z","snapshot_observed_at":"2026-08-07T16:06:38.584753Z","submitted_at":"2025-04-11T05:51:44Z","title":"VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.08269","snapshot_observed_at":"2026-08-04T13:29:57.017612Z","title":"Vlmt: Vision-language multimodal transformer for multimodal multi- hop question answering,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.07328","last_updated":"2026-07-09T05:29:24Z","snapshot_observed_at":"2026-08-07T08:51:58.794120Z","submitted_at":"2025-09-30T20:30:12Z","title":"MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T13:29:57.017612Z"},"links":{"cited_paper":"/paper/2504.08269","citing_paper":"/paper/2510.07328"},"observation_digest":"sha256:c9ffddf63bc0abd2af7ce0788a2546c3af2e8c7938870412d04153ac118fcd37","observation_id":"ed01cbd9-f911-4f3a-b349-b09013512c91","resolution":{"observed_at":"2026-08-04T13:29:57.017612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.08269","last_updated":"2025-04-11T05:51:44Z","snapshot_observed_at":"2026-08-07T16:06:38.584753Z","submitted_at":"2025-04-11T05:51:44Z","title":"VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering","version":1},"cited_work":{"arxiv_id":"2504.08269","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.08269","snapshot_observed_at":"2026-07-02T12:46:56.624171Z","title":"Vlmt: Vision- language multimodal transformer for multimodal multi-hop question answering.ArXiv, abs/2504.08269, 2025","venue":null,"work_id":"d480991d-e4e9-48af-b7bf-29be71c6fcc4","year":2025},"citing_paper":{"arxiv_id":"2606.05843","last_updated":"2026-06-04T08:18:31Z","snapshot_observed_at":"2026-08-07T20:51:53.666102Z","submitted_at":"2026-06-04T08:18:31Z","title":"Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T01:54:13.927736Z"},"links":{"cited_paper":"/paper/2504.08269","citing_paper":"/paper/2606.05843"},"observation_digest":"sha256:2b3fad59873f5a97f3ae18012e8beedf9c9e1f3aa35dbc68e4ba6c00950589d7","observation_id":"3b09c189-b6f4-4072-b995-5954bff139fb","resolution":{"observed_at":"2026-07-02T12:46:56.625600Z","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/2504.08269/citation-record","integrity":"/paper/2504.08269/integrity","json":"/paper/2504.08269/citation-record.json","paper":"/paper/2504.08269"},"outbound":[],"paper":{"arxiv_id":"2504.08269","last_updated":"2025-04-11T05:51:44Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:06:38.584753Z","submitted_at":"2025-04-11T05:51:44Z","title":"VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering"},"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 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2504.08269."}